window.WORLDMODELBENCH_CATALOG=[{"id":"ego4d_000786a73f9d4fe6","videoPath":"curated/spatial-world-model/v7/ego4d/videos/ego4d_000786a73f9d4fe6.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/ego4d/videos/ego4d_000786a73f9d4fe6.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/ego4d/initial_frames/ego4d_000786a73f9d4fe6.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"How does the camera wearer descend through the stairwell?","annotationPath":"curated/spatial-world-model/v7/ego4d/annotations/ego4d_000786a73f9d4fe6.json"},{"id":"ego4d_50d413f25709475d","videoPath":"curated/spatial-world-model/v7/ego4d/videos/ego4d_50d413f25709475d.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/ego4d/videos/ego4d_50d413f25709475d.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/ego4d/initial_frames/ego4d_50d413f25709475d.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"daily activity","spatialAbility":"Relative Spatial Relations, Topology and Containment","perspective":"Egocentric","caption":"What pad did I take out of the drawer?","annotationPath":"curated/spatial-world-model/v7/ego4d/annotations/ego4d_50d413f25709475d.json"},{"id":"ego4d_5d00d9aee93242d5","videoPath":"curated/spatial-world-model/v7/ego4d/videos/ego4d_5d00d9aee93242d5.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/ego4d/videos/ego4d_5d00d9aee93242d5.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/ego4d/initial_frames/ego4d_5d00d9aee93242d5.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"How does the camera wearer move through the stairwell?","annotationPath":"curated/spatial-world-model/v7/ego4d/annotations/ego4d_5d00d9aee93242d5.json"},{"id":"ego4d_65c16752c1574a21","videoPath":"curated/spatial-world-model/v7/ego4d/videos/ego4d_65c16752c1574a21.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/ego4d/videos/ego4d_65c16752c1574a21.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/ego4d/initial_frames/ego4d_65c16752c1574a21.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Topology and Containment","perspective":"Egocentric","caption":"What did I first take out of the freezer?","annotationPath":"curated/spatial-world-model/v7/ego4d/annotations/ego4d_65c16752c1574a21.json"},{"id":"ego4d_6d3939f5563643c7","videoPath":"curated/spatial-world-model/v7/ego4d/videos/ego4d_6d3939f5563643c7.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/ego4d/videos/ego4d_6d3939f5563643c7.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/ego4d/initial_frames/ego4d_6d3939f5563643c7.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"How does the camera wearer move from the stairwell toward the kitchen?","annotationPath":"curated/spatial-world-model/v7/ego4d/annotations/ego4d_6d3939f5563643c7.json"},{"id":"ego4d_8540abdbdb89442d","videoPath":"curated/spatial-world-model/v7/ego4d/videos/ego4d_8540abdbdb89442d.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/ego4d/videos/ego4d_8540abdbdb89442d.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/ego4d/initial_frames/ego4d_8540abdbdb89442d.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Topology and Containment","perspective":"Egocentric","caption":"What kitchen tool did I bring out of the cabinet?","annotationPath":"curated/spatial-world-model/v7/ego4d/annotations/ego4d_8540abdbdb89442d.json"},{"id":"ego4d_9e658f31c08a4b6d","videoPath":"curated/spatial-world-model/v7/ego4d/videos/ego4d_9e658f31c08a4b6d.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/ego4d/videos/ego4d_9e658f31c08a4b6d.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/ego4d/initial_frames/ego4d_9e658f31c08a4b6d.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"How does the camera wearer move along the uneven outdoor path?","annotationPath":"curated/spatial-world-model/v7/ego4d/annotations/ego4d_9e658f31c08a4b6d.json"},{"id":"ego4d_a86e5e870d724dd8","videoPath":"curated/spatial-world-model/v7/ego4d/videos/ego4d_a86e5e870d724dd8.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/ego4d/videos/ego4d_a86e5e870d724dd8.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/ego4d/initial_frames/ego4d_a86e5e870d724dd8.jpg","sourceDataset":"Ego4D","suggestedTrack":"coupled motion","scene":"daily activity","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How does the camera wearer carry the power tool down the stairwell?","annotationPath":"curated/spatial-world-model/v7/ego4d/annotations/ego4d_a86e5e870d724dd8.json"},{"id":"ego4d_candidate_00cc4aa761c2471f","videoPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_00cc4aa761c2471f.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_00cc4aa761c2471f.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/initial_frames/ego4d_candidate_00cc4aa761c2471f.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"What spatial motion is visible during Swimming in a pool/ocean?","annotationPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/annotations/ego4d_candidate_00cc4aa761c2471f.json"},{"id":"ego4d_candidate_025fa90bbf234023","videoPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_025fa90bbf234023.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_025fa90bbf234023.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/initial_frames/ego4d_candidate_025fa90bbf234023.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"driving","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"Where was the rag before i cleaned the floor with it ?","annotationPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/annotations/ego4d_candidate_025fa90bbf234023.json"},{"id":"ego4d_candidate_057670b3f243416c","videoPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_057670b3f243416c.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_057670b3f243416c.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/initial_frames/ego4d_candidate_057670b3f243416c.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion is visible during Going to the gym - exercise machine, class, weights?","annotationPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/annotations/ego4d_candidate_057670b3f243416c.json"},{"id":"ego4d_candidate_08496230ec8f4cb3","videoPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_08496230ec8f4cb3.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_08496230ec8f4cb3.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/initial_frames/ego4d_candidate_08496230ec8f4cb3.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"daily activity","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"Where was the yellow cup before I first left the bedroom","annotationPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/annotations/ego4d_candidate_08496230ec8f4cb3.json"},{"id":"ego4d_candidate_0df89feb74a648ca","videoPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_0df89feb74a648ca.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_0df89feb74a648ca.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/initial_frames/ego4d_candidate_0df89feb74a648ca.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion is visible during Bike | Going to the gym - exercise machine, class, weights?","annotationPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/annotations/ego4d_candidate_0df89feb74a648ca.json"},{"id":"ego4d_candidate_1eea73ff17814a36","videoPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_1eea73ff17814a36.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_1eea73ff17814a36.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/initial_frames/ego4d_candidate_1eea73ff17814a36.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What color was the bicycle","annotationPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/annotations/ego4d_candidate_1eea73ff17814a36.json"},{"id":"ego4d_candidate_1f82557c77a24245","videoPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_1f82557c77a24245.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_1f82557c77a24245.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/initial_frames/ego4d_candidate_1f82557c77a24245.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"Did I turn off the bicycle lights in the garage?","annotationPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/annotations/ego4d_candidate_1f82557c77a24245.json"},{"id":"ego4d_candidate_39084eacb4174e93","videoPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_39084eacb4174e93.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_39084eacb4174e93.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/initial_frames/ego4d_candidate_39084eacb4174e93.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"What spatial motion is visible during Outdoor technical climbing/belaying/rappelling (includes ropework)?","annotationPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/annotations/ego4d_candidate_39084eacb4174e93.json"},{"id":"ego4d_candidate_3c62f5e00afc48e9","videoPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_3c62f5e00afc48e9.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_3c62f5e00afc48e9.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/initial_frames/ego4d_candidate_3c62f5e00afc48e9.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion is visible during Attending sporting events - watching and participating in?","annotationPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/annotations/ego4d_candidate_3c62f5e00afc48e9.json"},{"id":"ego4d_candidate_414d6a2244f1438d","videoPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_414d6a2244f1438d.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_414d6a2244f1438d.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/initial_frames/ego4d_candidate_414d6a2244f1438d.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"daily activity","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"in what room did l play with a cat","annotationPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/annotations/ego4d_candidate_414d6a2244f1438d.json"},{"id":"ego4d_candidate_461ed176b687404b","videoPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_461ed176b687404b.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_461ed176b687404b.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/initial_frames/ego4d_candidate_461ed176b687404b.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"What spatial motion is visible during Walking on street | Working out outside?","annotationPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/annotations/ego4d_candidate_461ed176b687404b.json"},{"id":"ego4d_candidate_4bd37cffa43b4843","videoPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_4bd37cffa43b4843.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_4bd37cffa43b4843.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/initial_frames/ego4d_candidate_4bd37cffa43b4843.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry, Visibility and Occlusion","perspective":"Egocentric","caption":"How many bicycles were parked at the shop front","annotationPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/annotations/ego4d_candidate_4bd37cffa43b4843.json"},{"id":"ego4d_candidate_51b8e3588d284405","videoPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_51b8e3588d284405.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_51b8e3588d284405.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/initial_frames/ego4d_candidate_51b8e3588d284405.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"What spatial motion is visible during Outdoor technical climbing/belaying/rappelling (includes ropework)?","annotationPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/annotations/ego4d_candidate_51b8e3588d284405.json"},{"id":"ego4d_candidate_568e964d455e42f2","videoPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_568e964d455e42f2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_568e964d455e42f2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/initial_frames/ego4d_candidate_568e964d455e42f2.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"daily activity","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What tool did I remove the wood with?","annotationPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/annotations/ego4d_candidate_568e964d455e42f2.json"},{"id":"ego4d_candidate_633d1e83f3504983","videoPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_633d1e83f3504983.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_633d1e83f3504983.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/initial_frames/ego4d_candidate_633d1e83f3504983.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"daily activity","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What colour is the glue gun I dropped on the table?","annotationPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/annotations/ego4d_candidate_633d1e83f3504983.json"},{"id":"ego4d_candidate_676ef0a7a3904128","videoPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_676ef0a7a3904128.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_676ef0a7a3904128.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/initial_frames/ego4d_candidate_676ef0a7a3904128.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"put away (or take out) food items in the fridge","annotationPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/annotations/ego4d_candidate_676ef0a7a3904128.json"},{"id":"ego4d_candidate_74d38b4a6f2243b3","videoPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_74d38b4a6f2243b3.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_74d38b4a6f2243b3.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/initial_frames/ego4d_candidate_74d38b4a6f2243b3.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"Who did I talk to in the sitting room?","annotationPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/annotations/ego4d_candidate_74d38b4a6f2243b3.json"},{"id":"ego4d_candidate_7cad84ff4d084e18","videoPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_7cad84ff4d084e18.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_7cad84ff4d084e18.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/initial_frames/ego4d_candidate_7cad84ff4d084e18.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"driving","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"How many dust bins were on the road?","annotationPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/annotations/ego4d_candidate_7cad84ff4d084e18.json"},{"id":"ego4d_candidate_868b391620054bb0","videoPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_868b391620054bb0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_868b391620054bb0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/initial_frames/ego4d_candidate_868b391620054bb0.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"What spatial motion is visible during Outdoor social (includes campfire) | Outdoor technical climbing/belaying/rappelling (includes ropework)?","annotationPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/annotations/ego4d_candidate_868b391620054bb0.json"},{"id":"ego4d_candidate_8717d09f391c4203","videoPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_8717d09f391c4203.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_8717d09f391c4203.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/initial_frames/ego4d_candidate_8717d09f391c4203.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"driving","spatialAbility":"Relative Spatial Relations, Direction and Trajectory, Visibility and Occlusion","perspective":"Egocentric","caption":"What tool did I take out of my pocket?","annotationPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/annotations/ego4d_candidate_8717d09f391c4203.json"},{"id":"ego4d_candidate_8a551e975fd84fee","videoPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_8a551e975fd84fee.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_8a551e975fd84fee.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/initial_frames/ego4d_candidate_8a551e975fd84fee.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"daily activity","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"Did I switch on the light while entering the room?","annotationPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/annotations/ego4d_candidate_8a551e975fd84fee.json"},{"id":"ego4d_candidate_8d900b59e95d4c9b","videoPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_8d900b59e95d4c9b.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_8d900b59e95d4c9b.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/initial_frames/ego4d_candidate_8d900b59e95d4c9b.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"Did I turn-off my television?","annotationPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/annotations/ego4d_candidate_8d900b59e95d4c9b.json"},{"id":"ego4d_candidate_8e23dc4370254548","videoPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_8e23dc4370254548.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_8e23dc4370254548.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/initial_frames/ego4d_candidate_8e23dc4370254548.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"How many water buckets did I carry to bicycle?","annotationPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/annotations/ego4d_candidate_8e23dc4370254548.json"},{"id":"ego4d_candidate_8fd63cd644a54f3c","videoPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_8fd63cd644a54f3c.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_8fd63cd644a54f3c.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/initial_frames/ego4d_candidate_8fd63cd644a54f3c.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"What spatial motion is visible during Swimming in a pool/ocean?","annotationPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/annotations/ego4d_candidate_8fd63cd644a54f3c.json"},{"id":"ego4d_candidate_8fdc869727a34a1f","videoPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_8fdc869727a34a1f.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_8fdc869727a34a1f.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/initial_frames/ego4d_candidate_8fdc869727a34a1f.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"In what room did I saw the mirror?","annotationPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/annotations/ego4d_candidate_8fdc869727a34a1f.json"},{"id":"ego4d_candidate_96ec5200b456404f","videoPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_96ec5200b456404f.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_96ec5200b456404f.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/initial_frames/ego4d_candidate_96ec5200b456404f.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"What spatial motion is visible during Cycling / jogging | Grocery shopping indoors | Walking on street?","annotationPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/annotations/ego4d_candidate_96ec5200b456404f.json"},{"id":"ego4d_candidate_97e4effd1b194e02","videoPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_97e4effd1b194e02.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_97e4effd1b194e02.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/initial_frames/ego4d_candidate_97e4effd1b194e02.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"driving","spatialAbility":"Relative Spatial Relations, Direction and Trajectory, Visibility and Occlusion","perspective":"Egocentric","caption":"Where was the socket wrench after I went out of the workshop?","annotationPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/annotations/ego4d_candidate_97e4effd1b194e02.json"},{"id":"ego4d_candidate_a330bb337cef48d8","videoPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_a330bb337cef48d8.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_a330bb337cef48d8.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/initial_frames/ego4d_candidate_a330bb337cef48d8.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"natural scenery","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"who did I interact with when I placed the white and green cover on the tent?","annotationPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/annotations/ego4d_candidate_a330bb337cef48d8.json"},{"id":"ego4d_candidate_a6c7707dd7b54e73","videoPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_a6c7707dd7b54e73.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_a6c7707dd7b54e73.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/initial_frames/ego4d_candidate_a6c7707dd7b54e73.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"What spatial motion is visible during Cycling / jogging | Indoor Navigation (walking)?","annotationPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/annotations/ego4d_candidate_a6c7707dd7b54e73.json"},{"id":"ego4d_candidate_a724d61135fa498b","videoPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_a724d61135fa498b.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_a724d61135fa498b.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/initial_frames/ego4d_candidate_a724d61135fa498b.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"Where did I see the coffee maker?","annotationPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/annotations/ego4d_candidate_a724d61135fa498b.json"},{"id":"ego4d_candidate_a887acbeefd548e2","videoPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_a887acbeefd548e2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_a887acbeefd548e2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/initial_frames/ego4d_candidate_a887acbeefd548e2.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"Where were the sandals before I walked towards the countertop?","annotationPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/annotations/ego4d_candidate_a887acbeefd548e2.json"},{"id":"ego4d_candidate_bef14b0444c149f2","videoPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_bef14b0444c149f2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_bef14b0444c149f2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/initial_frames/ego4d_candidate_bef14b0444c149f2.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What did i remove from the bicycle tire?","annotationPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/annotations/ego4d_candidate_bef14b0444c149f2.json"},{"id":"ego4d_candidate_c037be7ae56b4053","videoPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_c037be7ae56b4053.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_c037be7ae56b4053.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/initial_frames/ego4d_candidate_c037be7ae56b4053.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What did i fix on the motorcycle with my hand?","annotationPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/annotations/ego4d_candidate_c037be7ae56b4053.json"},{"id":"ego4d_candidate_c181b3b003554f97","videoPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_c181b3b003554f97.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_c181b3b003554f97.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/initial_frames/ego4d_candidate_c181b3b003554f97.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"What spatial motion is visible during Swimming in a pool/ocean?","annotationPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/annotations/ego4d_candidate_c181b3b003554f97.json"},{"id":"ego4d_candidate_c58e188703144cb3","videoPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_c58e188703144cb3.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_c58e188703144cb3.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/initial_frames/ego4d_candidate_c58e188703144cb3.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion is visible during Gaming arcade / pool / billiards?","annotationPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/annotations/ego4d_candidate_c58e188703144cb3.json"},{"id":"ego4d_candidate_cb768fa730904d9c","videoPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_cb768fa730904d9c.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_cb768fa730904d9c.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/initial_frames/ego4d_candidate_cb768fa730904d9c.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion is visible during Attending sporting events - watching and participating in?","annotationPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/annotations/ego4d_candidate_cb768fa730904d9c.json"},{"id":"ego4d_candidate_ceea3a9083394512","videoPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_ceea3a9083394512.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_ceea3a9083394512.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/initial_frames/ego4d_candidate_ceea3a9083394512.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"put away (or take out) dishes utensils in storage","annotationPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/annotations/ego4d_candidate_ceea3a9083394512.json"},{"id":"ego4d_candidate_cf90f24b32de452a","videoPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_cf90f24b32de452a.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_cf90f24b32de452a.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/initial_frames/ego4d_candidate_cf90f24b32de452a.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion is visible during Listening to music | Working out at home?","annotationPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/annotations/ego4d_candidate_cf90f24b32de452a.json"},{"id":"ego4d_candidate_d8dfeeda494b4bd2","videoPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_d8dfeeda494b4bd2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_d8dfeeda494b4bd2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/initial_frames/ego4d_candidate_d8dfeeda494b4bd2.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"driving","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"Where was the drill driver before I left the room?","annotationPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/annotations/ego4d_candidate_d8dfeeda494b4bd2.json"},{"id":"ego4d_candidate_ec9f9e41aa3d4466","videoPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_ec9f9e41aa3d4466.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_ec9f9e41aa3d4466.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/initial_frames/ego4d_candidate_ec9f9e41aa3d4466.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"What spatial motion is visible during Outdoor technical climbing/belaying/rappelling (includes ropework)?","annotationPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/annotations/ego4d_candidate_ec9f9e41aa3d4466.json"},{"id":"ego4d_candidate_f5161d434fa84aed","videoPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_f5161d434fa84aed.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_f5161d434fa84aed.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/initial_frames/ego4d_candidate_f5161d434fa84aed.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion is visible during Attending sporting events - watching and participating in | Talking to colleagues | Working out outside?","annotationPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/annotations/ego4d_candidate_f5161d434fa84aed.json"},{"id":"ego4d_candidate_fdcdf464a350452d","videoPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_fdcdf464a350452d.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/videos/ego4d_candidate_fdcdf464a350452d.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/ego4d-candidate-pool/initial_frames/ego4d_candidate_fdcdf464a350452d.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"Who did I interact with when I last turned the bicycle pedal","annotationPath":"curated/spatial-world-model/v8/ego4d-candidate-pool/annotations/ego4d_candidate_fdcdf464a350452d.json"},{"id":"ego4d_dd08bc58b6144ba7","videoPath":"curated/spatial-world-model/v7/ego4d/videos/ego4d_dd08bc58b6144ba7.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/ego4d/videos/ego4d_dd08bc58b6144ba7.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/ego4d/initial_frames/ego4d_dd08bc58b6144ba7.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"How does the camera wearer navigate from the dining area through the stairwell?","annotationPath":"curated/spatial-world-model/v7/ego4d/annotations/ego4d_dd08bc58b6144ba7.json"},{"id":"ego4d_eff7f167e828421f","videoPath":"curated/spatial-world-model/v7/ego4d/videos/ego4d_eff7f167e828421f.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/ego4d/videos/ego4d_eff7f167e828421f.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/ego4d/initial_frames/ego4d_eff7f167e828421f.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Topology and Containment","perspective":"Egocentric","caption":"What container did I take from the fridge?","annotationPath":"curated/spatial-world-model/v7/ego4d/annotations/ego4d_eff7f167e828421f.json"},{"id":"ego4d_targeted_01aed4ae486e41eb","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_01aed4ae486e41eb.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_01aed4ae486e41eb.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_01aed4ae486e41eb.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Bike mechanic activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_01aed4ae486e41eb.json"},{"id":"ego4d_targeted_03551c71b8ec4a5d","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_03551c71b8ec4a5d.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_03551c71b8ec4a5d.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_03551c71b8ec4a5d.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Cooking activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_03551c71b8ec4a5d.json"},{"id":"ego4d_targeted_0755c2cbeb914e44","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_0755c2cbeb914e44.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_0755c2cbeb914e44.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_0755c2cbeb914e44.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Bike mechanic activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_0755c2cbeb914e44.json"},{"id":"ego4d_targeted_0780244de06c413a","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_0780244de06c413a.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_0780244de06c413a.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_0780244de06c413a.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Cooking activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_0780244de06c413a.json"},{"id":"ego4d_targeted_0a4c05dff5224a33","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_0a4c05dff5224a33.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_0a4c05dff5224a33.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_0a4c05dff5224a33.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"What spatial motion occurs during this Outdoor technical climbing/belaying/rappelling (includes ropework) activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_0a4c05dff5224a33.json"},{"id":"ego4d_targeted_0b8a87ed07f24434","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_0b8a87ed07f24434.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_0b8a87ed07f24434.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_0b8a87ed07f24434.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Bike mechanic activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_0b8a87ed07f24434.json"},{"id":"ego4d_targeted_0c3f8dc4f8994319","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_0c3f8dc4f8994319.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_0c3f8dc4f8994319.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_0c3f8dc4f8994319.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Cooking activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_0c3f8dc4f8994319.json"},{"id":"ego4d_targeted_0ce20f1b104c48aa","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_0ce20f1b104c48aa.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_0ce20f1b104c48aa.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_0ce20f1b104c48aa.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Golfing activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_0ce20f1b104c48aa.json"},{"id":"ego4d_targeted_0e46fbaead104a8e","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_0e46fbaead104a8e.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_0e46fbaead104a8e.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_0e46fbaead104a8e.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Bike mechanic activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_0e46fbaead104a8e.json"},{"id":"ego4d_targeted_114cdc4b4ae54938","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_114cdc4b4ae54938.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_114cdc4b4ae54938.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_114cdc4b4ae54938.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"What spatial motion occurs during this BasketBall | Walking on street activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_114cdc4b4ae54938.json"},{"id":"ego4d_targeted_11f1a11dfa7d442c","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_11f1a11dfa7d442c.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_11f1a11dfa7d442c.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_11f1a11dfa7d442c.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"What spatial motion occurs during this Outdoor technical climbing/belaying/rappelling (includes ropework) activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_11f1a11dfa7d442c.json"},{"id":"ego4d_targeted_126fe8f1226a4161","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_126fe8f1226a4161.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_126fe8f1226a4161.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_126fe8f1226a4161.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Cooking activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_126fe8f1226a4161.json"},{"id":"ego4d_targeted_1314208bb64d4ebc","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_1314208bb64d4ebc.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_1314208bb64d4ebc.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_1314208bb64d4ebc.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Cooking activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_1314208bb64d4ebc.json"},{"id":"ego4d_targeted_143f43b631084977","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_143f43b631084977.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_143f43b631084977.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_143f43b631084977.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Cooking activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_143f43b631084977.json"},{"id":"ego4d_targeted_1689d60b69144204","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_1689d60b69144204.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_1689d60b69144204.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_1689d60b69144204.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"What spatial motion occurs during this Cycling / jogging activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_1689d60b69144204.json"},{"id":"ego4d_targeted_16dc0b0576d44b80","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_16dc0b0576d44b80.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_16dc0b0576d44b80.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_16dc0b0576d44b80.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Bike mechanic activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_16dc0b0576d44b80.json"},{"id":"ego4d_targeted_17e336f33c84403a","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_17e336f33c84403a.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_17e336f33c84403a.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_17e336f33c84403a.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Bike mechanic activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_17e336f33c84403a.json"},{"id":"ego4d_targeted_1a36f5e096404b3e","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_1a36f5e096404b3e.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_1a36f5e096404b3e.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_1a36f5e096404b3e.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Skateboard/scooter activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_1a36f5e096404b3e.json"},{"id":"ego4d_targeted_1aa28dece81d4a76","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_1aa28dece81d4a76.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_1aa28dece81d4a76.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_1aa28dece81d4a76.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Cooking activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_1aa28dece81d4a76.json"},{"id":"ego4d_targeted_1d664e9ce8bb477d","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_1d664e9ce8bb477d.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_1d664e9ce8bb477d.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_1d664e9ce8bb477d.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Bike mechanic activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_1d664e9ce8bb477d.json"},{"id":"ego4d_targeted_1e02cef3e85748fc","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_1e02cef3e85748fc.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_1e02cef3e85748fc.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_1e02cef3e85748fc.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Bike mechanic activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_1e02cef3e85748fc.json"},{"id":"ego4d_targeted_1ea5b82f85ab4b05","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_1ea5b82f85ab4b05.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_1ea5b82f85ab4b05.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_1ea5b82f85ab4b05.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Bike mechanic activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_1ea5b82f85ab4b05.json"},{"id":"ego4d_targeted_2043d7fac369431e","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_2043d7fac369431e.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_2043d7fac369431e.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_2043d7fac369431e.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"daily activity","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Baker activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_2043d7fac369431e.json"},{"id":"ego4d_targeted_2329f80344b14654","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_2329f80344b14654.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_2329f80344b14654.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_2329f80344b14654.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"What colors were the socks my colleague pulled off?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_2329f80344b14654.json"},{"id":"ego4d_targeted_2893d55989cb4125","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_2893d55989cb4125.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_2893d55989cb4125.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_2893d55989cb4125.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"What spatial motion occurs during this Cycling / jogging activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_2893d55989cb4125.json"},{"id":"ego4d_targeted_28e0affccacb4db8","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_28e0affccacb4db8.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_28e0affccacb4db8.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_28e0affccacb4db8.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Cooking activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_28e0affccacb4db8.json"},{"id":"ego4d_targeted_29885a2404cb4045","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_29885a2404cb4045.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_29885a2404cb4045.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_29885a2404cb4045.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Bike mechanic activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_29885a2404cb4045.json"},{"id":"ego4d_targeted_2f0035c97efb4229","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_2f0035c97efb4229.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_2f0035c97efb4229.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_2f0035c97efb4229.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"where was the dustbin before I crossed the road?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_2f0035c97efb4229.json"},{"id":"ego4d_targeted_31a7128fd22b4332","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_31a7128fd22b4332.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_31a7128fd22b4332.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_31a7128fd22b4332.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Cooking | Talking with family members activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_31a7128fd22b4332.json"},{"id":"ego4d_targeted_326eb377b02b43c8","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_326eb377b02b43c8.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_326eb377b02b43c8.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_326eb377b02b43c8.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this BasketBall | Car - commuting, road trip activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_326eb377b02b43c8.json"},{"id":"ego4d_targeted_35ab724d5dba4094","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_35ab724d5dba4094.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_35ab724d5dba4094.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_35ab724d5dba4094.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"put away (or take out) food items in the fridge","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_35ab724d5dba4094.json"},{"id":"ego4d_targeted_38473fe0831144f0","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_38473fe0831144f0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_38473fe0831144f0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_38473fe0831144f0.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Bike mechanic activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_38473fe0831144f0.json"},{"id":"ego4d_targeted_3ab744ba9969452c","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_3ab744ba9969452c.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_3ab744ba9969452c.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_3ab744ba9969452c.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Football activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_3ab744ba9969452c.json"},{"id":"ego4d_targeted_3f19900e6ea1437c","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_3f19900e6ea1437c.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_3f19900e6ea1437c.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_3f19900e6ea1437c.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Attending sporting events - watching and participating in | Football | Talking to colleagues activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_3f19900e6ea1437c.json"},{"id":"ego4d_targeted_43d01891033e49f1","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_43d01891033e49f1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_43d01891033e49f1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_43d01891033e49f1.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"What spatial motion occurs during this Climbing activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_43d01891033e49f1.json"},{"id":"ego4d_targeted_45219b12354649ff","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_45219b12354649ff.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_45219b12354649ff.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_45219b12354649ff.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Bike mechanic activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_45219b12354649ff.json"},{"id":"ego4d_targeted_470499d1e0154d45","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_470499d1e0154d45.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_470499d1e0154d45.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_470499d1e0154d45.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"daily activity","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Dancing activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_470499d1e0154d45.json"},{"id":"ego4d_targeted_487ca35f25c64e5d","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_487ca35f25c64e5d.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_487ca35f25c64e5d.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_487ca35f25c64e5d.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"daily activity","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Baker activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_487ca35f25c64e5d.json"},{"id":"ego4d_targeted_490a50c0988d4091","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_490a50c0988d4091.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_490a50c0988d4091.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_490a50c0988d4091.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Cooking activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_490a50c0988d4091.json"},{"id":"ego4d_targeted_4ca97ff8bc2a462b","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_4ca97ff8bc2a462b.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_4ca97ff8bc2a462b.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_4ca97ff8bc2a462b.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"daily activity","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Dancing activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_4ca97ff8bc2a462b.json"},{"id":"ego4d_targeted_4e4401970547456f","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_4e4401970547456f.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_4e4401970547456f.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_4e4401970547456f.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Bike mechanic activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_4e4401970547456f.json"},{"id":"ego4d_targeted_503b03fe37f147cd","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_503b03fe37f147cd.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_503b03fe37f147cd.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_503b03fe37f147cd.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"What spatial motion occurs during this Climbing activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_503b03fe37f147cd.json"},{"id":"ego4d_targeted_520374ca09f94716","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_520374ca09f94716.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_520374ca09f94716.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_520374ca09f94716.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"What spatial motion occurs during this Outdoor technical climbing/belaying/rappelling (includes ropework) activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_520374ca09f94716.json"},{"id":"ego4d_targeted_6064dfcb3fee4f37","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_6064dfcb3fee4f37.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_6064dfcb3fee4f37.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_6064dfcb3fee4f37.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"What spatial motion occurs during this Outdoor technical climbing/belaying/rappelling (includes ropework) activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_6064dfcb3fee4f37.json"},{"id":"ego4d_targeted_60b0ccb649f74a44","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_60b0ccb649f74a44.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_60b0ccb649f74a44.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_60b0ccb649f74a44.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Cooking activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_60b0ccb649f74a44.json"},{"id":"ego4d_targeted_62e3b74a01ad4824","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_62e3b74a01ad4824.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_62e3b74a01ad4824.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_62e3b74a01ad4824.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"What spatial motion occurs during this Outdoor technical climbing/belaying/rappelling (includes ropework) activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_62e3b74a01ad4824.json"},{"id":"ego4d_targeted_630ccf3a06924531","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_630ccf3a06924531.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_630ccf3a06924531.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_630ccf3a06924531.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"daily activity","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Dancing activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_630ccf3a06924531.json"},{"id":"ego4d_targeted_6606c60b1ed94b78","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_6606c60b1ed94b78.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_6606c60b1ed94b78.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_6606c60b1ed94b78.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"What spatial motion occurs during this Cycling / jogging activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_6606c60b1ed94b78.json"},{"id":"ego4d_targeted_6667265c5d064072","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_6667265c5d064072.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_6667265c5d064072.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_6667265c5d064072.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Bike mechanic activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_6667265c5d064072.json"},{"id":"ego4d_targeted_66fc3efaaa5a4bf4","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_66fc3efaaa5a4bf4.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_66fc3efaaa5a4bf4.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_66fc3efaaa5a4bf4.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Bike mechanic activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_66fc3efaaa5a4bf4.json"},{"id":"ego4d_targeted_6fe7244f3a334d67","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_6fe7244f3a334d67.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_6fe7244f3a334d67.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_6fe7244f3a334d67.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Bike mechanic activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_6fe7244f3a334d67.json"},{"id":"ego4d_targeted_72c81e6086044897","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_72c81e6086044897.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_72c81e6086044897.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_72c81e6086044897.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"daily activity","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Dancing activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_72c81e6086044897.json"},{"id":"ego4d_targeted_7306232f31cc46bc","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_7306232f31cc46bc.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_7306232f31cc46bc.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_7306232f31cc46bc.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"What spatial motion occurs during this Cycling / jogging activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_7306232f31cc46bc.json"},{"id":"ego4d_targeted_747ca62c333e472a","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_747ca62c333e472a.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_747ca62c333e472a.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_747ca62c333e472a.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Bike mechanic activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_747ca62c333e472a.json"},{"id":"ego4d_targeted_775acd8e086f48cf","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_775acd8e086f48cf.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_775acd8e086f48cf.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_775acd8e086f48cf.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this BasketBall | Going to the park activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_775acd8e086f48cf.json"},{"id":"ego4d_targeted_786877d8e3534fae","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_786877d8e3534fae.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_786877d8e3534fae.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_786877d8e3534fae.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"daily activity","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Dancing activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_786877d8e3534fae.json"},{"id":"ego4d_targeted_793a9c9d327e4457","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_793a9c9d327e4457.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_793a9c9d327e4457.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_793a9c9d327e4457.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Cooking activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_793a9c9d327e4457.json"},{"id":"ego4d_targeted_7989f7d6cfc7423d","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_7989f7d6cfc7423d.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_7989f7d6cfc7423d.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_7989f7d6cfc7423d.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Bike mechanic activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_7989f7d6cfc7423d.json"},{"id":"ego4d_targeted_7d43e858fc764f75","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_7d43e858fc764f75.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_7d43e858fc764f75.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_7d43e858fc764f75.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Bike mechanic activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_7d43e858fc764f75.json"},{"id":"ego4d_targeted_7f3344585c4c4223","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_7f3344585c4c4223.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_7f3344585c4c4223.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_7f3344585c4c4223.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Bike mechanic activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_7f3344585c4c4223.json"},{"id":"ego4d_targeted_8065f48179cd443f","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_8065f48179cd443f.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_8065f48179cd443f.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_8065f48179cd443f.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Bike mechanic activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_8065f48179cd443f.json"},{"id":"ego4d_targeted_820d4b9e6fba472f","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_820d4b9e6fba472f.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_820d4b9e6fba472f.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_820d4b9e6fba472f.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Football | Working out outside activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_820d4b9e6fba472f.json"},{"id":"ego4d_targeted_82c57c2c45e84a1e","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_82c57c2c45e84a1e.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_82c57c2c45e84a1e.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_82c57c2c45e84a1e.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"daily activity","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Baker activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_82c57c2c45e84a1e.json"},{"id":"ego4d_targeted_834c74a73c9f4869","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_834c74a73c9f4869.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_834c74a73c9f4869.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_834c74a73c9f4869.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"What spatial motion occurs during this Outdoor technical climbing/belaying/rappelling (includes ropework) activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_834c74a73c9f4869.json"},{"id":"ego4d_targeted_83fd2efb168e4d90","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_83fd2efb168e4d90.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_83fd2efb168e4d90.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_83fd2efb168e4d90.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"What spatial motion occurs during this Cycling / jogging | Going to the park activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_83fd2efb168e4d90.json"},{"id":"ego4d_targeted_86fb4797274f4807","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_86fb4797274f4807.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_86fb4797274f4807.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_86fb4797274f4807.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"What spatial motion occurs during this Outdoor social (includes campfire) | Outdoor technical climbing/belaying/rappelling (includes ropework) activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_86fb4797274f4807.json"},{"id":"ego4d_targeted_879c0eaecc234dea","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_879c0eaecc234dea.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_879c0eaecc234dea.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_879c0eaecc234dea.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Bike mechanic activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_879c0eaecc234dea.json"},{"id":"ego4d_targeted_887a1aaa2b7e41d4","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_887a1aaa2b7e41d4.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_887a1aaa2b7e41d4.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_887a1aaa2b7e41d4.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Bike mechanic activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_887a1aaa2b7e41d4.json"},{"id":"ego4d_targeted_8b82db7f5c394850","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_8b82db7f5c394850.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_8b82db7f5c394850.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_8b82db7f5c394850.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"What spatial motion occurs during this Outdoor technical climbing/belaying/rappelling (includes ropework) activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_8b82db7f5c394850.json"},{"id":"ego4d_targeted_8dd63cb06b7b401d","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_8dd63cb06b7b401d.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_8dd63cb06b7b401d.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_8dd63cb06b7b401d.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Bike mechanic activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_8dd63cb06b7b401d.json"},{"id":"ego4d_targeted_8f91bc0d9ce74b31","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_8f91bc0d9ce74b31.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_8f91bc0d9ce74b31.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_8f91bc0d9ce74b31.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Cooking activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_8f91bc0d9ce74b31.json"},{"id":"ego4d_targeted_9164a62a31c94610","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_9164a62a31c94610.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_9164a62a31c94610.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_9164a62a31c94610.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this BasketBall | Going to the park | On a screen (phone/laptop) activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_9164a62a31c94610.json"},{"id":"ego4d_targeted_948317e174264bfa","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_948317e174264bfa.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_948317e174264bfa.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_948317e174264bfa.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"daily activity","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Dancing activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_948317e174264bfa.json"},{"id":"ego4d_targeted_949dd155f6584cd4","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_949dd155f6584cd4.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_949dd155f6584cd4.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_949dd155f6584cd4.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"What spatial motion occurs during this Cycling / jogging activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_949dd155f6584cd4.json"},{"id":"ego4d_targeted_983190f9ce86428c","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_983190f9ce86428c.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_983190f9ce86428c.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_983190f9ce86428c.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Cooking activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_983190f9ce86428c.json"},{"id":"ego4d_targeted_a1d5e8d531d84ef0","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_a1d5e8d531d84ef0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_a1d5e8d531d84ef0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_a1d5e8d531d84ef0.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Bike mechanic activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_a1d5e8d531d84ef0.json"},{"id":"ego4d_targeted_a4657809c8d244e1","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_a4657809c8d244e1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_a4657809c8d244e1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_a4657809c8d244e1.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"What spatial motion occurs during this Outdoor technical climbing/belaying/rappelling (includes ropework) activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_a4657809c8d244e1.json"},{"id":"ego4d_targeted_a4745642be2d4d15","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_a4745642be2d4d15.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_a4745642be2d4d15.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_a4745642be2d4d15.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Bike mechanic activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_a4745642be2d4d15.json"},{"id":"ego4d_targeted_a655a89719ed4466","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_a655a89719ed4466.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_a655a89719ed4466.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_a655a89719ed4466.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"What car did I go under?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_a655a89719ed4466.json"},{"id":"ego4d_targeted_a69ae4a88e1d47c1","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_a69ae4a88e1d47c1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_a69ae4a88e1d47c1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_a69ae4a88e1d47c1.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"How many bolts did I pick from the floor?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_a69ae4a88e1d47c1.json"},{"id":"ego4d_targeted_aa3aa45aab0a4f3e","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_aa3aa45aab0a4f3e.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_aa3aa45aab0a4f3e.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_aa3aa45aab0a4f3e.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Bike mechanic activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_aa3aa45aab0a4f3e.json"},{"id":"ego4d_targeted_ab6f68a2e5ba48ce","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_ab6f68a2e5ba48ce.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_ab6f68a2e5ba48ce.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_ab6f68a2e5ba48ce.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"What spatial motion occurs during this Outdoor technical climbing/belaying/rappelling (includes ropework) activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_ab6f68a2e5ba48ce.json"},{"id":"ego4d_targeted_af72c57cb24248b2","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_af72c57cb24248b2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_af72c57cb24248b2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_af72c57cb24248b2.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this BasketBall | Car - commuting, road trip | Going to the park activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_af72c57cb24248b2.json"},{"id":"ego4d_targeted_b30bf1cd0b5c4635","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_b30bf1cd0b5c4635.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_b30bf1cd0b5c4635.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_b30bf1cd0b5c4635.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Bike mechanic activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_b30bf1cd0b5c4635.json"},{"id":"ego4d_targeted_b4a8cf836f0e40ca","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_b4a8cf836f0e40ca.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_b4a8cf836f0e40ca.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_b4a8cf836f0e40ca.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Bike mechanic activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_b4a8cf836f0e40ca.json"},{"id":"ego4d_targeted_b79c14ac16fd4406","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_b79c14ac16fd4406.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_b79c14ac16fd4406.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_b79c14ac16fd4406.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"What spatial motion occurs during this Outdoor technical climbing/belaying/rappelling (includes ropework) activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_b79c14ac16fd4406.json"},{"id":"ego4d_targeted_b7bf3a7b9ff247cf","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_b7bf3a7b9ff247cf.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_b7bf3a7b9ff247cf.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_b7bf3a7b9ff247cf.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Cooking activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_b7bf3a7b9ff247cf.json"},{"id":"ego4d_targeted_b892e2cb259b467d","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_b892e2cb259b467d.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_b892e2cb259b467d.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_b892e2cb259b467d.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Bike mechanic activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_b892e2cb259b467d.json"},{"id":"ego4d_targeted_b8cf405f3d36448c","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_b8cf405f3d36448c.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_b8cf405f3d36448c.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_b8cf405f3d36448c.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"What spatial motion occurs during this Outdoor technical climbing/belaying/rappelling (includes ropework) activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_b8cf405f3d36448c.json"},{"id":"ego4d_targeted_bb77b981d50d444d","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_bb77b981d50d444d.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_bb77b981d50d444d.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_bb77b981d50d444d.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"What spatial motion occurs during this Cycling / jogging activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_bb77b981d50d444d.json"},{"id":"ego4d_targeted_be7ede7ac21245ff","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_be7ede7ac21245ff.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_be7ede7ac21245ff.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_be7ede7ac21245ff.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this BasketBall | Car - commuting, road trip activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_be7ede7ac21245ff.json"},{"id":"ego4d_targeted_beaa0a850b754540","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_beaa0a850b754540.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_beaa0a850b754540.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_beaa0a850b754540.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Cooking activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_beaa0a850b754540.json"},{"id":"ego4d_targeted_c0028015e421470b","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_c0028015e421470b.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_c0028015e421470b.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_c0028015e421470b.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Bike mechanic activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_c0028015e421470b.json"},{"id":"ego4d_targeted_c2e5f216057244ba","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_c2e5f216057244ba.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_c2e5f216057244ba.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_c2e5f216057244ba.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"What spatial motion occurs during this Cycling / jogging activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_c2e5f216057244ba.json"},{"id":"ego4d_targeted_c336101789994dfb","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_c336101789994dfb.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_c336101789994dfb.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_c336101789994dfb.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Bike mechanic activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_c336101789994dfb.json"},{"id":"ego4d_targeted_c48a70f744a344aa","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_c48a70f744a344aa.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_c48a70f744a344aa.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_c48a70f744a344aa.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this BasketBall activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_c48a70f744a344aa.json"},{"id":"ego4d_targeted_c604786851a34bb8","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_c604786851a34bb8.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_c604786851a34bb8.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_c604786851a34bb8.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this BasketBall activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_c604786851a34bb8.json"},{"id":"ego4d_targeted_c6d92468586f483d","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_c6d92468586f483d.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_c6d92468586f483d.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_c6d92468586f483d.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Cooking activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_c6d92468586f483d.json"},{"id":"ego4d_targeted_c9b40d8d7cb54ce7","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_c9b40d8d7cb54ce7.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_c9b40d8d7cb54ce7.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_c9b40d8d7cb54ce7.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Bike mechanic activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_c9b40d8d7cb54ce7.json"},{"id":"ego4d_targeted_ca6e9ec946ac4a02","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_ca6e9ec946ac4a02.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_ca6e9ec946ac4a02.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_ca6e9ec946ac4a02.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Cooking activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_ca6e9ec946ac4a02.json"},{"id":"ego4d_targeted_cce95cd8188e4d6b","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_cce95cd8188e4d6b.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_cce95cd8188e4d6b.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_cce95cd8188e4d6b.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Bike mechanic activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_cce95cd8188e4d6b.json"},{"id":"ego4d_targeted_d31d3761f88c4441","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_d31d3761f88c4441.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_d31d3761f88c4441.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_d31d3761f88c4441.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Cooking activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_d31d3761f88c4441.json"},{"id":"ego4d_targeted_d70be6cb867f4657","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_d70be6cb867f4657.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_d70be6cb867f4657.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_d70be6cb867f4657.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"What spatial motion occurs during this Outdoor technical climbing/belaying/rappelling (includes ropework) activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_d70be6cb867f4657.json"},{"id":"ego4d_targeted_d8e20ed11d8849f1","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_d8e20ed11d8849f1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_d8e20ed11d8849f1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_d8e20ed11d8849f1.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"Where is parked bike?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_d8e20ed11d8849f1.json"},{"id":"ego4d_targeted_db57792ce868468f","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_db57792ce868468f.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_db57792ce868468f.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_db57792ce868468f.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Cleaning / laundry | Cooking | Eating activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_db57792ce868468f.json"},{"id":"ego4d_targeted_dc708402b9184bef","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_dc708402b9184bef.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_dc708402b9184bef.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_dc708402b9184bef.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Football activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_dc708402b9184bef.json"},{"id":"ego4d_targeted_e256810fee9f4580","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_e256810fee9f4580.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_e256810fee9f4580.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_e256810fee9f4580.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"What spatial motion occurs during this Outdoor technical climbing/belaying/rappelling (includes ropework) activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_e256810fee9f4580.json"},{"id":"ego4d_targeted_e27f2af481224a23","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_e27f2af481224a23.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_e27f2af481224a23.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_e27f2af481224a23.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Bike mechanic activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_e27f2af481224a23.json"},{"id":"ego4d_targeted_e6d852dd2510482f","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_e6d852dd2510482f.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_e6d852dd2510482f.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_e6d852dd2510482f.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"What spatial motion occurs during this Outdoor technical climbing/belaying/rappelling (includes ropework) activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_e6d852dd2510482f.json"},{"id":"ego4d_targeted_e968df0e702a490c","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_e968df0e702a490c.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_e968df0e702a490c.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_e968df0e702a490c.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"What spatial motion occurs during this Outdoor technical climbing/belaying/rappelling (includes ropework) activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_e968df0e702a490c.json"},{"id":"ego4d_targeted_eac69ea67f0a4aa9","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_eac69ea67f0a4aa9.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_eac69ea67f0a4aa9.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_eac69ea67f0a4aa9.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Cooking activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_eac69ea67f0a4aa9.json"},{"id":"ego4d_targeted_ec55e7991d1d4faa","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_ec55e7991d1d4faa.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_ec55e7991d1d4faa.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_ec55e7991d1d4faa.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Bike mechanic activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_ec55e7991d1d4faa.json"},{"id":"ego4d_targeted_ed5791ed49ec4dca","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_ed5791ed49ec4dca.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_ed5791ed49ec4dca.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_ed5791ed49ec4dca.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"throw away trash put trash in trash can","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_ed5791ed49ec4dca.json"},{"id":"ego4d_targeted_eef71c56a40e4602","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_eef71c56a40e4602.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_eef71c56a40e4602.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_eef71c56a40e4602.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Cooking activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_eef71c56a40e4602.json"},{"id":"ego4d_targeted_f2f4eeaa49a24c01","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_f2f4eeaa49a24c01.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_f2f4eeaa49a24c01.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_f2f4eeaa49a24c01.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"What spatial motion occurs during this Cycling / jogging activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_f2f4eeaa49a24c01.json"},{"id":"ego4d_targeted_f589943495bc4cd3","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_f589943495bc4cd3.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_f589943495bc4cd3.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_f589943495bc4cd3.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"fix bicycle bike motorcycle chain","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_f589943495bc4cd3.json"},{"id":"ego4d_targeted_f97b9bb69afc4743","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_f97b9bb69afc4743.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_f97b9bb69afc4743.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_f97b9bb69afc4743.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"What spatial motion occurs during this Outdoor technical climbing/belaying/rappelling (includes ropework) activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_f97b9bb69afc4743.json"},{"id":"ego4d_targeted_fdd7011602cb44be","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_fdd7011602cb44be.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_fdd7011602cb44be.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_fdd7011602cb44be.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"What spatial motion occurs during this Bike | Cycling / jogging activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_fdd7011602cb44be.json"},{"id":"ego4d_targeted_ff82e459790a4bbd","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_ff82e459790a4bbd.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_ff82e459790a4bbd.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_ff82e459790a4bbd.jpg","sourceDataset":"Ego4D","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"What spatial motion occurs during this Cycling / jogging activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_ff82e459790a4bbd.json"},{"id":"ego4d_targeted_ffa8e210b20b4a22","videoPath":"curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_ffa8e210b20b4a22.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/videos/ego4d_targeted_ffa8e210b20b4a22.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/ego4d-targeted/initial_frames/ego4d_targeted_ffa8e210b20b4a22.jpg","sourceDataset":"Ego4D","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory","perspective":"Egocentric","caption":"What spatial motion occurs during this Attending sporting events - watching and participating in activity?","annotationPath":"curated/spatial-world-model/v11/ego4d-targeted/annotations/ego4d_targeted_ffa8e210b20b4a22.json"},{"id":"had_test0001","videoPath":"curated/spatial-world-model/v4/stage-b/had-advice-batch-005/videos/viewpoint_motion/had_test0001.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/had-advice-batch-005/videos/viewpoint_motion/had_test0001.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/had-advice-batch-005/candidate_review/initial_frames/viewpoint_motion/had_test0001.jpg","sourceDataset":"Honda Advice Dataset (HAD)","suggestedTrack":"viewpoint_motion","scene":"navigation, vehicle_motion","spatialAbility":"camera_translation, camera_rotation, direction, approach_recede","perspective":"","caption":"Change the ego vehicle's path through the static road layout while preserving the observed scene.","annotationPath":"curated/spatial-world-model/v4/stage-b/had-advice-batch-005/annotations/viewpoint_motion/had_test0001.json"},{"id":"had_test0025","videoPath":"curated/spatial-world-model/v4/stage-b/had-advice-batch-005/videos/viewpoint_motion/had_test0025.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/had-advice-batch-005/videos/viewpoint_motion/had_test0025.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/had-advice-batch-005/candidate_review/initial_frames/viewpoint_motion/had_test0025.jpg","sourceDataset":"Honda Advice Dataset (HAD)","suggestedTrack":"viewpoint_motion","scene":"navigation, vehicle_motion","spatialAbility":"camera_translation, camera_rotation, direction, approach_recede","perspective":"","caption":"Change the ego vehicle's path through the static road layout while preserving the observed scene.","annotationPath":"curated/spatial-world-model/v4/stage-b/had-advice-batch-005/annotations/viewpoint_motion/had_test0025.json"},{"id":"had_test0036","videoPath":"curated/spatial-world-model/v4/stage-b/had-advice-batch-005/videos/coupled_motion/had_test0036.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/had-advice-batch-005/videos/coupled_motion/had_test0036.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/had-advice-batch-005/candidate_review/initial_frames/coupled_motion/had_test0036.jpg","sourceDataset":"Honda Advice Dataset (HAD)","suggestedTrack":"coupled_motion","scene":"navigation, vehicle_motion, human_motion","spatialAbility":"camera_translation, relative_motion, overtaking, distance, depth_order","perspective":"","caption":"Alter the moving road user's trajectory while keeping the ego vehicle's observed approach and road geometry fixed.","annotationPath":"curated/spatial-world-model/v4/stage-b/had-advice-batch-005/annotations/coupled_motion/had_test0036.json"},{"id":"had_test0042","videoPath":"curated/spatial-world-model/v4/stage-b/had-advice-batch-005/videos/coupled_motion/had_test0042.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/had-advice-batch-005/videos/coupled_motion/had_test0042.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/had-advice-batch-005/candidate_review/initial_frames/coupled_motion/had_test0042.jpg","sourceDataset":"Honda Advice Dataset (HAD)","suggestedTrack":"coupled_motion","scene":"navigation, vehicle_motion, human_motion","spatialAbility":"camera_translation, crossing, relative_motion, distance, visibility","perspective":"","caption":"Alter the moving road user's trajectory while keeping the ego vehicle's observed approach and road geometry fixed.","annotationPath":"curated/spatial-world-model/v4/stage-b/had-advice-batch-005/annotations/coupled_motion/had_test0042.json"},{"id":"had_test0053","videoPath":"curated/spatial-world-model/v4/stage-b/had-advice-batch-005/videos/viewpoint_motion/had_test0053.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/had-advice-batch-005/videos/viewpoint_motion/had_test0053.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/had-advice-batch-005/candidate_review/initial_frames/viewpoint_motion/had_test0053.jpg","sourceDataset":"Honda Advice Dataset (HAD)","suggestedTrack":"viewpoint_motion","scene":"navigation, vehicle_motion","spatialAbility":"camera_translation, camera_rotation, direction, approach_recede","perspective":"","caption":"Change the ego vehicle's path through the static road layout while preserving the observed scene.","annotationPath":"curated/spatial-world-model/v4/stage-b/had-advice-batch-005/annotations/viewpoint_motion/had_test0053.json"},{"id":"had_test0059","videoPath":"curated/spatial-world-model/v4/stage-b/had-advice-batch-005/videos/viewpoint_motion/had_test0059.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/had-advice-batch-005/videos/viewpoint_motion/had_test0059.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/had-advice-batch-005/candidate_review/initial_frames/viewpoint_motion/had_test0059.jpg","sourceDataset":"Honda Advice Dataset (HAD)","suggestedTrack":"viewpoint_motion","scene":"navigation, vehicle_motion","spatialAbility":"camera_translation, camera_rotation, direction, approach_recede","perspective":"","caption":"Change the ego vehicle's path through the static road layout while preserving the observed scene.","annotationPath":"curated/spatial-world-model/v4/stage-b/had-advice-batch-005/annotations/viewpoint_motion/had_test0059.json"},{"id":"had_test0076","videoPath":"curated/spatial-world-model/v4/stage-b/had-advice-batch-005/videos/scene_motion/had_test0076.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/had-advice-batch-005/videos/scene_motion/had_test0076.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/had-advice-batch-005/candidate_review/initial_frames/viewpoint_motion/had_test0076.jpg","sourceDataset":"Honda Advice Dataset (HAD)","suggestedTrack":"scene_motion","scene":"human_motion, vehicle_motion, navigation","spatialAbility":"crossing, direction, entry_exit, relative_motion, visibility","perspective":"","caption":"Alter the moving road user's crossing trajectory while preserving the fixed camera and streetscape.","annotationPath":"curated/spatial-world-model/v4/stage-b/had-advice-batch-005/annotations/scene_motion/had_test0076.json"},{"id":"had_test0156","videoPath":"curated/spatial-world-model/v4/stage-b/had-advice-batch-005/videos/coupled_motion/had_test0156.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/had-advice-batch-005/videos/coupled_motion/had_test0156.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/had-advice-batch-005/candidate_review/initial_frames/coupled_motion/had_test0156.jpg","sourceDataset":"Honda Advice Dataset (HAD)","suggestedTrack":"coupled_motion","scene":"navigation, vehicle_motion, human_motion","spatialAbility":"camera_translation, crossing, relative_motion, direction, distance","perspective":"","caption":"Alter the moving road user's trajectory while keeping the ego vehicle's observed approach and road geometry fixed.","annotationPath":"curated/spatial-world-model/v4/stage-b/had-advice-batch-005/annotations/coupled_motion/had_test0156.json"},{"id":"had_test0177","videoPath":"curated/spatial-world-model/v4/stage-b/had-advice-batch-005/videos/coupled_motion/had_test0177.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/had-advice-batch-005/videos/coupled_motion/had_test0177.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/had-advice-batch-005/candidate_review/initial_frames/coupled_motion/had_test0177.jpg","sourceDataset":"Honda Advice Dataset (HAD)","suggestedTrack":"coupled_motion","scene":"navigation, vehicle_motion, human_motion","spatialAbility":"camera_translation, crossing, relative_motion, direction, visibility","perspective":"","caption":"Alter the moving road user's trajectory while keeping the ego vehicle's observed approach and road geometry fixed.","annotationPath":"curated/spatial-world-model/v4/stage-b/had-advice-batch-005/annotations/coupled_motion/had_test0177.json"},{"id":"had_test0544","videoPath":"curated/spatial-world-model/v4/stage-b/had-advice-batch-005/videos/coupled_motion/had_test0544.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/had-advice-batch-005/videos/coupled_motion/had_test0544.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/had-advice-batch-005/candidate_review/initial_frames/coupled_motion/had_test0544.jpg","sourceDataset":"Honda Advice Dataset (HAD)","suggestedTrack":"coupled_motion","scene":"navigation, vehicle_motion, human_motion","spatialAbility":"camera_translation, crossing, relative_motion, direction, depth_order","perspective":"","caption":"Alter the moving road user's trajectory while keeping the ego vehicle's observed approach and road geometry fixed.","annotationPath":"curated/spatial-world-model/v4/stage-b/had-advice-batch-005/annotations/coupled_motion/had_test0544.json"},{"id":"had_test0738","videoPath":"curated/spatial-world-model/v4/stage-b/had-advice-batch-005/videos/coupled_motion/had_test0738.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/had-advice-batch-005/videos/coupled_motion/had_test0738.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/had-advice-batch-005/candidate_review/initial_frames/coupled_motion/had_test0738.jpg","sourceDataset":"Honda Advice Dataset (HAD)","suggestedTrack":"coupled_motion","scene":"navigation, vehicle_motion, human_motion","spatialAbility":"camera_translation, relative_motion, following, distance, direction","perspective":"","caption":"Alter the moving road user's trajectory while keeping the ego vehicle's observed approach and road geometry fixed.","annotationPath":"curated/spatial-world-model/v4/stage-b/had-advice-batch-005/annotations/coupled_motion/had_test0738.json"},{"id":"had_train0009","videoPath":"curated/spatial-world-model/v4/stage-b/had-advice-batch-005/videos/viewpoint_motion/had_train0009.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/had-advice-batch-005/videos/viewpoint_motion/had_train0009.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/had-advice-batch-005/candidate_review/initial_frames/viewpoint_motion/had_train0009.jpg","sourceDataset":"Honda Advice Dataset (HAD)","suggestedTrack":"viewpoint_motion","scene":"navigation, vehicle_motion","spatialAbility":"camera_translation, camera_rotation, direction, approach_recede","perspective":"","caption":"Change the ego vehicle's path through the static road layout while preserving the observed scene.","annotationPath":"curated/spatial-world-model/v4/stage-b/had-advice-batch-005/annotations/viewpoint_motion/had_train0009.json"},{"id":"had_train0013","videoPath":"curated/spatial-world-model/v4/stage-b/had-advice-batch-005/videos/viewpoint_motion/had_train0013.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/had-advice-batch-005/videos/viewpoint_motion/had_train0013.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/had-advice-batch-005/candidate_review/initial_frames/viewpoint_motion/had_train0013.jpg","sourceDataset":"Honda Advice Dataset (HAD)","suggestedTrack":"viewpoint_motion","scene":"navigation, vehicle_motion","spatialAbility":"camera_translation, camera_rotation, direction, approach_recede","perspective":"","caption":"Change the ego vehicle's path through the static road layout while preserving the observed scene.","annotationPath":"curated/spatial-world-model/v4/stage-b/had-advice-batch-005/annotations/viewpoint_motion/had_train0013.json"},{"id":"had_train0054","videoPath":"curated/spatial-world-model/v4/stage-b/had-advice-batch-005/videos/viewpoint_motion/had_train0054.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/had-advice-batch-005/videos/viewpoint_motion/had_train0054.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/had-advice-batch-005/candidate_review/initial_frames/viewpoint_motion/had_train0054.jpg","sourceDataset":"Honda Advice Dataset (HAD)","suggestedTrack":"viewpoint_motion","scene":"navigation, vehicle_motion","spatialAbility":"camera_translation, camera_rotation, direction, approach_recede","perspective":"","caption":"Change the ego vehicle's path through the static road layout while preserving the observed scene.","annotationPath":"curated/spatial-world-model/v4/stage-b/had-advice-batch-005/annotations/viewpoint_motion/had_train0054.json"},{"id":"had_train0064","videoPath":"curated/spatial-world-model/v4/stage-b/had-advice-batch-005/videos/coupled_motion/had_train0064.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/had-advice-batch-005/videos/coupled_motion/had_train0064.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/had-advice-batch-005/candidate_review/initial_frames/coupled_motion/had_train0064.jpg","sourceDataset":"Honda Advice Dataset (HAD)","suggestedTrack":"coupled_motion","scene":"navigation, vehicle_motion, human_motion","spatialAbility":"camera_translation, crossing, relative_motion, direction, visibility","perspective":"","caption":"Alter the moving road user's trajectory while keeping the ego vehicle's observed approach and road geometry fixed.","annotationPath":"curated/spatial-world-model/v4/stage-b/had-advice-batch-005/annotations/coupled_motion/had_train0064.json"},{"id":"had_train0157","videoPath":"curated/spatial-world-model/v4/stage-b/had-advice-batch-005/videos/viewpoint_motion/had_train0157.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/had-advice-batch-005/videos/viewpoint_motion/had_train0157.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/had-advice-batch-005/candidate_review/initial_frames/viewpoint_motion/had_train0157.jpg","sourceDataset":"Honda Advice Dataset (HAD)","suggestedTrack":"viewpoint_motion","scene":"navigation, vehicle_motion","spatialAbility":"camera_translation, camera_rotation, direction, approach_recede","perspective":"","caption":"Change the ego vehicle's path through the static road layout while preserving the observed scene.","annotationPath":"curated/spatial-world-model/v4/stage-b/had-advice-batch-005/annotations/viewpoint_motion/had_train0157.json"},{"id":"had_train0165","videoPath":"curated/spatial-world-model/v4/stage-b/had-advice-batch-005/videos/viewpoint_motion/had_train0165.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/had-advice-batch-005/videos/viewpoint_motion/had_train0165.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/had-advice-batch-005/candidate_review/initial_frames/viewpoint_motion/had_train0165.jpg","sourceDataset":"Honda Advice Dataset (HAD)","suggestedTrack":"viewpoint_motion","scene":"navigation, vehicle_motion","spatialAbility":"camera_translation, camera_rotation, direction, approach_recede","perspective":"","caption":"Change the ego vehicle's path through the static road layout while preserving the observed scene.","annotationPath":"curated/spatial-world-model/v4/stage-b/had-advice-batch-005/annotations/viewpoint_motion/had_train0165.json"},{"id":"had_train0311","videoPath":"curated/spatial-world-model/v4/stage-b/had-advice-batch-005/videos/coupled_motion/had_train0311.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/had-advice-batch-005/videos/coupled_motion/had_train0311.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/had-advice-batch-005/candidate_review/initial_frames/coupled_motion/had_train0311.jpg","sourceDataset":"Honda Advice Dataset (HAD)","suggestedTrack":"coupled_motion","scene":"navigation, vehicle_motion, human_motion","spatialAbility":"camera_translation, crossing, relative_motion, direction, visibility","perspective":"","caption":"Alter the moving road user's trajectory while keeping the ego vehicle's observed approach and road geometry fixed.","annotationPath":"curated/spatial-world-model/v4/stage-b/had-advice-batch-005/annotations/coupled_motion/had_train0311.json"},{"id":"had_train0442","videoPath":"curated/spatial-world-model/v4/stage-b/had-advice-batch-005/videos/coupled_motion/had_train0442.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/had-advice-batch-005/videos/coupled_motion/had_train0442.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/had-advice-batch-005/candidate_review/initial_frames/coupled_motion/had_train0442.jpg","sourceDataset":"Honda Advice Dataset (HAD)","suggestedTrack":"coupled_motion","scene":"navigation, vehicle_motion, human_motion","spatialAbility":"camera_translation, crossing, relative_motion, direction, distance","perspective":"","caption":"Alter the moving road user's trajectory while keeping the ego vehicle's observed approach and road geometry fixed.","annotationPath":"curated/spatial-world-model/v4/stage-b/had-advice-batch-005/annotations/coupled_motion/had_train0442.json"},{"id":"had_train0457","videoPath":"curated/spatial-world-model/v4/stage-b/had-advice-batch-005/videos/viewpoint_motion/had_train0457.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/had-advice-batch-005/videos/viewpoint_motion/had_train0457.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/had-advice-batch-005/candidate_review/initial_frames/viewpoint_motion/had_train0457.jpg","sourceDataset":"Honda Advice Dataset (HAD)","suggestedTrack":"viewpoint_motion","scene":"navigation, vehicle_motion","spatialAbility":"camera_translation, camera_rotation, direction, approach_recede","perspective":"","caption":"Change the ego vehicle's path through the static road layout while preserving the observed scene.","annotationPath":"curated/spatial-world-model/v4/stage-b/had-advice-batch-005/annotations/viewpoint_motion/had_train0457.json"},{"id":"had_train1302","videoPath":"curated/spatial-world-model/v4/stage-b/had-advice-batch-005/videos/scene_motion/had_train1302.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/had-advice-batch-005/videos/scene_motion/had_train1302.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/had-advice-batch-005/candidate_review/initial_frames/coupled_motion/had_train1302.jpg","sourceDataset":"Honda Advice Dataset (HAD)","suggestedTrack":"scene_motion","scene":"human_motion, vehicle_motion, navigation","spatialAbility":"crossing, direction, entry_exit, relative_motion, visibility","perspective":"","caption":"Alter the moving road user's crossing trajectory while preserving the fixed camera and streetscape.","annotationPath":"curated/spatial-world-model/v4/stage-b/had-advice-batch-005/annotations/scene_motion/had_train1302.json"},{"id":"had_train2714","videoPath":"curated/spatial-world-model/v4/stage-b/had-advice-batch-005/videos/viewpoint_motion/had_train2714.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/had-advice-batch-005/videos/viewpoint_motion/had_train2714.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/had-advice-batch-005/candidate_review/initial_frames/viewpoint_motion/had_train2714.jpg","sourceDataset":"Honda Advice Dataset (HAD)","suggestedTrack":"viewpoint_motion","scene":"navigation, vehicle_motion","spatialAbility":"camera_translation, camera_rotation, direction, approach_recede","perspective":"","caption":"Change the ego vehicle's path through the static road layout while preserving the observed scene.","annotationPath":"curated/spatial-world-model/v4/stage-b/had-advice-batch-005/annotations/viewpoint_motion/had_train2714.json"},{"id":"pai_transfer_0000","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/pai_transfer_0000.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/pai_transfer_0000.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/pai_transfer_0000.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a first-person view from a robotic perspective; focusing on a small; round glass table in a modern kitchen setting. The table is organized with a few items: a black mug with a geometric design; a folded red cloth; a box of tissues; and a small decorative vase with fresh flowers. The background features a bright window with sheer curtains; and a green armchair is visible to the right. The robotic arms; which are black with metallic joints; are positioned in front of the camera; suggesting an interaction with the objects on the table. Throughout the video; the arms remain mostly static; hovering over the table; indicating a potential setup for a demonstration or test of the robotic arms' capabilities. The lighting is bright; creating a clean and modern atmosphere. The camera remains fixed; providing a stable view of the scene; allowing the viewer to focus on the details of the objects and the robotic arms. The setting suggests a domestic environment; possibly for a vlog or a demonstration video; emphasizing the interaction between technology and everyday life.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/pai_transfer_0000.json"},{"id":"pai_transfer_0000","videoPath":"web-review/compatible-media/pai-bench/pai_transfer_0000.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/web-review/compatible-media/pai-bench/pai_transfer_0000.mp4","initialFrameUrl":"","sourceDataset":"PAI-Bench","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":""},{"id":"pai_transfer_0001","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/pai_transfer_0001.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/pai_transfer_0001.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/pai_transfer_0001.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video is set in a cozy; dimly-lit workshop with a rustic; industrial design. The background features various tools and equipment; indicating a hands-on environment. The main focus is on a robotic interaction at a wooden workbench. Two robotic arms; equipped with black gloves; are seen handling a blue and white striped coffee cup with a silver lid. The arms are positioned in front of a woman who is standing on the opposite side of the workbench. She is wearing a denim jacket over a plaid shirt and has long dark hair. The robotic arms are articulated and move with precision; suggesting advanced technology.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/pai_transfer_0001.json"},{"id":"pai_transfer_0001","videoPath":"web-review/compatible-media/pai-bench/pai_transfer_0001.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/web-review/compatible-media/pai-bench/pai_transfer_0001.mp4","initialFrameUrl":"","sourceDataset":"PAI-Bench","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":""},{"id":"pai_transfer_0002","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/pai_transfer_0002.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/pai_transfer_0002.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/pai_transfer_0002.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video showcases robotic arms interacting with objects on a sleek metal cabinet. The setting is a contemporary; industrial-style room with a dark concrete floor and walls. On top of the cabinet; there are three objects: a small stack of two cubes; a tube of cream; and a round container. The cubes are metallic-colored; with one being silver and the other gold. The tube of cream is black with a silver cap; and the round container is red and black. A small potted cactus is placed at the back of the cabinet; adding a touch of nature to the scene.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/pai_transfer_0002.json"},{"id":"pai_transfer_0002","videoPath":"web-review/compatible-media/pai-bench/pai_transfer_0002.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/web-review/compatible-media/pai-bench/pai_transfer_0002.mp4","initialFrameUrl":"","sourceDataset":"PAI-Bench","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":""},{"id":"pai_transfer_0003","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/pai_transfer_0003.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/pai_transfer_0003.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/pai_transfer_0003.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video showcases robotic manipulation; with two robotic arms collaborating to fold a piece of fabric. The setting is a dimly lit workshop; featuring a table covered in a green cloth. On the table; there is a piece of beige fabric and a yellow cloth; which remains untouched throughout the video. The robotic arms are positioned on either side of the table; one with a silver base and the other with a gray base. Both arms have grippers resembling human hands; enabling them to grasp and manipulate objects.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/pai_transfer_0003.json"},{"id":"pai_transfer_0003","videoPath":"web-review/compatible-media/pai-bench/pai_transfer_0003.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/web-review/compatible-media/pai-bench/pai_transfer_0003.mp4","initialFrameUrl":"","sourceDataset":"PAI-Bench","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":""},{"id":"pai_transfer_0004","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/pai_transfer_0004.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/pai_transfer_0004.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/pai_transfer_0004.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video showcases robotic arms interacting with a piece of clothing; specifically a pair of denim shorts; on a workbench. The setting is an industrial workshop with a metal surface. The room has a utilitarian aesthetic; with steel shelves and concrete flooring. Two robotic arms; white in color with black mechanical grippers; are positioned above the workbench. These arms are equipped with sensors and wires; indicating advanced robotic technology. At the beginning; the robotic arms are positioned above the denim shorts; which are placed centrally on the workbench. The arms move in a coordinated manner; with the grippers opening and closing as they approach the shorts. As the video progresses; the arms lower towards the shorts; and the grippers make contact with the fabric. The arms then manipulate the shorts; lifting and adjusting them slightly. The motion is precise and controlled; showcasing the dexterity of the robotic arms. The camera remains static throughout the video; providing a clear and unobstructed view of the interaction between the robotic arms and the shorts. The focus is on the mechanical precision and the ability of the robots to handle delicate tasks; highlighting advancements in robotics technology.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/pai_transfer_0004.json"},{"id":"pai_transfer_0004","videoPath":"web-review/compatible-media/pai-bench/pai_transfer_0004.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/web-review/compatible-media/pai-bench/pai_transfer_0004.mp4","initialFrameUrl":"","sourceDataset":"PAI-Bench","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":""},{"id":"pai_transfer_0005","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/pai_transfer_0005.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/pai_transfer_0005.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/pai_transfer_0005.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video showcases robotic arms in a sleek; modern lab setting. Two robotic arms with grippers are featured; operating on a smooth; metallic floor with a white work surface outlined by red and white caution tape. The background includes equipment like a stool and a vertical panel with glowing blue lights; indicating active electronics.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/pai_transfer_0005.json"},{"id":"pai_transfer_0005","videoPath":"web-review/compatible-media/pai-bench/pai_transfer_0005.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/web-review/compatible-media/pai-bench/pai_transfer_0005.mp4","initialFrameUrl":"","sourceDataset":"PAI-Bench","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":""},{"id":"pai_transfer_0006","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/pai_transfer_0006.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/pai_transfer_0006.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/pai_transfer_0006.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video showcases robotic arms interacting with a piece of clothing; specifically a beige shirt; laid out on a table. The setting is a controlled environment; likely a laboratory or a workshop; with a polished; wooden floor and a table covered with a striped cloth. The tablecloth features vertical lines; adding a decorative element to the otherwise utilitarian setting. Two robotic arms are prominently featured; each equipped with a claw-like gripper. These arms are positioned on either side of the shirt; suggesting a task that involves manipulation or folding of the fabric.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/pai_transfer_0006.json"},{"id":"pai_transfer_0006","videoPath":"web-review/compatible-media/pai-bench/pai_transfer_0006.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/web-review/compatible-media/pai-bench/pai_transfer_0006.mp4","initialFrameUrl":"","sourceDataset":"PAI-Bench","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":""},{"id":"pai_transfer_0007","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/pai_transfer_0007.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/pai_transfer_0007.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/pai_transfer_0007.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video showcases robotic arms working on a table with a wooden finish. Two robotic arms are positioned above the table; each equipped with a gripper. The table is set against a dark; polished concrete floor and a gray wall; creating a sleek industrial environment. On the table; there is an open cardboard box; positioned centrally; with its flaps open. To the right of the box; there are two small packages and a set of bubble wrap. The packages are rectangular; one blue and one yellow; and are neatly placed next to each other. The robotic arms are positioned on either side of the box; with their grippers hovering above it; suggesting they are about to perform a task involving the box or the items next to it. Throughout the video; the robotic arms remain mostly static; with slight adjustments in their positioning; indicating precision and readiness for action. The camera angle is fixed; providing a top-down view of the entire setup; allowing a clear view of the objects and the robotic arms. The lighting is soft and warm; ensuring all elements are clearly visible. The video focuses on showcasing the potential of robotic automation in handling packaging tasks; emphasizing precision and efficiency.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/pai_transfer_0007.json"},{"id":"pai_transfer_0007","videoPath":"web-review/compatible-media/pai-bench/pai_transfer_0007.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/web-review/compatible-media/pai-bench/pai_transfer_0007.mp4","initialFrameUrl":"","sourceDataset":"PAI-Bench","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":""},{"id":"pai_transfer_0008","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/pai_transfer_0008.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/pai_transfer_0008.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/pai_transfer_0008.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video showcases robotic arms interacting with a cup of coffee on a table in a cozy kitchen setting. The table is dark wood with a rustic finish; and a white mug filled with coffee sits slightly off-center. A small coffee spill is visible to the left of the mug. Two robotic arms; each with a claw-like gripper; are positioned on either side of the mug; indicating a coordinated task.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/pai_transfer_0008.json"},{"id":"pai_transfer_0008","videoPath":"web-review/compatible-media/pai-bench/pai_transfer_0008.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/web-review/compatible-media/pai-bench/pai_transfer_0008.mp4","initialFrameUrl":"","sourceDataset":"PAI-Bench","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":""},{"id":"pai_transfer_0009","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/pai_transfer_0009.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/pai_transfer_0009.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/pai_transfer_0009.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video showcases robotic arms performing tasks in a kitchen setting. The scene is set in a modern kitchen with a granite-like countertop and a large window reflecting the actions. Two robotic arms are prominently featured; each equipped with a claw-like mechanism. These arms are positioned over a stainless steel sink; which contains various kitchen items such as a red spatula; a whisk; and bottles of spices. The robotic arms are engaged in a series of precise movements; interacting with the objects on the counter. One arm reaches towards the spatula; while the other seems to be adjusting or picking up smaller items like the whisk or spice bottles. The arms exhibit smooth; mechanical motions; indicative of advanced robotics technology. The camera remains static throughout the video; focusing on the interaction between the robotic arms and the kitchen items. The lighting is warm; highlighting the sleek; modern design of the kitchen and the robotic arms. The video does not contain any human presence; focusing solely on the capabilities of the robotic technology in a domestic environment. The overall atmosphere is one of technological advancement and innovation; showcasing the potential for robotics in everyday tasks.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/pai_transfer_0009.json"},{"id":"pai_transfer_0009","videoPath":"web-review/compatible-media/pai-bench/pai_transfer_0009.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/web-review/compatible-media/pai-bench/pai_transfer_0009.mp4","initialFrameUrl":"","sourceDataset":"PAI-Bench","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":""},{"id":"pai_transfer_0010","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/pai_transfer_0010.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/pai_transfer_0010.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/pai_transfer_0010.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video showcases robotic arms interacting with objects on a shelf. Two robotic arms; positioned on either side of the frame; are engaged in a task involving a small; brown; spherical object with antlers; resembling a decorative item or a small sculpture; placed centrally on a shelf. The background features a light wooden shelf with decorative elements; including a plant with long green leaves on the left and a bouquet of red flowers on the right. A small; colorful sticker with a cartoon design is affixed to the back wall of the shelf; adding a playful touch to the setting.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/pai_transfer_0010.json"},{"id":"pai_transfer_0010","videoPath":"web-review/compatible-media/pai-bench/pai_transfer_0010.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/web-review/compatible-media/pai-bench/pai_transfer_0010.mp4","initialFrameUrl":"","sourceDataset":"PAI-Bench","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":""},{"id":"pai_transfer_0011","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/pai_transfer_0011.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/pai_transfer_0011.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/pai_transfer_0011.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video showcases a robotic system interacting with packaged goods in a retail setting; with a backdrop of a shelf filled with vibrant snack packages. The scene is illuminated by soft; ambient lighting; highlighting the pastel hues of the packages; such as mint green; lavender; and peach. The robotic arms; with their sleek metallic finish; are seen picking up and placing items into a blue shopping cart. The arms move with precision; demonstrating their capability to handle various packages. The camera remains steady; capturing the interaction between the robotic arms and the products. The shopping cart gradually fills with snacks featuring whimsical designs. The video emphasizes the robotic system's efficiency in automating product selection in a retail environment.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/pai_transfer_0011.json"},{"id":"pai_transfer_0011","videoPath":"web-review/compatible-media/pai-bench/pai_transfer_0011.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/web-review/compatible-media/pai-bench/pai_transfer_0011.mp4","initialFrameUrl":"","sourceDataset":"PAI-Bench","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":""},{"id":"pai_transfer_0012","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/pai_transfer_0012.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/pai_transfer_0012.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/pai_transfer_0012.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video is set in a sleek; industrial workshop environment; featuring a pair of robotic arms engaged in a task. The floor is a polished; metallic surface; and in the center of the scene is a blue recycling bin. Scattered around the bin are crumpled pieces of colored paper; suggesting a sorting task. The robotic arms; which are black with chrome joints; are positioned on either side of the frame; indicating they are the main focus of the video. They are equipped with claw-like grippers; which are poised above a broom and dustpan setup; hinting at an interaction with these cleaning tools. The arms move with precision; suggesting they are controlled by an advanced system; possibly for a demonstration of robotic capabilities in handling everyday tasks. The camera remains static throughout; providing a clear; unobstructed view of the robotic arms and their interaction with the environment. The setting is minimalistic; with few distractions; emphasizing the technological aspect of the robotic arms. The video likely serves as a demonstration or educational piece; showcasing the potential of robotics in performing routine cleaning tasks autonomously.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/pai_transfer_0012.json"},{"id":"pai_transfer_0012","videoPath":"web-review/compatible-media/pai-bench/pai_transfer_0012.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/web-review/compatible-media/pai-bench/pai_transfer_0012.mp4","initialFrameUrl":"","sourceDataset":"PAI-Bench","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":""},{"id":"pai_transfer_0013","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/pai_transfer_0013.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/pai_transfer_0013.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/pai_transfer_0013.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video showcases robotic arms interacting with a plastic container on a wooden table. The setting is a workshop environment; with a textured brick wall in the background. Two robotic arms; each equipped with black gloves; are positioned on either side of the container. The arms are white with metallic joints and have visible green lights indicating their operational status. The container is rectangular; made of transparent plastic with a gray lid; and is centrally placed on the table. Throughout the video; the robotic arms move in a synchronized manner; approaching the container from opposite sides. The arms are positioned to grasp the container; with their fingers spread wide; suggesting an attempt to lift or manipulate it. The camera remains static; providing a top-down view of the interaction. The lighting is warm; casting soft shadows of the arms and container on the table surface. A small red and white box; possibly a tool kit; is placed in the background; adding context to the environment. The video focuses on the precision and coordination of the robotic arms; highlighting advancements in robotic manipulation and control technology.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/pai_transfer_0013.json"},{"id":"pai_transfer_0013","videoPath":"web-review/compatible-media/pai-bench/pai_transfer_0013.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/web-review/compatible-media/pai-bench/pai_transfer_0013.mp4","initialFrameUrl":"","sourceDataset":"PAI-Bench","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":""},{"id":"pai_transfer_0200","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0200.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0200.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_transfer_0200.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"A scenic drive unfolds along a coastal highway; under a partly cloudy sky with the sun peeking through. The video captures a smooth; continuous journey along a multi-lane road; with the camera positioned as if from the perspective of a vehicle traveling in the right lane. The road is bordered by a tall; rocky cliff on the right; casting dappled shadows over the highway; while the left side opens up to a view of the ocean; visible in the distance beyond a row of colorful wildflowers and a sidewalk. Several vehicles; including a red car and a darker vehicle; travel ahead; maintaining a steady pace. The road is well-maintained; with clear white lane markings and a wooden barrier separating the lanes from the cliff. Utility poles and power lines run parallel to the road on the left; adding to the infrastructure of the scene. The camera remains static; providing a consistent view of the road and surroundings; emphasizing the serene and uninterrupted nature of the drive. The landscape remains consistent throughout; with the cliff's texture and the ocean's horizon providing a picturesque backdrop to the journey.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_transfer_0200.json"},{"id":"pai_transfer_0201","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0201.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0201.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_transfer_0201.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a lively urban street scene; likely filmed from a vehicle navigating through dense traffic. The setting is a vibrant city intersection with multiple lanes filled with cars; SUVs; and trucks. The camera is positioned at the rear of a vehicle; offering a clear view of the traffic ahead. Vehicles are moving slowly; indicating congestion. The sky is clear and bright; suggesting it might be midday. On the left side of the street; there are sleek office buildings with mirrored facades; while on the right; there are quaint brick buildings and various storefronts; including a bakery and a coffee shop. Traffic lights are visible; with some showing red; pausing the vehicles. Street signs and traffic signals are present; directing the flow of traffic. Pedestrians are not prominently visible; but the sidewalks are lined with flower beds and streetlights. The camera remains mostly static; with slight adjustments to maintain focus on the road ahead. The overall atmosphere is typical of a bustling city street during rush hour; with a blend of modern and older architectural elements lining the road.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_transfer_0201.json"},{"id":"pai_transfer_0202","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0202.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0202.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_transfer_0202.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a scenic drive through a sunlit; mountainous landscape; likely filmed from a moving vehicle. The road is a two-lane highway; smoothly paved and winding gently through the golden autumn surroundings. On the left side of the road; dense forests of tall; amber trees create a natural barrier; their leaves rustling gently in the breeze. On the right; a set of railway tracks runs parallel to the road; separated by a low wooden fence. The tracks are well-maintained; with overhead power lines visible; suggesting an electrified railway system. In the background; towering mountains rise majestically; their peaks covered in a mix of rocky outcrops and patches of greenery; under a clear blue sky dotted with a few fluffy clouds.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_transfer_0202.json"},{"id":"pai_transfer_0203","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0203.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0203.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_transfer_0203.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"A scenic drive unfolds along a narrow; winding road nestled between lush green hills and a sky tinged with the warm hues of a setting sun. The video begins with a view of a large; empty flatbed trailer parked on the left side of the road. The trailer is metallic; with a weathered blue color; and its presence suggests a rural or remote setting. As the camera moves forward; the trailer gradually disappears from view; revealing a white car driving ahead on the road. The car maintains a steady pace; moving away from the camera; which follows it closely; creating a sense of pursuit or journey.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_transfer_0203.json"},{"id":"pai_transfer_0204","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0204.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0204.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_transfer_0204.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video shows a continuous driving scene from a dashcam on a cloudy day. The vehicle travels on a multi-lane urban road with a central barrier featuring decorative lights. Traffic is moderate; with several cars visible in both directions. The camera follows a dark-colored SUV; maintaining a steady speed. The SUV is slightly to the right of the lane; while other vehicles; including a white sedan and a silver car; are seen overtaking or driving alongside.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_transfer_0204.json"},{"id":"pai_transfer_0205","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0205.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0205.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_transfer_0205.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a drive through a bustling urban area on a sunny afternoon; with the sun casting long shadows from the towering skyscrapers. The buildings; a mix of steel and glass; reflect the sunlight; creating a dazzling effect. The road is a major artery; marked by a central yellow line; but remains surprisingly devoid of traffic; hinting at a lull in the usual hustle and bustle.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_transfer_0205.json"},{"id":"pai_transfer_0206","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0206.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0206.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_transfer_0206.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video shows a street scene from a stationary camera inside a vehicle; capturing a bustling urban intersection. It's a cloudy day; with overcast skies above. The camera faces forward; displaying a two-lane road bordered by buildings. On the left; a building with a balcony has modern glass railings. On the right; a building is visible with a row of green recycling bins along the sidewalk.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_transfer_0206.json"},{"id":"pai_transfer_0207","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0207.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0207.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_transfer_0207.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a drive through a misty mountain area; with the road winding through fog-shrouded trees. The two-lane highway is marked by a solid double yellow line; indicating no passing. The camera; mounted on the vehicle's front; shows the road and misty surroundings. The vehicle moves steadily; maintaining a smooth pace. The camera remains fixed; providing a continuous view of the misty journey.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_transfer_0207.json"},{"id":"pai_transfer_0208","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0208.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0208.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_transfer_0208.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a steady drive along a straight highway under a partly cloudy sky; with patches of sunlight breaking through. The landscape is vast and open; with dry grass and occasional shrubs lining the road. To the left; rolling hills with a hint of green are visible; while to the right; a series of rocky cliffs rise sharply. The road is a two-lane highway with a yellow center line and white edge markings. Scattered farmhouses and wind turbines can be seen in the distance; suggesting a rural setting. The vehicle's shadow is cast on the road; indicating the sun is behind the camera.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_transfer_0208.json"},{"id":"pai_transfer_0209","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0209.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0209.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_transfer_0209.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a scenic drive through a mountainous region; likely filmed from a vehicle moving along a highway. The road is a two-lane highway with clear white lane markings; bordered by wooden guardrails on both sides. On the left side; there is a dense growth of autumn foliage and trees that rise up the slope of a mountain. The mountain itself is covered in vibrant fall colors; indicating a seasonal change. On the right side; the landscape is more open; with occasional trees and shrubs; and a few rustic cabins visible in the distance; suggesting a rural or semi-rural setting. The sky is overcast; with large; fluffy gray clouds scattered across a muted blue sky; creating a serene backdrop.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_transfer_0209.json"},{"id":"pai_transfer_0210","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0210.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0210.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_transfer_0210.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video is a scenic travel vlog capturing a serene drive along a coastal road during a misty morning with a soft gray sky. The road is a narrow bridge flanked by wooden railings; with a picturesque view of the sea on the right and rocky cliffs on the left. The camera is positioned at a low angle; possibly mounted on a vehicle; providing a forward-moving perspective as it travels along the road. At the beginning; a black van is seen driving towards the camera; followed by a motorcycle ridden by a person wearing a helmet. As the video progresses; several pedestrians are walking along the right side of the bridge; some in pairs; enjoying the view. One woman in a colorful dress is pushing a stroller; while another woman in a hat and dress walks on the left side. Cars continue to pass by; including a white sedan and a silver car; maintaining a steady flow of traffic. The camera remains mostly static; with a slight forward motion; capturing the dynamic interaction between vehicles and pedestrians. The lighting is cool; suggesting early morning; enhancing the tranquil and leisurely atmosphere of the scene.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_transfer_0210.json"},{"id":"pai_transfer_0211","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0211.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0211.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_transfer_0211.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video showcases a digital map exploration; possibly part of a travel or educational series; highlighting a location in China. The main feature is a digital map interface; prominently displaying a region in China with a blue pin marking a location labeled as 'Bagasicion' in Changsha; Hunan. The map is detailed; showing various roads; towns; and geographical features; with names and routes clearly marked. The map interface includes a sidebar on the right; which provides additional information about the location; such as its name; region; and country. This sidebar also features icons that might represent different functionalities or categories; such as weather; nearby attractions; or user reviews.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_transfer_0211.json"},{"id":"pai_transfer_0212","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0212.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0212.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_transfer_0212.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video shows a drive through a bustling city street; captured from a dashcam. The camera is mounted at the front of the vehicle; offering a clear view of the road. It's a cloudy day with a gentle breeze; and the road is lined with cherry blossom trees; their pink flowers adding color to the scene. Two ornate stone arches frame the road at the start of the video; providing a historic touch.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_transfer_0212.json"},{"id":"pai_transfer_0213","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0213.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0213.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_transfer_0213.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a street scene in a bustling urban area; likely filmed from a moving vehicle. The camera is positioned at the rear; offering a view of a lively city street flanked by tall buildings. The architecture is a mix of sleek glass towers and classic brick structures. The sky is overcast; suggesting a cloudy day. Traffic is moderate; featuring a white delivery truck directly ahead; a black taxi to the left; and other cars in adjacent lanes. The road is marked with white lines; and pedestrian sidewalks are on both sides; with a few people strolling. Street signs and traffic lights are visible; with one traffic light showing red; indicating a stop. The camera remains static; capturing the steady flow of traffic and urban scenery.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_transfer_0213.json"},{"id":"pai_transfer_0214","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0214.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0214.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_transfer_0214.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a twilight drive through a cityscape; highlighting a lively urban environment. The camera is mounted at the front of a moving vehicle; offering a first-person view as it travels down a wide; multi-lane road. The road is softly lit with streetlights; and the surrounding area glows with the lights from tall buildings and traffic signals. The buildings on the right side of the road are modern and high-rise; with one particularly prominent structure featuring a glass facade and numerous lit windows; suggesting it might be a residential or office building.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_transfer_0214.json"},{"id":"pai_transfer_0215","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0215.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0215.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_transfer_0215.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a bustling city intersection under a clear blue sky; with sunlight casting sharp shadows on the street. The traffic light shows red; and a cyclist waits patiently. The buildings; a mix of modern glass and steel; line the street; with lush green trees adding a touch of nature.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_transfer_0215.json"},{"id":"pai_transfer_0216","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0216.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0216.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_transfer_0216.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a drive through a bustling urban area; with the camera positioned inside a vehicle. The scene features a wide; multi-lane road bordered by sleek; modern buildings with reflective glass facades. The road is mostly clear; with a few vehicles; including a black car directly in front; moving at a consistent speed. The camera remains fixed; offering a steady view of the road and its surroundings as the vehicle progresses.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_transfer_0216.json"},{"id":"pai_transfer_0217","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0217.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0217.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_transfer_0217.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a lively street scene during a misty morning; highlighting a bustling urban roadway. The camera is positioned from a vehicle's perspective; gliding smoothly along a multi-lane road. The scene is set in a city environment with a clear view of a highway overpass running parallel to the road. On the left side; a blue car is consistently visible; traveling in the same direction as the camera. Several other vehicles; including silver and gray cars; are seen moving along the road; maintaining a steady flow of traffic. A motorcyclist; wearing a helmet and bright clothing; rides in the center lane; slightly ahead of the camera's viewpoint; maintaining a consistent speed.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_transfer_0217.json"},{"id":"pai_transfer_0218","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0218.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0218.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_transfer_0218.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a cityscape scene from a moving vehicle on a highway; showcasing an urban environment under twilight. The camera is positioned at the rear of the vehicle; providing a view of the road ahead. The highway is busy with traffic; featuring a mix of vehicles including white and green cars; likely taxis; and other standard vehicles. The road is divided into multiple lanes; with vehicles moving in a steady flow; indicating a typical evening in the city. On the left side of the frame; a blue metal pedestrian bridge runs parallel to the highway; its structure visible throughout the video. The bridge is elevated; supported by metal beams; and features street lamps that cast a warm glow over the road.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_transfer_0218.json"},{"id":"pai_transfer_0219","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0219.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0219.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_transfer_0219.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a drive along a coastal road under a partly cloudy sky; giving a soft; diffused light. The left side features a rocky hillside with dense green foliage and a few scattered cacti; suggesting a desert-like coastal area. On the right; modern residential buildings with sleek glass facades and rooftop gardens line the street; indicating a contemporary suburban setting.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_transfer_0219.json"},{"id":"pai_transfer_0220","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0220.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0220.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_transfer_0220.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a highway scene during a foggy morning; likely filmed from a moving vehicle. The camera is positioned at the front; offering a clear view of the road ahead. The weather is misty; with light fog creating a hazy atmosphere. Condensation is visible on the camera lens; enhancing the sense of motion and weather conditions. The road is a two-lane highway; with a yellow-striped section indicating a speed bump or a warning area. The highway is bordered by autumn foliage on both sides; with trees and bushes lining the road. The sky is a pale gray; suggesting light cloud cover.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_transfer_0220.json"},{"id":"pai_transfer_0221","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0221.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0221.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_transfer_0221.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video is a travel vlog showcasing a leisurely drive through a misty; pine-lined street in a city. The camera is mounted on a vehicle; providing a first-person perspective as it smoothly travels down the road. The street is wide and features multiple lanes; with clearly marked pedestrian crossings and road signs. On either side of the street; tall pine trees stand still; adding a forest-like feel to the urban environment. The sky is overcast; indicating a cool; cloudy day.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_transfer_0221.json"},{"id":"pai_transfer_0222","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0222.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0222.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_transfer_0222.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video shows a daytime drive through a bustling city; captured from a dashcam. The urban setting features tall buildings on both sides of the road. On the left; a building with a unique spiral design stands out; while on the right; sleek glass office towers are visible. The road is dry; and the sunlight casts sharp shadows on the asphalt. The camera remains mostly static; providing a clear view of the road ahead.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_transfer_0222.json"},{"id":"pai_transfer_0223","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0223.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0223.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_transfer_0223.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video shows a drive on a multi-lane highway under several overpasses; with the camera capturing a first-person view from the dashboard. The highway is lined with tall metal pillars; giving a tunnel-like appearance. The road is smooth with clear lane markings. A white van travels steadily in the center lane. The sky is overcast; suggesting a cloudy day. On both sides; there are patches of trees and distant buildings; indicating a suburban area. Overhead; green road signs with white text guide the traffic. The camera remains fixed; focusing on the road and the van; with no panning or zooming. The drive is smooth and uninterrupted; with the van and signs as focal points.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_transfer_0223.json"},{"id":"pai_transfer_0224","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0224.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0224.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_transfer_0224.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a tranquil scene in a natural setting; possibly a park or nature reserve; with a gently flowing river bordered by vibrant autumn foliage. The sky is overcast; creating a soft; diffused light that enhances the peaceful atmosphere. In the foreground; a grassy area features a circular arrangement of stones; perhaps a fire pit or decorative element. The well-kept grass adds to the serene ambiance.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_transfer_0224.json"},{"id":"pai_transfer_0225","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0225.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0225.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_transfer_0225.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video is a dashcam recording of a drive along a multi-lane highway on a cloudy; overcast day. The sky is a muted gray with thick clouds; creating a somber backdrop. The road is divided into several lanes; with vehicles traveling in both directions. The camera is mounted on the dashboard of a car; providing a steady; forward-facing view of the highway. Throughout the video; the camera remains static; capturing the movement of traffic as the car progresses down the road.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_transfer_0225.json"},{"id":"pai_transfer_0226","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0226.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0226.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_transfer_0226.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a scenic drive along a highway; likely from a dashcam on a vehicle. The two-lane road shows signs of wear; with visible cracks and patches. The camera is mounted at the front; offering a clear view ahead. On the left; a grassy area is dotted with wildflowers; while a dense line of trees forms a natural barrier. To the right; a guardrail separates the road from a rocky coastline; hinting at the ocean nearby. The sky is overcast with a few scattered clouds; suggesting a mild day. A single car is visible ahead; maintaining a steady speed in the right lane. The camera remains static; providing a consistent view of the road and surroundings. The vehicle moves smoothly; indicating a leisurely drive without sudden stops or turns. The atmosphere is calm and serene; capturing the essence of a peaceful coastal highway journey.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_transfer_0226.json"},{"id":"pai_transfer_0227","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0227.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0227.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_transfer_0227.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video shows a drive through a lively urban area; with the dashcam capturing a clear view of the road. The city street is lined with tall residential buildings; and traffic flows smoothly in multiple lanes. Parked cars; including a red convertible; line the street; and vibrant autumn leaves add color to the scene.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_transfer_0227.json"},{"id":"pai_transfer_0228","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0228.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0228.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_transfer_0228.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a lively urban street scene during the late afternoon. The camera is at street level; showing a bustling city street lined with tall; modern buildings featuring sleek glass and steel designs. The sidewalks are crowded with pedestrians; many wearing light-colored casual outfits; indicating a mix of business and leisure activities.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_transfer_0228.json"},{"id":"pai_transfer_0229","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0229.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0229.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_transfer_0229.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video is a driving scene captured from a dashcam perspective; showcasing a busy urban road. The camera remains static; mounted on the dashboard of a vehicle; providing a clear view of the road ahead. The scene is set on a cloudy day; with overcast skies and moderate visibility. The road is a multi-lane street; with two lanes visible in the direction of travel. On the left; a white sedan is driving alongside a black SUV; both moving steadily forward. The road is lined with flowering bushes on the right; providing a colorful backdrop; while on the left; there is a construction site with a green fence and a crane visible in the distance.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_transfer_0229.json"},{"id":"pai_transfer_0400","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_transfer_0400.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_transfer_0400.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/pai_transfer_0400.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video is set in a bicycle repair shop; where a mechanic is working on a bike suspended on a repair stand. The shop is dimly lit; with various bicycle parts and tools casting long shadows on the walls. The mechanic; wearing a black t-shirt and khaki shorts; is focused on adjusting the bike; which is a dark green color with a sturdy frame. The bike is elevated on a stand; allowing the mechanic to work comfortably at eye level. The shop has a rustic look; with wooden beams and a low ceiling; providing a cozy atmosphere.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/pai_transfer_0400.json"},{"id":"pai_transfer_0401","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_transfer_0401.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_transfer_0401.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/pai_transfer_0401.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"A man is working in a dimly lit bicycle repair shop; focusing on a bicycle mounted on a repair stand. The shop is equipped with various tools and equipment; including shelves filled with parts and accessories; and a workbench lined with tools. The man is wearing a dark blue shirt and khaki shorts; and he is intently working on the rear wheel of the bicycle; which is elevated on the stand. He appears to be adjusting or repairing the gear mechanism; using a tool in his right hand. The bicycle is positioned centrally in the room; with its rear wheel facing the man.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/pai_transfer_0401.json"},{"id":"pai_transfer_0402","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_transfer_0402.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_transfer_0402.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/pai_transfer_0402.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"A man is working in a cozy bicycle repair shop; focusing on maintaining a bicycle mounted on a repair stand. The shop is equipped with various tools and equipment; including wooden shelves filled with parts and accessories; and a workbench with neatly arranged tools. Bicycles and wheels are suspended from the ceiling; indicating a professional and busy environment. The man; wearing a dark blue shirt and khaki shorts; is engaged in different tasks throughout the video. He uses a wrench to adjust parts of the bicycle; ensuring everything is tightened and functioning correctly. His movements are deliberate and focused; demonstrating expertise in bicycle maintenance.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/pai_transfer_0402.json"},{"id":"pai_transfer_0403","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_transfer_0403.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_transfer_0403.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/pai_transfer_0403.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video is set in a workshop environment; featuring two individuals engaged in different activities. The workshop is well-equipped; with various tools and equipment visible throughout the space. On the left side; a man in a plaid shirt and overalls is actively working on a project. He is standing on a wooden mat; handling a bicycle wheel placed on a workbench. His actions suggest he is either repairing or assembling the wheel; as he uses tools and occasionally examines the wheel closely. The man is focused and methodical in his movements; indicating a level of expertise in his task.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/pai_transfer_0403.json"},{"id":"pai_transfer_0404","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_transfer_0404.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_transfer_0404.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/pai_transfer_0404.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video is set in a cozy bicycle repair workshop; featuring two individuals engaged in different tasks. The main focus is on a red bicycle mounted on a repair stand in the center of the room. The bicycle is elevated; allowing for easy access to its components. The first individual; wearing a gray shirt and jeans; is actively working on the bicycle. They are adjusting the brakes and checking the alignment of the wheels; demonstrating a methodical approach to bicycle maintenance. The repair stand is equipped with a red coiled air hose; suggesting the use of pneumatic tools.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/pai_transfer_0404.json"},{"id":"pai_transfer_0405","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_transfer_0405.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_transfer_0405.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/pai_transfer_0405.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"A person is working in a cozy bicycle repair workshop. The setting is a compact room with wooden floors and walls; equipped with various tools and equipment. A red and silver bicycle is mounted on a professional bike repair stand; elevated off the ground; allowing easy access to its components. The person; wearing a gray t-shirt; shorts; and protective eyewear; is focused on adjusting or repairing the bicycle. They are standing on a gray mat; which provides comfort and stability during the repair process.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/pai_transfer_0405.json"},{"id":"pai_transfer_0406","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_transfer_0406.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_transfer_0406.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/pai_transfer_0406.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"A man is working in a well-equipped bicycle repair workshop. The setting is a spacious room with wooden walls and a variety of tools and equipment neatly organized around the space. The man is focused on repairing a bicycle wheel; which is mounted on a red repair stand in the center of the room. He is wearing a black t-shirt; gray shorts; and black socks; and he has a tool belt around his waist; indicating his role as a mechanic or technician.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/pai_transfer_0406.json"},{"id":"pai_transfer_0407","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_transfer_0407.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_transfer_0407.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/pai_transfer_0407.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"A cooking video set in a professional kitchen features a chef preparing ingredients on a marble countertop. The chef; wearing a white apron and a light shirt; is focused on slicing vegetables on a wooden cutting board. The vegetables; including bell peppers and possibly cucumbers; are being cut into thin strips; which are collected in a large ceramic bowl nearby. The kitchen is spacious and modern; equipped with multiple black appliances; including ovens and stoves; lining the walls. Silver pendant lights hang from the ceiling; providing cool lighting over the workspace. A tripod is set up on the right side of the counter; suggesting that the cooking process is being filmed or photographed. The camera remains static throughout the video; capturing the chef's back as he works diligently. The chef's movements are precise and methodical; indicating a professional level of skill. The environment is clean and organized; with additional bowls and utensils neatly arranged on the counter. The video maintains a consistent focus on the chef's actions; emphasizing the preparation process without any distractions or additional narrative elements. The overall atmosphere is calm and professional; highlighting the culinary expertise involved in the preparation of the dish.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/pai_transfer_0407.json"},{"id":"pai_transfer_0408","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_transfer_0408.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_transfer_0408.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/pai_transfer_0408.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"A woman is cooking in a cozy kitchen; softly illuminated by warm pendant lights hanging from the ceiling. She is standing at the stove; stirring a pot with a spoon. The kitchen features various appliances; including a coffee maker; a food processor; and a toaster oven. The countertops are organized with kitchen items such as a cutting board with a knife; a jar of olive oil; and a few spice jars. The cabinets are light blue with silver handles; and the floor is made of dark-colored tiles. The woman is wearing a white t-shirt and jeans; and her hair is tied back. She is focused on her cooking task; occasionally adjusting the heat on the stove. The camera remains static throughout the video; capturing the scene from a fixed angle that shows the entire kitchen area. The spatial arrangement places the woman to the right of the frame; with the sink and countertop to her left. The window in the background reveals a view of a lush garden; adding tranquility to the scene. The video maintains a calm and domestic atmosphere; emphasizing the routine of cooking in a home kitchen.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/pai_transfer_0408.json"},{"id":"pai_transfer_0409","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_transfer_0409.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_transfer_0409.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/pai_transfer_0409.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"A woman is seated at a glass table in a contemporary office setting; engaged in a task that involves examining and writing on a large sheet of paper. She is wearing a black top with cut-out shoulders and blue jeans; and her hair is tied back in a ponytail. The room is softly lit with ambient lights; and the walls are painted a light gray. Behind her; there are two cameras mounted on tripods; positioned to capture her actions from different angles. These cameras suggest that the activity might be part of a recorded experiment or study.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/pai_transfer_0409.json"},{"id":"pai_transfer_0410","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_transfer_0410.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_transfer_0410.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/pai_transfer_0410.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"A woman is seated at a glass table in a contemporary office setting; engaged in a focused activity. She is wearing a striped shirt and glasses; with her hair tied back. The room is softly lit; with gray walls and a large corkboard in the background; covered with various diagrams and notes. Two tripods with cameras are positioned in the room; suggesting a recording or observational setup. On the table in front of her are several items: a small electronic device; a box; and some papers. She is actively writing or taking notes on a notepad; occasionally glancing at the materials in front of her. The electronic device; possibly a timer or a small gadget; is placed to her left; while the box and papers are directly in front of her. The woman maintains a consistent posture; leaning slightly forward as she writes; indicating concentration and engagement with the task. The camera angle remains static throughout; capturing the scene from a slightly elevated position; providing a clear view of the woman and her workspace. The environment is quiet and professional; with no other people present; emphasizing her solitary focus on the task at hand.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/pai_transfer_0410.json"},{"id":"pai_transfer_0411","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_transfer_0411.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_transfer_0411.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/pai_transfer_0411.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"A man is seated at a glass table in a sleek; minimalist office; engaged in a scientific or technical task. He is wearing a light blue button-up shirt and dark sunglasses; focusing intently on his work. The table is organized with various items; including a large sheet of paper with diagrams and text; a small electronic device resembling a timer or calculator; and several strips of paper or test strips. The man is holding a small object in his right hand; possibly a test strip or a small tool; and is examining it closely.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/pai_transfer_0411.json"},{"id":"pai_transfer_0412","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_transfer_0412.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_transfer_0412.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/pai_transfer_0412.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"A man is seated at a glass table in a contemporary office; engaged in a detailed task. The room is dimly lit; with a chalkboard in the background covered in various handwritten notes and diagrams. Two tripods with cameras are positioned behind the man; suggesting a recording or monitoring setup. The man; wearing a light blue shirt and glasses; is focused on assembling or examining a small object on the table. A detailed instruction sheet is spread out in front of him; indicating that he is following specific guidelines or steps. A small electronic device; possibly a timer or a remote; is also on the table; adding to the technical nature of the task.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/pai_transfer_0412.json"},{"id":"pai_transfer_0413","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_transfer_0413.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_transfer_0413.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/pai_transfer_0413.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"A man is seated at a glass table in a contemporary office setting; engaged in a detailed task. He is wearing a light blue shirt and glasses; focusing intently on assembling or examining a small object; possibly a piece of technology or a model. The table is dark-colored and has a few items on it; including a small electronic device; a box; and a sheet of paper with printed instructions. The man is using his hands to manipulate the object; indicating a careful and precise action.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/pai_transfer_0413.json"},{"id":"pai_transfer_0414","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_transfer_0414.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_transfer_0414.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/pai_transfer_0414.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"A woman is seated at a glass table in a room that resembles a cozy library or reading nook. She is wearing a light sweater and sunglasses; with her hair tied back. The table is dark-colored and has several items on it; including a notebook; a small electronic device; a mug; and some books. The woman is engaged in an activity that involves handling these items. She is holding a small object; possibly a pen or similar item; and appears to be examining or using it. Her posture is upright; and she occasionally adjusts her sunglasses or touches her face; indicating a focused or thoughtful demeanor.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/pai_transfer_0414.json"},{"id":"pai_transfer_0415","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_transfer_0415.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_transfer_0415.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/pai_transfer_0415.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"A man is seated at a glass table in a modern office setting; engaged in a task involving a small box and some paperwork. He is wearing a light green t-shirt and glasses; and his attention is focused on the items in front of him. The table is positioned in a room with a chalkboard on the wall; which is covered with various handwritten notes and diagrams. Two cameras on tripods are set up behind him; suggesting that the activity is being recorded or monitored for a specific purpose; possibly a tutorial or an experiment.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/pai_transfer_0415.json"},{"id":"pai_transfer_0416","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_transfer_0416.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_transfer_0416.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/pai_transfer_0416.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"A woman is seated at a wooden table in a room designed for a demonstration or instructional video. She is wearing a floral-patterned blouse and glasses; with her hair tied back in a ponytail. The setting includes a red chair and a green storage unit in the background; suggesting a casual or educational environment. On the table in front of her; there is a large sheet of paper with printed instructions; a small electronic device resembling a timer or thermometer; and a box that likely contains a testing kit. Two tripods with cameras are positioned around her; indicating that the scene is being recorded from multiple angles.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/pai_transfer_0416.json"},{"id":"pai_transfer_0520","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0520.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0520.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_transfer_0520.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"A person is engaged in a bouldering activity on an indoor climbing wall. The wall is steeply inclined; covered with a multitude of pastel-colored climbing holds in various shapes and sizes; including lavender; mint; peach; cream; and sky blue. These holds are strategically placed to create a challenging route for the climber. The person; wearing a blue tank top and black pants; begins at the bottom of the wall; reaching up to grasp a hold with their right hand while their left hand is positioned lower. Their feet are placed on lower holds; providing stability as they prepare to ascend.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_transfer_0520.json"},{"id":"pai_transfer_0521","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0521.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_transfer_0521.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_transfer_0521.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"A person is engaged in an indoor bouldering activity at a climbing gym. The scene is set against a large; overhanging climbing wall covered with a multitude of colorful climbing holds in various shapes and sizes. These holds are arranged in a complex pattern; providing a challenging route for the climber. The wall is predominantly white; and the holds are brightly colored in shades of purple; teal; pink; yellow; and orange; creating a vibrant contrast. The climber; wearing a bright orange shirt and dark pants; is positioned near the bottom of the wall; gripping onto the holds with both hands and feet. The climber's posture is dynamic; with their body angled towards the wall; demonstrating strength and balance as they navigate the route. The gym environment is softly lit; with ambient lights casting a warm glow over the climbing area. The floor is covered with thick grey mats for safety. The camera remains static throughout the video; capturing the climber's movements from a consistent angle; allowing viewers to focus on the technique and strategy involved in the climb. The background is relatively plain; with some climbing equipment visible; emphasizing the indoor gym setting. The video does not contain any text overlays or channel logos; maintaining a clear focus on the climbing activity itself.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_transfer_0521.json"},{"id":"pai_understanding_0b24aa07-32e0-4541-bbbd-928409b4d967","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_understanding_0b24aa07-32e0-4541-bbbd-928409b4d967.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_understanding_0b24aa07-32e0-4541-bbbd-928409b4d967.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/pai_understanding_0b24aa07-32e0-4541-bbbd-928409b4d967.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"Is the bathtub empty?","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/pai_understanding_0b24aa07-32e0-4541-bbbd-928409b4d967.json"},{"id":"pai_understanding_1488a94f-480b-4b06-87fb-db0b9a4104bb","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_understanding_1488a94f-480b-4b06-87fb-db0b9a4104bb.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_understanding_1488a94f-480b-4b06-87fb-db0b9a4104bb.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/pai_understanding_1488a94f-480b-4b06-87fb-db0b9a4104bb.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"Does the woman on the left wearing orange look away from her phone screen while the man on the right wearing light green is shaking his left hand?","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/pai_understanding_1488a94f-480b-4b06-87fb-db0b9a4104bb.json"},{"id":"pai_understanding_1cd2d3bd-6198-467f-83c9-4b12e5af1235","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_understanding_1cd2d3bd-6198-467f-83c9-4b12e5af1235.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_understanding_1cd2d3bd-6198-467f-83c9-4b12e5af1235.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_understanding_1cd2d3bd-6198-467f-83c9-4b12e5af1235.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"Based on the ego vehicle's actions in the video, what is the most likely immediate action it will take next?","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_understanding_1cd2d3bd-6198-467f-83c9-4b12e5af1235.json"},{"id":"pai_understanding_1d4bb630-b003-47a5-8fe5-ac0ff544a03f","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_understanding_1d4bb630-b003-47a5-8fe5-ac0ff544a03f.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_understanding_1d4bb630-b003-47a5-8fe5-ac0ff544a03f.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_understanding_1d4bb630-b003-47a5-8fe5-ac0ff544a03f.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"Based on the ego vehicle's actions in the video, what is the most likely immediate action it will take next?","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_understanding_1d4bb630-b003-47a5-8fe5-ac0ff544a03f.json"},{"id":"pai_understanding_301eb63f-c7f1-4604-aeae-6a2e8ad75276","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_understanding_301eb63f-c7f1-4604-aeae-6a2e8ad75276.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_understanding_301eb63f-c7f1-4604-aeae-6a2e8ad75276.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_understanding_301eb63f-c7f1-4604-aeae-6a2e8ad75276.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"Based on the ego vehicle's actions in the video, is it true that the ego vehicle has finished a left lane change?","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_understanding_301eb63f-c7f1-4604-aeae-6a2e8ad75276.json"},{"id":"pai_understanding_387e60cb-4cbf-4dbc-b524-0aee5f3f36a3","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_understanding_387e60cb-4cbf-4dbc-b524-0aee5f3f36a3.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_understanding_387e60cb-4cbf-4dbc-b524-0aee5f3f36a3.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/pai_understanding_387e60cb-4cbf-4dbc-b524-0aee5f3f36a3.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"Does the camera follow the old man as he stands up?","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/pai_understanding_387e60cb-4cbf-4dbc-b524-0aee5f3f36a3.json"},{"id":"pai_understanding_395527b9-a6c7-429e-b5b8-d73b5f61f0e8","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_understanding_395527b9-a6c7-429e-b5b8-d73b5f61f0e8.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_understanding_395527b9-a6c7-429e-b5b8-d73b5f61f0e8.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_understanding_395527b9-a6c7-429e-b5b8-d73b5f61f0e8.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"Based on the ego vehicle's actions in the video, what is the most likely immediate action it will take next?","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_understanding_395527b9-a6c7-429e-b5b8-d73b5f61f0e8.json"},{"id":"pai_understanding_48e4c62c-d3f2-48be-8635-620a0c6a912d","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_understanding_48e4c62c-d3f2-48be-8635-620a0c6a912d.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_understanding_48e4c62c-d3f2-48be-8635-620a0c6a912d.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_understanding_48e4c62c-d3f2-48be-8635-620a0c6a912d.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"Based on the ego vehicle's actions in the video, what is the most likely immediate action it will take next?","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_understanding_48e4c62c-d3f2-48be-8635-620a0c6a912d.json"},{"id":"pai_understanding_52d5332d-0f5f-49f5-9d76-46bd13b594b8","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_understanding_52d5332d-0f5f-49f5-9d76-46bd13b594b8.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_understanding_52d5332d-0f5f-49f5-9d76-46bd13b594b8.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_understanding_52d5332d-0f5f-49f5-9d76-46bd13b594b8.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"Based on the ego vehicle's actions in the video, what is the most likely immediate action it will take next?","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_understanding_52d5332d-0f5f-49f5-9d76-46bd13b594b8.json"},{"id":"pai_understanding_5caf81de-c8c8-4e2f-a237-677e8e0607be","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_understanding_5caf81de-c8c8-4e2f-a237-677e8e0607be.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_understanding_5caf81de-c8c8-4e2f-a237-677e8e0607be.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_understanding_5caf81de-c8c8-4e2f-a237-677e8e0607be.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"Based on the ego vehicle's actions in the video, what is the most likely immediate action it will take next?","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_understanding_5caf81de-c8c8-4e2f-a237-677e8e0607be.json"},{"id":"pai_understanding_5dcc4245-ae67-4b44-998a-4232628b692e","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_understanding_5dcc4245-ae67-4b44-998a-4232628b692e.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_understanding_5dcc4245-ae67-4b44-998a-4232628b692e.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_understanding_5dcc4245-ae67-4b44-998a-4232628b692e.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"Based on the ego vehicle's actions in the video, is it true that the ego vehicle has finished a left lane change?","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_understanding_5dcc4245-ae67-4b44-998a-4232628b692e.json"},{"id":"pai_understanding_5f49a550-7193-4721-a72b-4170b6fe5cc3","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_understanding_5f49a550-7193-4721-a72b-4170b6fe5cc3.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_understanding_5f49a550-7193-4721-a72b-4170b6fe5cc3.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_understanding_5f49a550-7193-4721-a72b-4170b6fe5cc3.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"Based on the ego vehicle's actions in the video, what is the most likely immediate action it will take next?","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_understanding_5f49a550-7193-4721-a72b-4170b6fe5cc3.json"},{"id":"pai_understanding_5f567f79-4dd0-413d-a81a-2607684decf2","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_understanding_5f567f79-4dd0-413d-a81a-2607684decf2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_understanding_5f567f79-4dd0-413d-a81a-2607684decf2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_understanding_5f567f79-4dd0-413d-a81a-2607684decf2.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"Based on the ego vehicle's actions in the video, what is the most likely immediate action it will take next?","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_understanding_5f567f79-4dd0-413d-a81a-2607684decf2.json"},{"id":"pai_understanding_6105b039-c4fa-445c-a56f-48df1a3a2960","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_understanding_6105b039-c4fa-445c-a56f-48df1a3a2960.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_understanding_6105b039-c4fa-445c-a56f-48df1a3a2960.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/pai_understanding_6105b039-c4fa-445c-a56f-48df1a3a2960.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"Why are the leaves floating on the water surface?","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/pai_understanding_6105b039-c4fa-445c-a56f-48df1a3a2960.json"},{"id":"pai_understanding_75c0488a-9ecd-476c-8fbe-882fb8dc3799","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_understanding_75c0488a-9ecd-476c-8fbe-882fb8dc3799.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_understanding_75c0488a-9ecd-476c-8fbe-882fb8dc3799.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_understanding_75c0488a-9ecd-476c-8fbe-882fb8dc3799.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"Based on the ego vehicle's actions in the video, is it true that the ego vehicle has finished a right-turn?","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_understanding_75c0488a-9ecd-476c-8fbe-882fb8dc3799.json"},{"id":"pai_understanding_845d7a44-758f-4d13-918b-19f5b32bd87f","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_understanding_845d7a44-758f-4d13-918b-19f5b32bd87f.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_understanding_845d7a44-758f-4d13-918b-19f5b32bd87f.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_understanding_845d7a44-758f-4d13-918b-19f5b32bd87f.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"Based on the ego vehicle's actions in the video, is it true that the ego vehicle has remained in its lane without making a left or right lane change?","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_understanding_845d7a44-758f-4d13-918b-19f5b32bd87f.json"},{"id":"pai_understanding_88182919-a0ad-46de-bbb4-9fcaec20b6d3","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_understanding_88182919-a0ad-46de-bbb4-9fcaec20b6d3.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_understanding_88182919-a0ad-46de-bbb4-9fcaec20b6d3.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/pai_understanding_88182919-a0ad-46de-bbb4-9fcaec20b6d3.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"Does the camera shift from the man wearing orange shirt towards the man wearing a green blazer?","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/pai_understanding_88182919-a0ad-46de-bbb4-9fcaec20b6d3.json"},{"id":"pai_understanding_8d4e314b-498a-405d-a63f-3493e44007c7","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_understanding_8d4e314b-498a-405d-a63f-3493e44007c7.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_understanding_8d4e314b-498a-405d-a63f-3493e44007c7.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/pai_understanding_8d4e314b-498a-405d-a63f-3493e44007c7.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"Does the stovetop remain stationary throughout the video?","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/pai_understanding_8d4e314b-498a-405d-a63f-3493e44007c7.json"},{"id":"pai_understanding_a3383a70-bdf9-4402-a451-f3dbf218c3d2","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_understanding_a3383a70-bdf9-4402-a451-f3dbf218c3d2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_understanding_a3383a70-bdf9-4402-a451-f3dbf218c3d2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/pai_understanding_a3383a70-bdf9-4402-a451-f3dbf218c3d2.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"Does the camera zoom out away from the building?","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/pai_understanding_a3383a70-bdf9-4402-a451-f3dbf218c3d2.json"},{"id":"pai_understanding_a92598e5-0020-4da1-9b25-b9e5971e2680","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_understanding_a92598e5-0020-4da1-9b25-b9e5971e2680.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_understanding_a92598e5-0020-4da1-9b25-b9e5971e2680.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/pai_understanding_a92598e5-0020-4da1-9b25-b9e5971e2680.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"How does the man move the rectangular device?","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/pai_understanding_a92598e5-0020-4da1-9b25-b9e5971e2680.json"},{"id":"pai_understanding_b1c6ceb5-b8b3-4128-820d-6eb8c59828d4","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_understanding_b1c6ceb5-b8b3-4128-820d-6eb8c59828d4.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_understanding_b1c6ceb5-b8b3-4128-820d-6eb8c59828d4.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/pai_understanding_b1c6ceb5-b8b3-4128-820d-6eb8c59828d4.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"What did the baby not do?","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/pai_understanding_b1c6ceb5-b8b3-4128-820d-6eb8c59828d4.json"},{"id":"pai_understanding_c2167f34-6d0d-45c7-82f1-204e63dbe2a6","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_understanding_c2167f34-6d0d-45c7-82f1-204e63dbe2a6.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_understanding_c2167f34-6d0d-45c7-82f1-204e63dbe2a6.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/pai_understanding_c2167f34-6d0d-45c7-82f1-204e63dbe2a6.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"How many cyclists are riding the bicycles on the road?","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/pai_understanding_c2167f34-6d0d-45c7-82f1-204e63dbe2a6.json"},{"id":"pai_understanding_c24e9cac-80f7-4d34-a399-669de06b8467","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_understanding_c24e9cac-80f7-4d34-a399-669de06b8467.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_understanding_c24e9cac-80f7-4d34-a399-669de06b8467.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_understanding_c24e9cac-80f7-4d34-a399-669de06b8467.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"Based on the ego vehicle's actions in the video, what is the most likely immediate action it will take next?","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_understanding_c24e9cac-80f7-4d34-a399-669de06b8467.json"},{"id":"pai_understanding_d8aab98f-10db-4cbd-a99b-8204460507b1","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_understanding_d8aab98f-10db-4cbd-a99b-8204460507b1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/pai_understanding_d8aab98f-10db-4cbd-a99b-8204460507b1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/pai_understanding_d8aab98f-10db-4cbd-a99b-8204460507b1.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"Based on the ego vehicle's actions in the video, what is the most likely immediate action it will take next?","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/pai_understanding_d8aab98f-10db-4cbd-a99b-8204460507b1.json"},{"id":"pai_understanding_e1607e76-10e8-40d2-ab27-d8858f619f5b","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_understanding_e1607e76-10e8-40d2-ab27-d8858f619f5b.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_understanding_e1607e76-10e8-40d2-ab27-d8858f619f5b.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/pai_understanding_e1607e76-10e8-40d2-ab27-d8858f619f5b.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"What does the woman in the blue helmet, touch with her left hand?","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/pai_understanding_e1607e76-10e8-40d2-ab27-d8858f619f5b.json"},{"id":"pai_understanding_e85bc2af-53a0-49f7-9964-03a07fb09684","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_understanding_e85bc2af-53a0-49f7-9964-03a07fb09684.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_understanding_e85bc2af-53a0-49f7-9964-03a07fb09684.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/pai_understanding_e85bc2af-53a0-49f7-9964-03a07fb09684.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"Is the bedding on the bed neatly arranged?","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/pai_understanding_e85bc2af-53a0-49f7-9964-03a07fb09684.json"},{"id":"pai_understanding_f1673b12-5a38-4b18-ad0f-ba117161a758","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_understanding_f1673b12-5a38-4b18-ad0f-ba117161a758.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_understanding_f1673b12-5a38-4b18-ad0f-ba117161a758.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/pai_understanding_f1673b12-5a38-4b18-ad0f-ba117161a758.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"What is the purpose of the item the man is holding in his left hand?","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/pai_understanding_f1673b12-5a38-4b18-ad0f-ba117161a758.json"},{"id":"pai_understanding_f2fe5d57-143f-47f5-a5e3-01bafdb12a3b","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_understanding_f2fe5d57-143f-47f5-a5e3-01bafdb12a3b.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_understanding_f2fe5d57-143f-47f5-a5e3-01bafdb12a3b.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/pai_understanding_f2fe5d57-143f-47f5-a5e3-01bafdb12a3b.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"Is the floor where people are visible at ground level?","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/pai_understanding_f2fe5d57-143f-47f5-a5e3-01bafdb12a3b.json"},{"id":"pai_understanding_f3196950-5fe8-4973-976f-1c23adf1f6b5","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_understanding_f3196950-5fe8-4973-976f-1c23adf1f6b5.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_understanding_f3196950-5fe8-4973-976f-1c23adf1f6b5.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/pai_understanding_f3196950-5fe8-4973-976f-1c23adf1f6b5.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"Does the person fix the component on the motherboard?","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/pai_understanding_f3196950-5fe8-4973-976f-1c23adf1f6b5.json"},{"id":"pai_understanding_f46bc3fa-f8f5-44ee-a519-4454ceabeaf1","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_understanding_f46bc3fa-f8f5-44ee-a519-4454ceabeaf1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_understanding_f46bc3fa-f8f5-44ee-a519-4454ceabeaf1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/pai_understanding_f46bc3fa-f8f5-44ee-a519-4454ceabeaf1.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"One can see a vacant bench?","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/pai_understanding_f46bc3fa-f8f5-44ee-a519-4454ceabeaf1.json"},{"id":"pai_understanding_f6478289-be08-43c8-87b9-f21df6f7e195","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_understanding_f6478289-be08-43c8-87b9-f21df6f7e195.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_understanding_f6478289-be08-43c8-87b9-f21df6f7e195.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/pai_understanding_f6478289-be08-43c8-87b9-f21df6f7e195.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"Does the camera provide a different view of the person within the video?","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/pai_understanding_f6478289-be08-43c8-87b9-f21df6f7e195.json"},{"id":"pai_understanding_f813699e-7b61-4e42-9185-751265bff80e","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_understanding_f813699e-7b61-4e42-9185-751265bff80e.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/pai_understanding_f813699e-7b61-4e42-9185-751265bff80e.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/pai_understanding_f813699e-7b61-4e42-9185-751265bff80e.jpg","sourceDataset":"PAI-Bench","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"Can the dog in the middle jump over the dog on the left?","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/pai_understanding_f813699e-7b61-4e42-9185-751265bff80e.json"},{"id":"panda_ants_under_moss","videoPath":"curated/spatial-world-model/v5/screenshot-references/videos/scene_motion/Nuia1y8ZfhE.13.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v5/screenshot-references/videos/scene_motion/Nuia1y8ZfhE.13.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v5/screenshot-references/initial_frames/panda_ants_under_moss.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"ants, moss tunnel, natural ground","spatialAbility":"containment, occlusion, enter_exit, traversal","perspective":"macro view looking into and across a moss-covered tunnel opening","caption":"There are ants tunneling under a thick carpet of moss.","annotationPath":"curated/spatial-world-model/v5/screenshot-references/annotations/panda_ants_under_moss.json"},{"id":"panda_basketball_practice","videoPath":"curated/spatial-world-model/v5/screenshot-references/videos/scene_motion/7axksThlAok.79.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v5/screenshot-references/videos/scene_motion/7axksThlAok.79.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v5/screenshot-references/initial_frames/panda_basketball_practice.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"basketball practice, indoor court","spatialAbility":"vertical_trajectory, target_relation, depth, contact","perspective":"stationary or lightly moving court-side view","caption":"A group of basketball players are practicing their shots on the court.","annotationPath":"curated/spatial-world-model/v5/screenshot-references/annotations/panda_basketball_practice.json"},{"id":"panda_beach_volleyball","videoPath":"curated/spatial-world-model/v5/screenshot-references/videos/scene_motion/vGmnTxev7bo.3.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v5/screenshot-references/videos/scene_motion/vGmnTxev7bo.3.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v5/screenshot-references/initial_frames/panda_beach_volleyball.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"beach volleyball, sports court, crowd","spatialAbility":"trajectory, over_under, near_far, relative_motion","perspective":"sideline spectator view across a bounded court","caption":"There is a group of people playing beach volleyball on a sandy beach with a crowd watching the game.","annotationPath":"curated/spatial-world-model/v5/screenshot-references/annotations/panda_beach_volleyball.json"},{"id":"panda_boat_rocks_waterfall","videoPath":"curated/spatial-world-model/v5/screenshot-references/videos/coupled_motion/fjSw0PBrtMU.45.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v5/screenshot-references/videos/coupled_motion/fjSw0PBrtMU.45.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v5/screenshot-references/initial_frames/panda_boat_rocks_waterfall.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"river, boat navigation, rocky channel","spatialAbility":"egocentric_translation, depth, approach_avoidance, flow_direction","perspective":"moving boat-mounted or closely following perspective through a river channel","caption":"A person is driving a boat on a river with rocks and waterfalls.","annotationPath":"curated/spatial-world-model/v5/screenshot-references/annotations/panda_boat_rocks_waterfall.json"},{"id":"panda_cnc_milling_wood","videoPath":"curated/spatial-world-model/v5/screenshot-references/videos/scene_motion/YI4dFTTlGa4.7.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v5/screenshot-references/videos/scene_motion/YI4dFTTlGa4.7.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v5/screenshot-references/initial_frames/panda_cnc_milling_wood.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"CNC milling, wood machining, tool-object interaction","spatialAbility":"tool_path, contact, surface_relation, material_change","perspective":"fixed oblique view inside the milling workspace","caption":"A cnc milling machine cutting a piece of wood.","annotationPath":"curated/spatial-world-model/v5/screenshot-references/annotations/panda_cnc_milling_wood.json"},{"id":"panda_freeway_interchange_dusk","videoPath":"curated/spatial-world-model/v5/screenshot-references/videos/coupled_motion/J2vHbuGsxxs.16.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v5/screenshot-references/videos/coupled_motion/J2vHbuGsxxs.16.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v5/screenshot-references/initial_frames/panda_freeway_interchange_dusk.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"road interchange, multi-level traffic, outdoor aerial","spatialAbility":"topology, depth_order, direction, relative_motion","perspective":"oblique aerial overview; the camera observes multiple road levels simultaneously","caption":"An aerial view of a freeway intersection at dusk.","annotationPath":"curated/spatial-world-model/v5/screenshot-references/annotations/panda_freeway_interchange_dusk.json"},{"id":"panda_hug_in_front_of_trophy","videoPath":"curated/spatial-world-model/v5/screenshot-references/videos/scene_motion/vdGG2_5VM9U.2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v5/screenshot-references/videos/scene_motion/vdGG2_5VM9U.2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v5/screenshot-references/initial_frames/panda_hug_in_front_of_trophy.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"celebration, two-person interaction, trophy","spatialAbility":"interpersonal_distance, contact, foreground_background, body_orientation","perspective":"medium close-up with the trophy as a fixed side/background anchor","caption":"Two men hugging each other in front of a trophy.","annotationPath":"curated/spatial-world-model/v5/screenshot-references/annotations/panda_hug_in_front_of_trophy.json"},{"id":"panda_lipstick_silicone_doll","videoPath":"curated/spatial-world-model/v5/screenshot-references/videos/scene_motion/YemkZ7DLOBU.15.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v5/screenshot-references/videos/scene_motion/YemkZ7DLOBU.15.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v5/screenshot-references/initial_frames/panda_lipstick_silicone_doll.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"makeup application, face close-up, hand-tool contact","spatialAbility":"approach, fine_contact, left_right, surface_following","perspective":"close-up side view of face, hand, and applicator","caption":"A makeup artist is applying lipstick to a silicone doll.","annotationPath":"curated/spatial-world-model/v5/screenshot-references/annotations/panda_lipstick_silicone_doll.json"},{"id":"panda_planet_orbiting_star","videoPath":"curated/spatial-world-model/v5/screenshot-references/videos/scene_motion/OjXeF568qUA.18.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v5/screenshot-references/videos/scene_motion/OjXeF568qUA.18.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v5/screenshot-references/initial_frames/panda_planet_orbiting_star.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"animated orbital system, planet and star","spatialAbility":"orbital_path, relative_position, occlusion, scale","perspective":"fixed distant view of a stylized celestial system","caption":"A planet is orbiting around a large star in the sky.","annotationPath":"curated/spatial-world-model/v5/screenshot-references/annotations/panda_planet_orbiting_star.json"},{"id":"panda_satellite_city_navigation","videoPath":"curated/spatial-world-model/v5/screenshot-references/videos/viewpoint_motion/COLGm4vIVuQ.9.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v5/screenshot-references/videos/viewpoint_motion/COLGm4vIVuQ.9.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v5/screenshot-references/initial_frames/panda_satellite_city_navigation.jpg","sourceDataset":"Panda-70M","suggestedTrack":"viewpoint_motion","scene":"digital satellite map, city overview, screen interaction","spatialAbility":"camera_pan, zoom_scale, map_orientation, viewpoint_change","perspective":"screen-recorded bird's-eye map view with navigation-driven viewpoint changes","caption":"A computer screen showing a satellite view of a city.","annotationPath":"curated/spatial-world-model/v5/screenshot-references/annotations/panda_satellite_city_navigation.json"},{"id":"panda_skateboard_trick","videoPath":"curated/spatial-world-model/v5/screenshot-references/videos/coupled_motion/DY6EvKeXpoo.15.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v5/screenshot-references/videos/coupled_motion/DY6EvKeXpoo.15.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v5/screenshot-references/initial_frames/panda_skateboard_trick.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"skate park, skateboard trick, rail and ramps","spatialAbility":"support, contact, clearance, trajectory","perspective":"close spectator or tracking view of the skater and obstacle","caption":"A skateboarder performs a trick in a skate park.","annotationPath":"curated/spatial-world-model/v5/screenshot-references/annotations/panda_skateboard_trick.json"},{"id":"panda_soccer_stadium","videoPath":"curated/spatial-world-model/v5/screenshot-references/videos/scene_motion/0idSKtn42WY.2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v5/screenshot-references/videos/scene_motion/0idSKtn42WY.2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v5/screenshot-references/initial_frames/panda_soccer_stadium.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"soccer match, field, stadium","spatialAbility":"direction, relative_distance, foreground_background, bounded_space","perspective":"wide sideline view with the stadium as a stable background reference","caption":"A soccer game is being played on a green field with a large stadium in the background.","annotationPath":"curated/spatial-world-model/v5/screenshot-references/annotations/panda_soccer_stadium.json"},{"id":"panda_v6_-pzgf4NP6IQ_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_-pzgf4NP6IQ_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_-pzgf4NP6IQ_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_-pzgf4NP6IQ_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"tool_contact_state_change","spatialAbility":"tool_contact_state_change, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A young boy is walking on a path with red paint on his shirt.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_-pzgf4NP6IQ_1.json"},{"id":"panda_v6_-wWZSRpwpaA_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_-wWZSRpwpaA_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_-wWZSRpwpaA_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_-wWZSRpwpaA_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"reflection_surface","spatialAbility":"reflection_surface, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"There are two people riding on the back of two horses, they are walking along a dirt path that is next to a body of water.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_-wWZSRpwpaA_1.json"},{"id":"panda_v6_-Xs7leOtI4E_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_-Xs7leOtI4E_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_-Xs7leOtI4E_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_-Xs7leOtI4E_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"sports_trajectory","spatialAbility":"sports_trajectory, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"The player is in a minecraft game and is riding on a roller coaster.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_-Xs7leOtI4E_1.json"},{"id":"panda_v6_0H8O2CzLk7c_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_0H8O2CzLk7c_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_0H8O2CzLk7c_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_0H8O2CzLk7c_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"occlusion_containment","spatialAbility":"occlusion_containment, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A person is walking through a snow-covered parking lot and passing by several shipping containers.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_0H8O2CzLk7c_1.json"},{"id":"panda_v6_0Jez8PBQAcc_1","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_0Jez8PBQAcc_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_0Jez8PBQAcc_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_0Jez8PBQAcc_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"A group of people are riding roller skates in a tunnel.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_0Jez8PBQAcc_1.json"},{"id":"panda_v6_0MpmadgaydQ_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_0MpmadgaydQ_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_0MpmadgaydQ_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_0MpmadgaydQ_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"reflection_surface","spatialAbility":"reflection_surface, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"People are walking on a rocky terrain and admiring the view of a glacier with icebergs floating in the water.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_0MpmadgaydQ_2.json"},{"id":"panda_v6_0sAK3A1mGJ0_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_0sAK3A1mGJ0_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_0sAK3A1mGJ0_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_0sAK3A1mGJ0_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"tool_contact_state_change","spatialAbility":"tool_contact_state_change, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is making a paper flower poppy by cutting out red and green petals, gluing them together to form the base of the flower, and then adding a wire stem to hold it in place.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_0sAK3A1mGJ0_0.json"},{"id":"panda_v6_0Tj2Qwgeh00_2","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_0Tj2Qwgeh00_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_0Tj2Qwgeh00_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_0Tj2Qwgeh00_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative and Coupled Motion","perspective":"Egocentric","caption":"A red sports car is driving on a winding road in the countryside, surrounded by fall foliage.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_0Tj2Qwgeh00_2.json"},{"id":"panda_v6_12QfJmBPb8o_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_12QfJmBPb8o_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_12QfJmBPb8o_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_12QfJmBPb8o_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"topology_navigation","spatialAbility":"topology_navigation, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A car is driving on a highway at sunset, passing through a flyover. the video also shows the driver's view of the road and the surroundings.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_12QfJmBPb8o_1.json"},{"id":"panda_v6_15H8_z7gaCU_0","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_15H8_z7gaCU_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_15H8_z7gaCU_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_15H8_z7gaCU_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative and Coupled Motion","perspective":"Egocentric","caption":"The player is in a first-person shooter game and is walking through a grassy field with trees in the background.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_15H8_z7gaCU_0.json"},{"id":"panda_v6_1iS_LsxKSZY_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_1iS_LsxKSZY_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_1iS_LsxKSZY_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_1iS_LsxKSZY_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"topology_navigation","spatialAbility":"topology_navigation, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"The driver is driving a white sports car on a wet asphalt road and turns around cones.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_1iS_LsxKSZY_0.json"},{"id":"panda_v6_1o4km9BD_eU_0","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_1o4km9BD_eU_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_1o4km9BD_eU_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_1o4km9BD_eU_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled motion","scene":"object physics","spatialAbility":"Direction and Trajectory, Relative and Coupled Motion","perspective":"Egocentric","caption":"A small turtle is walking on a table, and there is a cactus in the background.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_1o4km9BD_eU_0.json"},{"id":"panda_v6_1wp28IkCR9k_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_1wp28IkCR9k_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_1wp28IkCR9k_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_1wp28IkCR9k_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"topology_navigation","spatialAbility":"topology_navigation, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A young man is riding his skateboard on the sidewalk of a city street. he is wearing black pants and a black shirt, and he has long hair.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_1wp28IkCR9k_1.json"},{"id":"panda_v6_1ZGcE7tABSk_0","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_1ZGcE7tABSk_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_1ZGcE7tABSk_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_1ZGcE7tABSk_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled motion","scene":"human interaction","spatialAbility":"Direction and Trajectory, Relative and Coupled Motion","perspective":"Egocentric","caption":"A group of people in red shirts are walking through an open gate and entering a building.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_1ZGcE7tABSk_0.json"},{"id":"panda_v6_20SwaTpJZUQ_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_20SwaTpJZUQ_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_20SwaTpJZUQ_0.mp4","initialFrameUrl":"","sourceDataset":"Panda-70M","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":""},{"id":"panda_v6_2BrhmkrYyG4_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_2BrhmkrYyG4_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_2BrhmkrYyG4_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_2BrhmkrYyG4_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"human_object_interaction","spatialAbility":"human_object_interaction, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"The person is holding a flower arrangement made of dried flowers and leaves on a lace tablecloth.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_2BrhmkrYyG4_1.json"},{"id":"panda_v6_2J1KSF_vl_0_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_2J1KSF_vl_0_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_2J1KSF_vl_0_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_2J1KSF_vl_0_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"topology_navigation","spatialAbility":"topology_navigation, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A man and woman are riding in an off-road vehicle at night and taking turns filming each other while driving.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_2J1KSF_vl_0_2.json"},{"id":"panda_v6_2K78JE_iplc_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_2K78JE_iplc_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_2K78JE_iplc_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_2K78JE_iplc_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"human_object_interaction","spatialAbility":"human_object_interaction, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A person is riding on an amusement park ride at night.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_2K78JE_iplc_1.json"},{"id":"panda_v6_2kf3kFhAY1A_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_2kf3kFhAY1A_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_2kf3kFhAY1A_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_2kf3kFhAY1A_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"human_object_interaction","spatialAbility":"human_object_interaction, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A person is holding a purple flower in their hand, and the camera zooms in on the flower.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_2kf3kFhAY1A_2.json"},{"id":"panda_v6_2UACT7S5YTk_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_2UACT7S5YTk_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_2UACT7S5YTk_0.mp4","initialFrameUrl":"","sourceDataset":"Panda-70M","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":""},{"id":"panda_v6_2yHZZmKAUck_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_2yHZZmKAUck_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_2yHZZmKAUck_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_2yHZZmKAUck_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"tool_contact_state_change","spatialAbility":"tool_contact_state_change, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is replacing the drive belt on a whirlpool front-load washing machine by lifting and sliding out the rear panel cabinet plugs, removing the mounting screws, sliding the panel down and out, rotating the tub drive pulley to help unthread the old drive belt, and pulling it free.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_2yHZZmKAUck_1.json"},{"id":"panda_v6_37w9qcCac04_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_37w9qcCac04_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_37w9qcCac04_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_37w9qcCac04_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"tool_contact_state_change","spatialAbility":"tool_contact_state_change, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"Person is pouring syrup on a stack of pancakes with blackberries on top.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_37w9qcCac04_2.json"},{"id":"panda_v6_3Z2YXtVRZMg_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_3Z2YXtVRZMg_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_3Z2YXtVRZMg_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_3Z2YXtVRZMg_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"support_rolling_contact","spatialAbility":"support_rolling_contact, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"The camera is walking through a forest with fallen leaves on the ground.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_3Z2YXtVRZMg_1.json"},{"id":"panda_v6_4D6WF-qrFyE_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_4D6WF-qrFyE_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_4D6WF-qrFyE_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_4D6WF-qrFyE_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"reflection_surface","spatialAbility":"reflection_surface, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is washing beans in a stainless steel sink using their fingers to ensure they are clean before draining the water and adding more water for rinsing.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_4D6WF-qrFyE_0.json"},{"id":"panda_v6_4fGVlEBwqls_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_4fGVlEBwqls_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_4fGVlEBwqls_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_4fGVlEBwqls_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"support_rolling_contact","spatialAbility":"support_rolling_contact, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"There is a parade at disney's magic kingdom, and people are riding on floats with mickey mouse on board.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_4fGVlEBwqls_1.json"},{"id":"panda_v6_4VZ5-5voQ90_0","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_4VZ5-5voQ90_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_4VZ5-5voQ90_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_4VZ5-5voQ90_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled motion","scene":"driving","spatialAbility":"Direction and Trajectory, Relative and Coupled Motion","perspective":"Egocentric","caption":"A person is walking through an indian street at night and passing by shops and people.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_4VZ5-5voQ90_0.json"},{"id":"panda_v6_59p1PLDqbTU_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_59p1PLDqbTU_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_59p1PLDqbTU_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_59p1PLDqbTU_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"reflection_surface","spatialAbility":"reflection_surface, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"People are walking on a transparent glass walkway over the edge of a cliff.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_59p1PLDqbTU_0.json"},{"id":"panda_v6_5aXvRUl-WxI_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_5aXvRUl-WxI_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_5aXvRUl-WxI_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_5aXvRUl-WxI_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"sports_trajectory","spatialAbility":"sports_trajectory, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"The player is in a minecraft game and is walking through a village with houses, trees, and flowers.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_5aXvRUl-WxI_2.json"},{"id":"panda_v6_5m1jm55yIf4_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_5m1jm55yIf4_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_5m1jm55yIf4_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_5m1jm55yIf4_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"topology_navigation","spatialAbility":"topology_navigation, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"The driver of a convertible car is driving on a winding road in the countryside, passing by other cars and pedestrians.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_5m1jm55yIf4_0.json"},{"id":"panda_v6_5Pqo-rvX8SE_0","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_5Pqo-rvX8SE_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_5Pqo-rvX8SE_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_5Pqo-rvX8SE_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled motion","scene":"driving","spatialAbility":"Direction and Trajectory, Relative and Coupled Motion","perspective":"Egocentric","caption":"The camera is mounted on a moving vehicle, driving through a scenic coastal road with lush green trees and blue ocean in the background.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_5Pqo-rvX8SE_0.json"},{"id":"panda_v6_5QomH2DaZF8_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_5QomH2DaZF8_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_5QomH2DaZF8_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_5QomH2DaZF8_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"human_object_interaction","spatialAbility":"human_object_interaction, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A person is holding a pink flower in their hand, and the camera zooms in on the flower.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_5QomH2DaZF8_1.json"},{"id":"panda_v6_5uuzDpp_40o_2","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_5uuzDpp_40o_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_5uuzDpp_40o_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_5uuzDpp_40o_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"A young man is riding a skateboard in a skate park.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_5uuzDpp_40o_2.json"},{"id":"panda_v6_6ATR4La7Ook_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_6ATR4La7Ook_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_6ATR4La7Ook_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_6ATR4La7Ook_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"reflection_surface","spatialAbility":"reflection_surface, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"The person is making a flower arrangement using water and flowers.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_6ATR4La7Ook_2.json"},{"id":"panda_v6_6L2er6l63Lw_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_6L2er6l63Lw_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_6L2er6l63Lw_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_6L2er6l63Lw_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"support_rolling_contact","spatialAbility":"support_rolling_contact, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"There is a wooden floor in an old barn and the camera moves along the length of the floor.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_6L2er6l63Lw_0.json"},{"id":"panda_v6_6rrpihcHH34_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_6rrpihcHH34_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_6rrpihcHH34_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_6rrpihcHH34_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"occlusion_containment","spatialAbility":"occlusion_containment, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is completing a flower base by matching up the flower edge, following score lines on the back, and attaching a clothes pin cover.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_6rrpihcHH34_0.json"},{"id":"panda_v6_7COT9cmD5Ig_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_7COT9cmD5Ig_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_7COT9cmD5Ig_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_7COT9cmD5Ig_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"topology_navigation","spatialAbility":"topology_navigation, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"The driver and his co-driver are driving a car in a race track.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_7COT9cmD5Ig_0.json"},{"id":"panda_v6_7gK3fihKkec_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_7gK3fihKkec_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_7gK3fihKkec_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_7gK3fihKkec_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"support_rolling_contact","spatialAbility":"support_rolling_contact, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is using a rolling pin to roll out dough on a wooden cutting board.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_7gK3fihKkec_0.json"},{"id":"panda_v6_7hghpLueO3k_1","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_7hghpLueO3k_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_7hghpLueO3k_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_7hghpLueO3k_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled motion","scene":"driving","spatialAbility":"Direction and Trajectory, Relative and Coupled Motion","perspective":"Egocentric","caption":"A tractor is driving on a field and the driver's hand is holding the steering wheel.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_7hghpLueO3k_1.json"},{"id":"panda_v6_830qJ538Ejc_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_830qJ538Ejc_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_830qJ538Ejc_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_830qJ538Ejc_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"support_rolling_contact","spatialAbility":"support_rolling_contact, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is cutting a green pepper on a cutting board next to a bowl and sink with a knife.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_830qJ538Ejc_1.json"},{"id":"panda_v6_87NjN6rfGi4_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_87NjN6rfGi4_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_87NjN6rfGi4_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_87NjN6rfGi4_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"topology_navigation","spatialAbility":"topology_navigation, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A car is driving down a street in a small town, passing by buildings and people walking on the sidewalk.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_87NjN6rfGi4_1.json"},{"id":"panda_v6_90fv9VAROZU_1","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_90fv9VAROZU_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_90fv9VAROZU_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_90fv9VAROZU_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"human interaction","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"The dough is being rolled out on a cutting board with fruit inside, and the person starts from the longest edge and rolls towards the other edge first lightly to secure everything.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_90fv9VAROZU_1.json"},{"id":"panda_v6_9aor0Rr7L98_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_9aor0Rr7L98_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_9aor0Rr7L98_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_9aor0Rr7L98_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"reflection_surface","spatialAbility":"reflection_surface, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A woman and a child are riding on a blue water ride in an amusement park.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_9aor0Rr7L98_0.json"},{"id":"panda_v6_9lwf6zGWB8I_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_9lwf6zGWB8I_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_9lwf6zGWB8I_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_9lwf6zGWB8I_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"occlusion_containment","spatialAbility":"occlusion_containment, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A woman with a hat rides a bike through a forest with a basket and another person walking behind her.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_9lwf6zGWB8I_0.json"},{"id":"panda_v6_9w-ZltyGYO4_1","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_9w-ZltyGYO4_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_9w-ZltyGYO4_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_9w-ZltyGYO4_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled motion","scene":"human interaction","spatialAbility":"Direction and Trajectory, Relative and Coupled Motion","perspective":"Egocentric","caption":"A person is kayaking on the water and passing by a wooden dock.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_9w-ZltyGYO4_1.json"},{"id":"panda_v6__-urLNCdTyk_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6__-urLNCdTyk_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6__-urLNCdTyk_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6__-urLNCdTyk_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"human_object_interaction","spatialAbility":"human_object_interaction, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A group of people riding skateboards in a skate park.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6__-urLNCdTyk_1.json"},{"id":"panda_v6__Bv7o4TxN2E_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6__Bv7o4TxN2E_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6__Bv7o4TxN2E_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6__Bv7o4TxN2E_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"reflection_surface","spatialAbility":"reflection_surface, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"The couple is walking on a white sandy beach with clear blue water in the background.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6__Bv7o4TxN2E_0.json"},{"id":"panda_v6__CHpExEskxw_0","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6__CHpExEskxw_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6__CHpExEskxw_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6__CHpExEskxw_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"human interaction","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"Person is pouring olive oil into a frying pan.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6__CHpExEskxw_0.json"},{"id":"panda_v6__kuQXbMKfA8_2","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6__kuQXbMKfA8_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6__kuQXbMKfA8_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6__kuQXbMKfA8_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled motion","scene":"daily activity","spatialAbility":"Direction and Trajectory, Relative and Coupled Motion","perspective":"Egocentric","caption":"A man is walking on a wooden dock in the middle of a lake covered in snow,.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6__kuQXbMKfA8_2.json"},{"id":"panda_v6__LF_u2p-Hgc_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6__LF_u2p-Hgc_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6__LF_u2p-Hgc_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6__LF_u2p-Hgc_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"tool_contact_state_change","spatialAbility":"tool_contact_state_change, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A person is walking through an abandoned house and cutting down overgrown plants with a machete.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6__LF_u2p-Hgc_2.json"},{"id":"panda_v6__z87gLhBFhc_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6__z87gLhBFhc_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6__z87gLhBFhc_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6__z87gLhBFhc_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"occlusion_containment","spatialAbility":"occlusion_containment, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A dog is running through the woods on a cloudy day. the dog is wearing pants, and there are trees in the background.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6__z87gLhBFhc_1.json"},{"id":"panda_v6__ZGo16iMEKc_2","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6__ZGo16iMEKc_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6__ZGo16iMEKc_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6__ZGo16iMEKc_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"driving","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"People are crossing the street at a crosswalk with a crossing guard.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6__ZGo16iMEKc_2.json"},{"id":"panda_v6__Zvsnl7QcCQ_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6__Zvsnl7QcCQ_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6__Zvsnl7QcCQ_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6__Zvsnl7QcCQ_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"support_rolling_contact","spatialAbility":"support_rolling_contact, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is using a rolling pin to roll out dough on a cutting board.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6__Zvsnl7QcCQ_0.json"},{"id":"panda_v6_A1uwyo_EgF4_1","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_A1uwyo_EgF4_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_A1uwyo_EgF4_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_A1uwyo_EgF4_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"human interaction","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"A person is cutting a pair of pants with scissors.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_A1uwyo_EgF4_1.json"},{"id":"panda_v6_a55Xm79UGBE_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_a55Xm79UGBE_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_a55Xm79UGBE_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_a55Xm79UGBE_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"human_object_interaction","spatialAbility":"human_object_interaction, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"There is a horse rider on a black horse riding on a path surrounded by people watching.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_a55Xm79UGBE_2.json"},{"id":"panda_v6_A7QHv7S2Wzg_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_A7QHv7S2Wzg_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_A7QHv7S2Wzg_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_A7QHv7S2Wzg_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"tool_contact_state_change","spatialAbility":"tool_contact_state_change, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is using a serrated knife to crack open a quail egg by turning the smaller end of the egg up and puncturing it with the knife, then tipping the egg over to pour out the contents.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_A7QHv7S2Wzg_1.json"},{"id":"panda_v6_AbcN7wUtpvk_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_AbcN7wUtpvk_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_AbcN7wUtpvk_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_AbcN7wUtpvk_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"reflection_surface","spatialAbility":"reflection_surface, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"The person is using a sprayer to rinse plants and the surrounding landscape with clear water, turning the sprayer to the off position and shutting off the water flow before removing from the hose.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_AbcN7wUtpvk_1.json"},{"id":"panda_v6_aFuJcDYXb30_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_aFuJcDYXb30_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_aFuJcDYXb30_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_aFuJcDYXb30_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"topology_navigation","spatialAbility":"topology_navigation, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"The camera is mounted on a moving car, driving through the city and passing by various landmarks.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_aFuJcDYXb30_2.json"},{"id":"panda_v6_AKwxMNzS-FE_0","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_AKwxMNzS-FE_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_AKwxMNzS-FE_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_AKwxMNzS-FE_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled motion","scene":"human interaction","spatialAbility":"Direction and Trajectory, Relative and Coupled Motion","perspective":"Egocentric","caption":"People are riding on inflatable tubes in a water park.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_AKwxMNzS-FE_0.json"},{"id":"panda_v6_AljMEQA2R6s_1","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_AljMEQA2R6s_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_AljMEQA2R6s_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_AljMEQA2R6s_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"human interaction","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"A person is making crescent rolls by lightly flouring a surface, cutting a quarter of an inch of cream cheese, laying it in the large end of the dough, covering it with three or four pieces of pepperoni, rolling it up, and laying it on a baking sheet.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_AljMEQA2R6s_1.json"},{"id":"panda_v6_aYdL8dNTeOI_1","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_aYdL8dNTeOI_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_aYdL8dNTeOI_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_aYdL8dNTeOI_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"human interaction","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"A person pouring olive oil into a pan with some rosemary in it.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_aYdL8dNTeOI_1.json"},{"id":"panda_v6_B0zKFtbLNd8_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_B0zKFtbLNd8_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_B0zKFtbLNd8_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_B0zKFtbLNd8_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"reflection_surface","spatialAbility":"reflection_surface, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A crowd of people watch as a person riding a horse jumps over a fence into a puddle of water.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_B0zKFtbLNd8_1.json"},{"id":"panda_v6_B2VTfYJgvNg_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_B2VTfYJgvNg_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_B2VTfYJgvNg_0.mp4","initialFrameUrl":"","sourceDataset":"Panda-70M","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":""},{"id":"panda_v6_B3LQREWgtN0_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_B3LQREWgtN0_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_B3LQREWgtN0_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_B3LQREWgtN0_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"topology_navigation","spatialAbility":"topology_navigation, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A young man in a red shirt rides a skateboard down a ramp at an indoor skate park.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_B3LQREWgtN0_1.json"},{"id":"panda_v6_B853Tlpmc94_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_B853Tlpmc94_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_B853Tlpmc94_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_B853Tlpmc94_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"human_object_interaction","spatialAbility":"human_object_interaction, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A person is walking on a walkway made of flagstone and stone for a driveway or sidewalk.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_B853Tlpmc94_2.json"},{"id":"panda_v6_bBfoO-si_NI_1","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_bBfoO-si_NI_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_bBfoO-si_NI_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_bBfoO-si_NI_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled motion","scene":"object physics","spatialAbility":"Direction and Trajectory, Relative and Coupled Motion","perspective":"Egocentric","caption":"A black iphone is placed on a wooden table and the camera pans around it, revealing different angles of the device.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_bBfoO-si_NI_1.json"},{"id":"panda_v6_BCu1CQs4jfY_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_BCu1CQs4jfY_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_BCu1CQs4jfY_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_BCu1CQs4jfY_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"sports_trajectory","spatialAbility":"sports_trajectory, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"The player is walking through a winter wonderland, with snow falling and stars shining in the sky.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_BCu1CQs4jfY_0.json"},{"id":"panda_v6_BgWgzk0vkxI_0","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_BgWgzk0vkxI_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_BgWgzk0vkxI_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_BgWgzk0vkxI_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative and Coupled Motion","perspective":"Egocentric","caption":"The player is in a minecraft game and they are walking through a grassy field.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_BgWgzk0vkxI_0.json"},{"id":"panda_v6_bHrj4cVxnSQ_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_bHrj4cVxnSQ_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_bHrj4cVxnSQ_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_bHrj4cVxnSQ_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"occlusion_containment","spatialAbility":"occlusion_containment, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A beautiful young woman in a white dress is walking through a field of grass and flowers, throwing seeds into the air.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_bHrj4cVxnSQ_0.json"},{"id":"panda_v6_BL-cr0szVh4_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_BL-cr0szVh4_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_BL-cr0szVh4_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_BL-cr0szVh4_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"reflection_surface","spatialAbility":"reflection_surface, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A person is walking on a frozen lake and the camera follows them as they walk.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_BL-cr0szVh4_2.json"},{"id":"panda_v6_BM_4VU9FJSw_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_BM_4VU9FJSw_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_BM_4VU9FJSw_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_BM_4VU9FJSw_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"support_rolling_contact","spatialAbility":"support_rolling_contact, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is using a knife to cut sushi rolls on a wooden cutting board.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_BM_4VU9FJSw_2.json"},{"id":"panda_v6_byIEwtRCL34_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_byIEwtRCL34_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_byIEwtRCL34_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_byIEwtRCL34_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"sports_trajectory","spatialAbility":"sports_trajectory, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"The player is in a minecraft game and they are walking through a field with flowers.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_byIEwtRCL34_2.json"},{"id":"panda_v6_cah43_hs6hw_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_cah43_hs6hw_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_cah43_hs6hw_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_cah43_hs6hw_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"topology_navigation","spatialAbility":"topology_navigation, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A skateboarder is riding on a wooden ramp in an indoor skate park.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_cah43_hs6hw_2.json"},{"id":"panda_v6_Caz7abtsHQk_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_Caz7abtsHQk_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_Caz7abtsHQk_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_Caz7abtsHQk_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"reflection_surface","spatialAbility":"reflection_surface, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"There is a glass of milk on a countertop, and the camera zooms in to show the details of the milk.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_Caz7abtsHQk_2.json"},{"id":"panda_v6_cCYhxz9qVHI_0","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_cCYhxz9qVHI_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_cCYhxz9qVHI_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_cCYhxz9qVHI_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"driving","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"The driver is driving a car and passing by a school building on a sunny day.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_cCYhxz9qVHI_0.json"},{"id":"panda_v6_CfAOasdm8ks_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_CfAOasdm8ks_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_CfAOasdm8ks_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_CfAOasdm8ks_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"support_rolling_contact","spatialAbility":"support_rolling_contact, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is using a rolling pin to roll out dough on a wooden cutting board.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_CfAOasdm8ks_2.json"},{"id":"panda_v6_CFrYuDIFf-Y_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_CFrYuDIFf-Y_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_CFrYuDIFf-Y_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_CFrYuDIFf-Y_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"topology_navigation","spatialAbility":"topology_navigation, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A young man rides a skateboard down a ramp at an indoor skate park with other people watching.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_CFrYuDIFf-Y_1.json"},{"id":"panda_v6_cv6BdwMe560_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_cv6BdwMe560_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_cv6BdwMe560_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_cv6BdwMe560_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"tool_contact_state_change","spatialAbility":"tool_contact_state_change, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A man walking on a construction site with a red tool in his hand.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_cv6BdwMe560_0.json"},{"id":"panda_v6_CxKb7sZSfyU_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_CxKb7sZSfyU_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_CxKb7sZSfyU_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_CxKb7sZSfyU_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"human_object_interaction","spatialAbility":"human_object_interaction, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"The video is about a group of people riding on a roller coaster.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_CxKb7sZSfyU_0.json"},{"id":"panda_v6_CyykFX0uPJU_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_CyykFX0uPJU_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_CyykFX0uPJU_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_CyykFX0uPJU_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"human_object_interaction","spatialAbility":"human_object_interaction, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"Person timberlake and jimmy fallon are sitting on a couch facing each other. they are both wearing suits and have serious expressions on their faces as they take turns doing a slow turn and trying to do the tiniest nod possible without laughing.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_CyykFX0uPJU_0.json"},{"id":"panda_v6_cyYVaAAN9Fg_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_cyYVaAAN9Fg_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_cyYVaAAN9Fg_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_cyYVaAAN9Fg_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"sports_trajectory","spatialAbility":"sports_trajectory, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A young man is riding his skateboard at a skate park, performing various tricks and stunts.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_cyYVaAAN9Fg_1.json"},{"id":"panda_v6_D-N7GCflqPE_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_D-N7GCflqPE_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_D-N7GCflqPE_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_D-N7GCflqPE_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"human_object_interaction","spatialAbility":"human_object_interaction, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A person is riding on a roller coaster at an amusement park.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_D-N7GCflqPE_2.json"},{"id":"panda_v6_d6NngIiG-y8_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_d6NngIiG-y8_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_d6NngIiG-y8_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_d6NngIiG-y8_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"tool_contact_state_change","spatialAbility":"tool_contact_state_change, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A man with a tool belt walking on a construction site.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_d6NngIiG-y8_1.json"},{"id":"panda_v6_d8AUtPER5U0_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_d8AUtPER5U0_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_d8AUtPER5U0_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_d8AUtPER5U0_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"topology_navigation","spatialAbility":"topology_navigation, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A tractor is driving on a field and the driver's view of the instrument panel.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_d8AUtPER5U0_2.json"},{"id":"panda_v6_diU2P_YEVcI_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_diU2P_YEVcI_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_diU2P_YEVcI_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_diU2P_YEVcI_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"tool_contact_state_change","spatialAbility":"tool_contact_state_change, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"The person is walking through a hallway and holding a vending machine token.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_diU2P_YEVcI_0.json"},{"id":"panda_v6_dPSDqoyQFGA_2","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_dPSDqoyQFGA_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_dPSDqoyQFGA_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_dPSDqoyQFGA_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"human interaction","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"A person is riding a roller coaster inside of a building.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_dPSDqoyQFGA_2.json"},{"id":"panda_v6_dqNH7sAJaP8_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_dqNH7sAJaP8_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_dqNH7sAJaP8_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_dqNH7sAJaP8_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"human_object_interaction","spatialAbility":"human_object_interaction, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is making a flower from dough by carefully lifting each petal from one side and turning it around to the other side, then overlapping the first petal with the last petal to create a flower.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_dqNH7sAJaP8_0.json"},{"id":"panda_v6_e-ir0l7TEXM_2","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_e-ir0l7TEXM_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_e-ir0l7TEXM_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_e-ir0l7TEXM_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative and Coupled Motion","perspective":"Egocentric","caption":"The woman is wearing a red dress and walking on a rocky terrain with a golf club in her hand.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_e-ir0l7TEXM_2.json"},{"id":"panda_v6_e3aKw7Cp5EA_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_e3aKw7Cp5EA_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_e3aKw7Cp5EA_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_e3aKw7Cp5EA_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"sports_trajectory","spatialAbility":"sports_trajectory, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is riding a bicycle and performing a stunt called a \"bomb drop\" where they jump off a ledge and land on the bike.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_e3aKw7Cp5EA_2.json"},{"id":"panda_v6_E8HQyNhHbJk_0","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_E8HQyNhHbJk_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_E8HQyNhHbJk_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_E8HQyNhHbJk_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled motion","scene":"object physics","spatialAbility":"Direction and Trajectory, Relative and Coupled Motion","perspective":"Egocentric","caption":"A woman is walking through a field of grass and flowers.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_E8HQyNhHbJk_0.json"},{"id":"panda_v6_EfL5OD79o2w_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_EfL5OD79o2w_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_EfL5OD79o2w_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_EfL5OD79o2w_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"reflection_surface","spatialAbility":"reflection_surface, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is washing lettuce in a kitchen sink with running water.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_EfL5OD79o2w_0.json"},{"id":"panda_v6_ElVMhC1y-34_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_ElVMhC1y-34_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_ElVMhC1y-34_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_ElVMhC1y-34_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"sports_trajectory","spatialAbility":"sports_trajectory, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"The player is mining blocks in a minecraft game, and the camera pans out to show snow falling in the background.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_ElVMhC1y-34_1.json"},{"id":"panda_v6_eM6XYQdLsEU_0","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_eM6XYQdLsEU_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_eM6XYQdLsEU_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_eM6XYQdLsEU_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"The dallas cowboys are running a fake punt play in which the quarterback, dak prescott, is running with the ball and has a lot of room to run.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_eM6XYQdLsEU_0.json"},{"id":"panda_v6_EomHbPMYX_w_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_EomHbPMYX_w_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_EomHbPMYX_w_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_EomHbPMYX_w_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"sports_trajectory","spatialAbility":"sports_trajectory, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"The player is walking on an airport runway.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_EomHbPMYX_w_0.json"},{"id":"panda_v6_ev6GyawNigc_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_ev6GyawNigc_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_ev6GyawNigc_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_ev6GyawNigc_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"occlusion_containment","spatialAbility":"occlusion_containment, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A man is walking along a path in a rocky terrain, and the camera follows him from behind.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_ev6GyawNigc_1.json"},{"id":"panda_v6_EXhh6PX3eF4_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_EXhh6PX3eF4_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_EXhh6PX3eF4_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_EXhh6PX3eF4_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"human_object_interaction","spatialAbility":"human_object_interaction, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"There is a yellow flower growing in the grass, and a person is walking in the grass and picking the flower.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_EXhh6PX3eF4_1.json"},{"id":"panda_v6_ezVNk34f2Cc_2","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_ezVNk34f2Cc_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_ezVNk34f2Cc_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_ezVNk34f2Cc_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled motion","scene":"human interaction","spatialAbility":"Direction and Trajectory, Relative and Coupled Motion","perspective":"Egocentric","caption":"A person is walking on a rooftop and jumping down.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_ezVNk34f2Cc_2.json"},{"id":"panda_v6_f30ARHKLVI0_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_f30ARHKLVI0_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_f30ARHKLVI0_0.mp4","initialFrameUrl":"","sourceDataset":"Panda-70M","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":""},{"id":"panda_v6_fAc2YDLZ9ZY_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_fAc2YDLZ9ZY_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_fAc2YDLZ9ZY_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_fAc2YDLZ9ZY_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"occlusion_containment","spatialAbility":"occlusion_containment, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A person is walking through an abandoned house and the camera follows them as they walk down a dimly lit hallway.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_fAc2YDLZ9ZY_1.json"},{"id":"panda_v6_fi-Axv9-ZBk_2","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_fi-Axv9-ZBk_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_fi-Axv9-ZBk_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_fi-Axv9-ZBk_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"human interaction","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"A group of people cutting a ribbon at a ribbon cutting ceremony.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_fi-Axv9-ZBk_2.json"},{"id":"panda_v6_FI5lNNDu-7c_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_FI5lNNDu-7c_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_FI5lNNDu-7c_1.mp4","initialFrameUrl":"","sourceDataset":"Panda-70M","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":""},{"id":"panda_v6_FPlVmgiAk3M_0","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_FPlVmgiAk3M_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_FPlVmgiAk3M_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_FPlVmgiAk3M_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"A young man is riding a skateboard in a skate park, performing tricks and stunts.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_FPlVmgiAk3M_0.json"},{"id":"panda_v6_fq6WZSXJ7K4_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_fq6WZSXJ7K4_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_fq6WZSXJ7K4_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_fq6WZSXJ7K4_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"human_object_interaction","spatialAbility":"human_object_interaction, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"The person is designing a flower arrangement using carnations and roses. they are arranging the flowers side by side to create a mound that looks beautiful with the textures of the flowers showing up.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_fq6WZSXJ7K4_1.json"},{"id":"panda_v6_Fvh0XuUwM-Y_0","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_Fvh0XuUwM-Y_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_Fvh0XuUwM-Y_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_Fvh0XuUwM-Y_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled motion","scene":"human interaction","spatialAbility":"Direction and Trajectory, Relative and Coupled Motion","perspective":"Egocentric","caption":"There is a roller coaster in an amusement park with people riding on it.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_Fvh0XuUwM-Y_0.json"},{"id":"panda_v6_fWrEtMgnuC8_0","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_fWrEtMgnuC8_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_fWrEtMgnuC8_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_fWrEtMgnuC8_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled motion","scene":"object physics","spatialAbility":"Direction and Trajectory, Relative and Coupled Motion","perspective":"Egocentric","caption":"A black and yellow lizard is walking on the ground in the forest.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_fWrEtMgnuC8_0.json"},{"id":"panda_v6_fWvKyNeZPaA_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_fWvKyNeZPaA_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_fWvKyNeZPaA_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_fWvKyNeZPaA_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"topology_navigation","spatialAbility":"topology_navigation, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"There is a person riding a bicycle on a street with other people walking and driving cars.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_fWvKyNeZPaA_1.json"},{"id":"panda_v6_G_b_0NcclZk_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_G_b_0NcclZk_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_G_b_0NcclZk_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_G_b_0NcclZk_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"sports_trajectory","spatialAbility":"sports_trajectory, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A young man is riding a skateboard in an indoor skate park. he is wearing a blue shirt and black pants, and he has a beard.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_G_b_0NcclZk_1.json"},{"id":"panda_v6_gcnF4idGj7c_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_gcnF4idGj7c_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_gcnF4idGj7c_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_gcnF4idGj7c_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"sports_trajectory","spatialAbility":"sports_trajectory, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"The player is in a minecraft game, walking through a village with pink houses and flowers.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_gcnF4idGj7c_2.json"},{"id":"panda_v6_GeT76UIY7pU_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_GeT76UIY7pU_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_GeT76UIY7pU_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_GeT76UIY7pU_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"human_object_interaction","spatialAbility":"human_object_interaction, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A person is walking along a field of yellow rapeseed and pointing out the flowers.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_GeT76UIY7pU_1.json"},{"id":"panda_v6_gktzh-GvfnI_2","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_gktzh-GvfnI_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_gktzh-GvfnI_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_gktzh-GvfnI_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"A person enters a house through an arched doorway and walks towards the living room.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_gktzh-GvfnI_2.json"},{"id":"panda_v6_GKUgZtGiPRI_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_GKUgZtGiPRI_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_GKUgZtGiPRI_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_GKUgZtGiPRI_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"occlusion_containment","spatialAbility":"occlusion_containment, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"The user is playing a game in minecraft. the video starts with the user walking through a hallway, and then he enters a room with a door. he then walks through a corridor and enters another room with a door.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_GKUgZtGiPRI_2.json"},{"id":"panda_v6_gN898QtfB-k_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_gN898QtfB-k_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_gN898QtfB-k_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_gN898QtfB-k_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"topology_navigation","spatialAbility":"topology_navigation, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A truck has crashed into a honda accord on fm 1485 and forest drive in montgomery county, resulting in the death of the driver of the car and the driver of the truck being taken to the hospital in critical condition.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_gN898QtfB-k_2.json"},{"id":"panda_v6_gPxGjUsD4iM_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_gPxGjUsD4iM_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_gPxGjUsD4iM_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_gPxGjUsD4iM_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"occlusion_containment","spatialAbility":"occlusion_containment, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A man is walking through a dark forest and the camera follows him as he walks.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_gPxGjUsD4iM_1.json"},{"id":"panda_v6_grUb_SwD2qs_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_grUb_SwD2qs_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_grUb_SwD2qs_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_grUb_SwD2qs_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"occlusion_containment","spatialAbility":"occlusion_containment, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A wii game screen showing a person walking through a field of flowers.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_grUb_SwD2qs_1.json"},{"id":"panda_v6_gSI7XFq6Aeg_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_gSI7XFq6Aeg_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_gSI7XFq6Aeg_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_gSI7XFq6Aeg_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"topology_navigation","spatialAbility":"topology_navigation, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A person is walking on a snowy road and the camera follows them as they walk.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_gSI7XFq6Aeg_2.json"},{"id":"panda_v6_gV2imEtTEss_2","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_gV2imEtTEss_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_gV2imEtTEss_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_gV2imEtTEss_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"A young man is riding a skateboard and jumping in the air on a ramp near a building.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_gV2imEtTEss_2.json"},{"id":"panda_v6_gYNKP2SSsQs_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_gYNKP2SSsQs_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_gYNKP2SSsQs_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_gYNKP2SSsQs_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"tool_contact_state_change","spatialAbility":"tool_contact_state_change, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"Person information about cutting fabric with a rotary cutter and self-healing cutting mat is provided.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_gYNKP2SSsQs_1.json"},{"id":"panda_v6_Ha-l2qCbFms_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_Ha-l2qCbFms_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_Ha-l2qCbFms_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_Ha-l2qCbFms_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"occlusion_containment","spatialAbility":"occlusion_containment, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A skydiver is jumping out of an airplane with a parachute and the camera captures his point of view as he falls through the sky.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_Ha-l2qCbFms_1.json"},{"id":"panda_v6_haKOP1O7mK0_2","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_haKOP1O7mK0_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_haKOP1O7mK0_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_haKOP1O7mK0_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative and Coupled Motion","perspective":"Egocentric","caption":"A person is riding on roller skates in an empty parking garage.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_haKOP1O7mK0_2.json"},{"id":"panda_v6_HCEaF7yKxNs_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_HCEaF7yKxNs_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_HCEaF7yKxNs_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_HCEaF7yKxNs_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"tool_contact_state_change","spatialAbility":"tool_contact_state_change, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"The person is walking on a stairmaster machine at the gym.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_HCEaF7yKxNs_2.json"},{"id":"panda_v6_HgL2Jx7dujc_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_HgL2Jx7dujc_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_HgL2Jx7dujc_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_HgL2Jx7dujc_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"reflection_surface","spatialAbility":"reflection_surface, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A raccoon is walking along the edge of a pond in a grassy area.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_HgL2Jx7dujc_2.json"},{"id":"panda_v6_HHdJjVbTcFc_1","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_HHdJjVbTcFc_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_HHdJjVbTcFc_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_HHdJjVbTcFc_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative and Coupled Motion","perspective":"Egocentric","caption":"The player is walking through a dark and eerie medieval town with old stone buildings and cobblestone streets.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_HHdJjVbTcFc_1.json"},{"id":"panda_v6_HIi1aSpJLRQ_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_HIi1aSpJLRQ_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_HIi1aSpJLRQ_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_HIi1aSpJLRQ_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"topology_navigation","spatialAbility":"topology_navigation, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"The player is driving a car in a racing game and the view is from the driver's seat.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_HIi1aSpJLRQ_1.json"},{"id":"panda_v6_HM0dElxjhsg_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_HM0dElxjhsg_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_HM0dElxjhsg_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_HM0dElxjhsg_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"reflection_surface","spatialAbility":"reflection_surface, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is washing their hands in a bathroom sink with soap and water running from the faucet.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_HM0dElxjhsg_0.json"},{"id":"panda_v6_hY1ZFD48gIE_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_hY1ZFD48gIE_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_hY1ZFD48gIE_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_hY1ZFD48gIE_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"reflection_surface","spatialAbility":"reflection_surface, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A man and woman are walking along a path near a lake or pond with their dogs.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_hY1ZFD48gIE_2.json"},{"id":"panda_v6_HYk5GCTvK0c_2","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_HYk5GCTvK0c_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_HYk5GCTvK0c_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_HYk5GCTvK0c_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled motion","scene":"daily activity","spatialAbility":"Direction and Trajectory, Relative and Coupled Motion","perspective":"Egocentric","caption":"A dog and two other dogs are walking on a beach with a lake in the background.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_HYk5GCTvK0c_2.json"},{"id":"panda_v6_IcDsNs3ToE0_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_IcDsNs3ToE0_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_IcDsNs3ToE0_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_IcDsNs3ToE0_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"topology_navigation","spatialAbility":"topology_navigation, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A car is driving on a city street, with the driver's side window showing a view of the street and other cars passing by.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_IcDsNs3ToE0_0.json"},{"id":"panda_v6_IEnS68STqNc_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_IEnS68STqNc_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_IEnS68STqNc_2.mp4","initialFrameUrl":"","sourceDataset":"Panda-70M","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":""},{"id":"panda_v6_iFrtzDEGdHY_2","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_iFrtzDEGdHY_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_iFrtzDEGdHY_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_iFrtzDEGdHY_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"human interaction","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"A person is walking down a dark staircase and the camera follows them from behind.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_iFrtzDEGdHY_2.json"},{"id":"panda_v6_IGxDfqHcMhE_0","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_IGxDfqHcMhE_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_IGxDfqHcMhE_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_IGxDfqHcMhE_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"A young man rides a skateboard down a ramp at a skate park with mountains in the background.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_IGxDfqHcMhE_0.json"},{"id":"panda_v6_IhhZJ0_P9Ng_1","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_IhhZJ0_P9Ng_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_IhhZJ0_P9Ng_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_IhhZJ0_P9Ng_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"A person riding a skateboard in a skate park.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_IhhZJ0_P9Ng_1.json"},{"id":"panda_v6_Ihw64E9YMBI_2","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_Ihw64E9YMBI_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_Ihw64E9YMBI_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_Ihw64E9YMBI_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative and Coupled Motion","perspective":"Egocentric","caption":"A young man is walking through a parking lot at night with a skateboard.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_Ihw64E9YMBI_2.json"},{"id":"panda_v6_IJ-h0SO8EUI_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_IJ-h0SO8EUI_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_IJ-h0SO8EUI_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_IJ-h0SO8EUI_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"tool_contact_state_change","spatialAbility":"tool_contact_state_change, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is using a knife to cut the bottom of a watermelon and then reshaping the opening to create a pouring spout.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_IJ-h0SO8EUI_1.json"},{"id":"panda_v6_IL4K2V82hiw_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_IL4K2V82hiw_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_IL4K2V82hiw_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_IL4K2V82hiw_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"topology_navigation","spatialAbility":"topology_navigation, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"There is a purple car driving on a street, passing through a traffic light, and turning left at an intersection.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_IL4K2V82hiw_2.json"},{"id":"panda_v6_IlIvagCXHCc_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_IlIvagCXHCc_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_IlIvagCXHCc_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_IlIvagCXHCc_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"human_object_interaction","spatialAbility":"human_object_interaction, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is installing a sink in a kitchen, and they need to run a bead of silicone around the whole underside of the sink before placing it in the cutout.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_IlIvagCXHCc_2.json"},{"id":"panda_v6_IOHZAMxyzDc_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_IOHZAMxyzDc_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_IOHZAMxyzDc_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_IOHZAMxyzDc_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"support_rolling_contact","spatialAbility":"support_rolling_contact, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"Three different lenses are placed on a table and the camera pans around them.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_IOHZAMxyzDc_1.json"},{"id":"panda_v6_Is7obNhL9XE_1","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_Is7obNhL9XE_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_Is7obNhL9XE_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_Is7obNhL9XE_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled motion","scene":"human interaction","spatialAbility":"Direction and Trajectory, Relative and Coupled Motion","perspective":"Egocentric","caption":"A group of people walking through a room with a wall covered in paint.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_Is7obNhL9XE_1.json"},{"id":"panda_v6_ixjrqtXYsS4_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_ixjrqtXYsS4_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_ixjrqtXYsS4_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_ixjrqtXYsS4_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"tool_contact_state_change","spatialAbility":"tool_contact_state_change, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A person walking on a tread machine.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_ixjrqtXYsS4_2.json"},{"id":"panda_v6_jGA51f0u-Ts_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_jGA51f0u-Ts_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_jGA51f0u-Ts_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_jGA51f0u-Ts_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"reflection_surface","spatialAbility":"reflection_surface, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A woman is riding on an inflatable ring in a water park.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_jGA51f0u-Ts_0.json"},{"id":"panda_v6_jlmyhwUfisk_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_jlmyhwUfisk_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_jlmyhwUfisk_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_jlmyhwUfisk_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"sports_trajectory","spatialAbility":"sports_trajectory, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"The player is in a minecraft game, walking through a forest and cutting down trees with an axe.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_jlmyhwUfisk_2.json"},{"id":"panda_v6_JNtggFwafAY_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_JNtggFwafAY_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_JNtggFwafAY_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_JNtggFwafAY_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"human_object_interaction","spatialAbility":"human_object_interaction, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A dragon is riding on top of a float in a parade at night. the float is decorated with lights, and there are people watching the parade.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_JNtggFwafAY_1.json"},{"id":"panda_v6_JQ8l35BFunI_0","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_JQ8l35BFunI_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_JQ8l35BFunI_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_JQ8l35BFunI_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Relative and Coupled Motion","perspective":"Egocentric","caption":"A windsurfer is riding on the water and performing tricks.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_JQ8l35BFunI_0.json"},{"id":"panda_v6_jQKTETdgi2k_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_jQKTETdgi2k_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_jQKTETdgi2k_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_jQKTETdgi2k_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"support_rolling_contact","spatialAbility":"support_rolling_contact, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is using a rolling pin to roll out dough on a cutting board.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_jQKTETdgi2k_0.json"},{"id":"panda_v6_jRWf_k3NnUQ_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_jRWf_k3NnUQ_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_jRWf_k3NnUQ_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_jRWf_k3NnUQ_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"occlusion_containment","spatialAbility":"occlusion_containment, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is holding a battery and a speaker cone, and they are passing electrical current through the voice coil to make the cone move.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_jRWf_k3NnUQ_0.json"},{"id":"panda_v6_JTLTRnMExss_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_JTLTRnMExss_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_JTLTRnMExss_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_JTLTRnMExss_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"occlusion_containment","spatialAbility":"occlusion_containment, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is washing shrimp in a kitchen sink under running water.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_JTLTRnMExss_0.json"},{"id":"panda_v6_jyFyDbu64l8_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_jyFyDbu64l8_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_jyFyDbu64l8_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_jyFyDbu64l8_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"sports_trajectory","spatialAbility":"sports_trajectory, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"There is a person riding a skateboard in an indoor skate park, the person is wearing black shoes and black pants, the walls of the skate park are made of concrete and there are some graffiti on them.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_jyFyDbu64l8_1.json"},{"id":"panda_v6_jZ4_XjHUOV0_2","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_jZ4_XjHUOV0_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_jZ4_XjHUOV0_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_jZ4_XjHUOV0_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled motion","scene":"human interaction","spatialAbility":"Direction and Trajectory, Relative and Coupled Motion","perspective":"Egocentric","caption":"The person is holding a set of rocks on a table, and the camera zooms in to show each rock in detail.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_jZ4_XjHUOV0_2.json"},{"id":"panda_v6_K1-JnupY0do_2","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_K1-JnupY0do_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_K1-JnupY0do_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_K1-JnupY0do_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled motion","scene":"driving","spatialAbility":"Direction and Trajectory, Relative and Coupled Motion","perspective":"Egocentric","caption":"A woman is walking through a hallway in a small apartment, and she is wearing a blue plaid dress and carrying a yellow tool.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_K1-JnupY0do_2.json"},{"id":"panda_v6_K_EisFo6PKE_1","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_K_EisFo6PKE_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_K_EisFo6PKE_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_K_EisFo6PKE_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"human interaction","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"A person is walking towards an old stone building and entering through an arched doorway.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_K_EisFo6PKE_1.json"},{"id":"panda_v6_kbNmkH9e62U_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_kbNmkH9e62U_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_kbNmkH9e62U_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_kbNmkH9e62U_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"tool_contact_state_change","spatialAbility":"tool_contact_state_change, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is assembling an appliance by threading a mounting screw into a bracket, securing the assembly to the bracket, and reinstalling a side panel by aligning the frame tabs with the slots on the front of the panel and snapping the panel into place.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_kbNmkH9e62U_1.json"},{"id":"panda_v6_kf8dPaCLa3k_1","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_kf8dPaCLa3k_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_kf8dPaCLa3k_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_kf8dPaCLa3k_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled motion","scene":"object physics","spatialAbility":"Direction and Trajectory, Relative and Coupled Motion","perspective":"Egocentric","caption":"A man is holding a cordless drill and walking through a hallway.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_kf8dPaCLa3k_1.json"},{"id":"panda_v6_KiGJ_RizEZw_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_KiGJ_RizEZw_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_KiGJ_RizEZw_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_KiGJ_RizEZw_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"human_object_interaction","spatialAbility":"human_object_interaction, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"There is a red flower in a garden, and a person is using a pair of scissors to cut the flower.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_KiGJ_RizEZw_0.json"},{"id":"panda_v6_kLc2oc9lwlM_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_kLc2oc9lwlM_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_kLc2oc9lwlM_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_kLc2oc9lwlM_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"human_object_interaction","spatialAbility":"human_object_interaction, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A group of people walking down a walkway with penguins.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_kLc2oc9lwlM_1.json"},{"id":"panda_v6_kTGh0sR_tJk_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_kTGh0sR_tJk_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_kTGh0sR_tJk_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_kTGh0sR_tJk_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"human_object_interaction","spatialAbility":"human_object_interaction, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A person is walking on a carpet and the camera pans to show different parts of the carpet.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_kTGh0sR_tJk_2.json"},{"id":"panda_v6_KYP8QKOU_wU_1","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_KYP8QKOU_wU_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_KYP8QKOU_wU_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_KYP8QKOU_wU_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled motion","scene":"human interaction","spatialAbility":"Direction and Trajectory, Relative and Coupled Motion","perspective":"Egocentric","caption":"People are biking and walking along a trail by the water.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_KYP8QKOU_wU_1.json"},{"id":"panda_v6_L1V2cE35wr8_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_L1V2cE35wr8_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_L1V2cE35wr8_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_L1V2cE35wr8_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"support_rolling_contact","spatialAbility":"support_rolling_contact, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is cutting meat rolls on a wooden cutting board.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_L1V2cE35wr8_2.json"},{"id":"panda_v6_lCgYmtLT2KM_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_lCgYmtLT2KM_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_lCgYmtLT2KM_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_lCgYmtLT2KM_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"reflection_surface","spatialAbility":"reflection_surface, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A person is walking on grass and stepping on a puddle of water.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_lCgYmtLT2KM_0.json"},{"id":"panda_v6_lDSy5tTx6Y0_1","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_lDSy5tTx6Y0_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_lDSy5tTx6Y0_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_lDSy5tTx6Y0_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"human interaction","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"A person is frying an egg in a pan and turning it over with a spatula.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_lDSy5tTx6Y0_1.json"},{"id":"panda_v6_lIFCIbsD2Hc_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_lIFCIbsD2Hc_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_lIFCIbsD2Hc_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_lIFCIbsD2Hc_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"occlusion_containment","spatialAbility":"occlusion_containment, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person enters a subway station and passes through a turnstile.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_lIFCIbsD2Hc_0.json"},{"id":"panda_v6_LIOcIlJ3kYY_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_LIOcIlJ3kYY_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_LIOcIlJ3kYY_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_LIOcIlJ3kYY_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"sports_trajectory","spatialAbility":"sports_trajectory, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A french bulldog is riding a skateboard in a skate park.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_LIOcIlJ3kYY_0.json"},{"id":"panda_v6_LPJZ1ywNsZ8_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_LPJZ1ywNsZ8_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_LPJZ1ywNsZ8_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_LPJZ1ywNsZ8_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"occlusion_containment","spatialAbility":"occlusion_containment, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is riding a motorcycle in the woods and passing through a campsite.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_LPJZ1ywNsZ8_1.json"},{"id":"panda_v6_LqmAIxg5OhE_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_LqmAIxg5OhE_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_LqmAIxg5OhE_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_LqmAIxg5OhE_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"support_rolling_contact","spatialAbility":"support_rolling_contact, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A person is riding on an amusement park ride and falling to the ground.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_LqmAIxg5OhE_1.json"},{"id":"panda_v6_Ltbq8Kv0H2I_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_Ltbq8Kv0H2I_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_Ltbq8Kv0H2I_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_Ltbq8Kv0H2I_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"human_object_interaction","spatialAbility":"human_object_interaction, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"The person is restoring an old macbook air from 2008 by copying the contents of an external drive to the internal drive and then booting back onto the external drive.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_Ltbq8Kv0H2I_0.json"},{"id":"panda_v6_lxtYzFY2vtQ_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_lxtYzFY2vtQ_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_lxtYzFY2vtQ_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_lxtYzFY2vtQ_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"topology_navigation","spatialAbility":"topology_navigation, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is riding roller skates on an outdoor ramp.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_lxtYzFY2vtQ_1.json"},{"id":"panda_v6_M-qEpChONWU_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_M-qEpChONWU_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_M-qEpChONWU_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_M-qEpChONWU_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"sports_trajectory","spatialAbility":"sports_trajectory, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"The player is walking through a deserted town and approaching an abandoned house.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_M-qEpChONWU_1.json"},{"id":"panda_v6_M2hC5FLnJt8_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_M2hC5FLnJt8_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_M2hC5FLnJt8_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_M2hC5FLnJt8_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"support_rolling_contact","spatialAbility":"support_rolling_contact, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A laptop is placed on a table and the camera pans around it, showing different angles of the device.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_M2hC5FLnJt8_1.json"},{"id":"panda_v6_M5SddILUPi8_1","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_M5SddILUPi8_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_M5SddILUPi8_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_M5SddILUPi8_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative and Coupled Motion","perspective":"Egocentric","caption":"It is a group of people riding on skateboards in an outdoor park with several ramps and a group of people watching them.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_M5SddILUPi8_1.json"},{"id":"panda_v6_malX-TfVfhw_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_malX-TfVfhw_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_malX-TfVfhw_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_malX-TfVfhw_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"sports_trajectory","spatialAbility":"sports_trajectory, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is riding a skateboard at a skate park on a cloudy day.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_malX-TfVfhw_1.json"},{"id":"panda_v6_MD-eGYmkb6U_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_MD-eGYmkb6U_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_MD-eGYmkb6U_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_MD-eGYmkb6U_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"topology_navigation","spatialAbility":"topology_navigation, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A young man in a helmet rides a skateboard down a ramp at an indoor skate park.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_MD-eGYmkb6U_1.json"},{"id":"panda_v6_MEFmFcDxCso_1","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_MEFmFcDxCso_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_MEFmFcDxCso_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_MEFmFcDxCso_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"human interaction","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"A person enters a hotel lobby and walks towards the fireplace.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_MEFmFcDxCso_1.json"},{"id":"panda_v6_MjWE1j9R4xM_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_MjWE1j9R4xM_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_MjWE1j9R4xM_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_MjWE1j9R4xM_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"occlusion_containment","spatialAbility":"occlusion_containment, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is walking in a snowy forest and the camera follows them from behind.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_MjWE1j9R4xM_0.json"},{"id":"panda_v6_nb_32qMsrc0_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_nb_32qMsrc0_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_nb_32qMsrc0_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_nb_32qMsrc0_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"occlusion_containment","spatialAbility":"occlusion_containment, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A person is walking on a wooden pier in a jungle area, passing by tables and chairs under a thatched roof.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_nb_32qMsrc0_2.json"},{"id":"panda_v6_no9BeKCcdt4_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_no9BeKCcdt4_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_no9BeKCcdt4_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_no9BeKCcdt4_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"human_object_interaction","spatialAbility":"human_object_interaction, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"The person is using a smartphone to access the touch id and passcode settings, and then turns off the passcode.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_no9BeKCcdt4_1.json"},{"id":"panda_v6_Nt5K7rkh9sQ_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_Nt5K7rkh9sQ_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_Nt5K7rkh9sQ_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_Nt5K7rkh9sQ_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"tool_contact_state_change","spatialAbility":"tool_contact_state_change, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A person is walking through a metro station and interacting with a ticket machine.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_Nt5K7rkh9sQ_1.json"},{"id":"panda_v6_NXe1gFzF1Bw_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_NXe1gFzF1Bw_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_NXe1gFzF1Bw_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_NXe1gFzF1Bw_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"sports_trajectory","spatialAbility":"sports_trajectory, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A young man is riding a skateboard at a skate park on a cloudy day.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_NXe1gFzF1Bw_2.json"},{"id":"panda_v6_O54MMDAVZOk_1","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_O54MMDAVZOk_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_O54MMDAVZOk_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_O54MMDAVZOk_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled motion","scene":"human interaction","spatialAbility":"Direction and Trajectory, Relative and Coupled Motion","perspective":"Egocentric","caption":"A video game showing two people walking on a brick walkway.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_O54MMDAVZOk_1.json"},{"id":"panda_v6_o5lguvJ0Ezs_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_o5lguvJ0Ezs_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_o5lguvJ0Ezs_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_o5lguvJ0Ezs_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"support_rolling_contact","spatialAbility":"support_rolling_contact, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"Person is walking on a wooden floor and the camera follows the footsteps.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_o5lguvJ0Ezs_0.json"},{"id":"panda_v6_o7PzrY_S3qs_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_o7PzrY_S3qs_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_o7PzrY_S3qs_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_o7PzrY_S3qs_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"topology_navigation","spatialAbility":"topology_navigation, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A person is riding a motorcycle and driving through the city, passing by cars and other vehicles.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_o7PzrY_S3qs_1.json"},{"id":"panda_v6_oA101VqHEmc_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_oA101VqHEmc_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_oA101VqHEmc_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_oA101VqHEmc_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"human_object_interaction","spatialAbility":"human_object_interaction, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is riding a scooter and the camera follows the scooter as it moves.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_oA101VqHEmc_0.json"},{"id":"panda_v6_OaVmf9hBXAw_1","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_OaVmf9hBXAw_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_OaVmf9hBXAw_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_OaVmf9hBXAw_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative and Coupled Motion","perspective":"Egocentric","caption":"The player is in a minecraft game and they are walking through a village at night.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_OaVmf9hBXAw_1.json"},{"id":"panda_v6_ofZDK3OoVHU_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_ofZDK3OoVHU_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_ofZDK3OoVHU_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_ofZDK3OoVHU_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"sports_trajectory","spatialAbility":"sports_trajectory, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A young man is riding his skateboard at a skate park, performing various tricks and stunts.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_ofZDK3OoVHU_0.json"},{"id":"panda_v6_oL1GM45FRck_0","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_oL1GM45FRck_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_oL1GM45FRck_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_oL1GM45FRck_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled motion","scene":"object physics","spatialAbility":"Direction and Trajectory, Relative and Coupled Motion","perspective":"Egocentric","caption":"There is a packaged burger on a table and the camera zooms in to show the product details.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_oL1GM45FRck_0.json"},{"id":"panda_v6_omiq76C5f2I_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_omiq76C5f2I_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_omiq76C5f2I_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_omiq76C5f2I_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"tool_contact_state_change","spatialAbility":"tool_contact_state_change, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"The person is building a cake in a springform pan and then pouring the mixture into the pan.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_omiq76C5f2I_2.json"},{"id":"panda_v6_OOoDGZ0HEH4_1","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_OOoDGZ0HEH4_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_OOoDGZ0HEH4_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_OOoDGZ0HEH4_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"human interaction","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"The person is rolling up a sweet roll in baking paper, making sure to cover the corners well, while the roll is refrigerating.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_OOoDGZ0HEH4_1.json"},{"id":"panda_v6_Os2vrOT8F1Q_1","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_Os2vrOT8F1Q_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_Os2vrOT8F1Q_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_Os2vrOT8F1Q_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"human interaction","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"A person is using a chainsaw to cut down a tree by making horizontal and vertical cuts, starting from the top of the tree and working downwards.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_Os2vrOT8F1Q_1.json"},{"id":"panda_v6_OsrP-_GcVFw_1","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_OsrP-_GcVFw_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_OsrP-_GcVFw_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_OsrP-_GcVFw_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"human interaction","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"A person touching a piece of paper with water drops on it.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_OsrP-_GcVFw_1.json"},{"id":"panda_v6_oUX4kaehE18_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_oUX4kaehE18_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_oUX4kaehE18_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_oUX4kaehE18_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"tool_contact_state_change","spatialAbility":"tool_contact_state_change, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is attempting to turn alcohol into pure water by lighting it on fire and then pouring it into a container.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_oUX4kaehE18_1.json"},{"id":"panda_v6_OX1htn2mL9I_2","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_OX1htn2mL9I_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_OX1htn2mL9I_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_OX1htn2mL9I_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled motion","scene":"human interaction","spatialAbility":"Direction and Trajectory, Relative and Coupled Motion","perspective":"Egocentric","caption":"A person is riding on a roller coaster at an amusement park.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_OX1htn2mL9I_2.json"},{"id":"panda_v6_p2GdWNykVvw_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_p2GdWNykVvw_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_p2GdWNykVvw_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_p2GdWNykVvw_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"reflection_surface","spatialAbility":"reflection_surface, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A man standing in a stream of water next to a fallen tree with sticks and branches sticking out of it and another person walking in the water.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_p2GdWNykVvw_0.json"},{"id":"panda_v6_P85Pf0IDMog_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_P85Pf0IDMog_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_P85Pf0IDMog_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_P85Pf0IDMog_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"tool_contact_state_change","spatialAbility":"tool_contact_state_change, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A woman walking on a tread machine in a gym.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_P85Pf0IDMog_1.json"},{"id":"panda_v6_pFRY4tEg2YM_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_pFRY4tEg2YM_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_pFRY4tEg2YM_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_pFRY4tEg2YM_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"human_object_interaction","spatialAbility":"human_object_interaction, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"There is an amusement park with roller coasters and people riding on them.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_pFRY4tEg2YM_1.json"},{"id":"panda_v6_PHz5mqnbELg_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_PHz5mqnbELg_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_PHz5mqnbELg_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_PHz5mqnbELg_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"sports_trajectory","spatialAbility":"sports_trajectory, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"The skateboarder is riding a skateboard on a skate park and the camera follows the skateboarder's point of view.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_PHz5mqnbELg_0.json"},{"id":"panda_v6_porpgz6q5m0_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_porpgz6q5m0_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_porpgz6q5m0_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_porpgz6q5m0_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"tool_contact_state_change","spatialAbility":"tool_contact_state_change, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is frying sausages in a pan and pouring beer into the pan.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_porpgz6q5m0_0.json"},{"id":"panda_v6_pP5khldpNlM_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_pP5khldpNlM_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_pP5khldpNlM_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_pP5khldpNlM_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"human_object_interaction","spatialAbility":"human_object_interaction, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"Pancakes are being cooked in a pan on a stove, and a person is using a spatula to flip the pancakes.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_pP5khldpNlM_1.json"},{"id":"panda_v6_pSRJehdNL50_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_pSRJehdNL50_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_pSRJehdNL50_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_pSRJehdNL50_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"occlusion_containment","spatialAbility":"occlusion_containment, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"There is a man walking through the woods with purple flowers in the background.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_pSRJehdNL50_2.json"},{"id":"panda_v6_pW6wZZs5_0Q_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_pW6wZZs5_0Q_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_pW6wZZs5_0Q_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_pW6wZZs5_0Q_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"support_rolling_contact","spatialAbility":"support_rolling_contact, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"Person is cutting a sushi roll on a cutting board with a knife.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_pW6wZZs5_0Q_2.json"},{"id":"panda_v6_pwixvyY34XQ_1","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_pwixvyY34XQ_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_pwixvyY34XQ_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_pwixvyY34XQ_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled motion","scene":"driving","spatialAbility":"Direction and Trajectory, Relative and Coupled Motion","perspective":"Egocentric","caption":"A white tesla model 3 is driving on a city street and passing by other cars.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_pwixvyY34XQ_1.json"},{"id":"panda_v6_pxKg-4VhHN0_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_pxKg-4VhHN0_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_pxKg-4VhHN0_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_pxKg-4VhHN0_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"reflection_surface","spatialAbility":"reflection_surface, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person holding an iphone in front of water droplets.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_pxKg-4VhHN0_0.json"},{"id":"panda_v6_PzgXV5ZsP48_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_PzgXV5ZsP48_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_PzgXV5ZsP48_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_PzgXV5ZsP48_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"sports_trajectory","spatialAbility":"sports_trajectory, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A skateboarder is riding a skateboard in a skate park and performing various tricks.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_PzgXV5ZsP48_1.json"},{"id":"panda_v6_Q-0X2P1sbAg_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_Q-0X2P1sbAg_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_Q-0X2P1sbAg_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_Q-0X2P1sbAg_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"support_rolling_contact","spatialAbility":"support_rolling_contact, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person pouring batter into two pans on a cutting board.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_Q-0X2P1sbAg_0.json"},{"id":"panda_v6_Q-PCMyzXxCc_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_Q-PCMyzXxCc_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_Q-PCMyzXxCc_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_Q-PCMyzXxCc_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"tool_contact_state_change","spatialAbility":"tool_contact_state_change, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A soldier is walking through a war-torn city and firing a machine gun.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_Q-PCMyzXxCc_2.json"},{"id":"panda_v6_Q1YL3WounzQ_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_Q1YL3WounzQ_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_Q1YL3WounzQ_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_Q1YL3WounzQ_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"tool_contact_state_change","spatialAbility":"tool_contact_state_change, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"The person is taking a tag and folding over a piece of white cardstock in half so that they can get two cuts from one pass through their die cut machine.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_Q1YL3WounzQ_0.json"},{"id":"panda_v6_q4RKUV4VQGE_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_q4RKUV4VQGE_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_q4RKUV4VQGE_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_q4RKUV4VQGE_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"human_object_interaction","spatialAbility":"human_object_interaction, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is preparing to make tamagoyaki by throwing oil into a cold pan, using chopsticks and a paper towel to evenly coat the oil, and turning it into a rolled omelette.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_q4RKUV4VQGE_1.json"},{"id":"panda_v6_qK7BWFVs794_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_qK7BWFVs794_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_qK7BWFVs794_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_qK7BWFVs794_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"human_object_interaction","spatialAbility":"human_object_interaction, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is walking into a cave and the camera follows them as they move deeper into the cave.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_qK7BWFVs794_0.json"},{"id":"panda_v6_QmefJUG8fZo_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_QmefJUG8fZo_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_QmefJUG8fZo_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_QmefJUG8fZo_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"occlusion_containment","spatialAbility":"occlusion_containment, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A truck is being driven through a parking lot and passing by a white storage container.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_QmefJUG8fZo_1.json"},{"id":"panda_v6_QVdiDRHtYPg_0","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_QVdiDRHtYPg_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_QVdiDRHtYPg_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_QVdiDRHtYPg_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled motion","scene":"human interaction","spatialAbility":"Direction and Trajectory, Relative and Coupled Motion","perspective":"Egocentric","caption":"The person is walking along a path in a forest and then enters a marshy area with tall grass and reeds.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_QVdiDRHtYPg_0.json"},{"id":"panda_v6_qvZBFKO4zOU_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_qvZBFKO4zOU_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_qvZBFKO4zOU_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_qvZBFKO4zOU_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"occlusion_containment","spatialAbility":"occlusion_containment, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A group of mountain bikers are riding through a forest and taking turns to take selfies with the camera.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_qvZBFKO4zOU_1.json"},{"id":"panda_v6_QYhiRMAs1uU_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_QYhiRMAs1uU_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_QYhiRMAs1uU_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_QYhiRMAs1uU_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"support_rolling_contact","spatialAbility":"support_rolling_contact, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is using a rolling pin to roll out dough on a cutting board.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_QYhiRMAs1uU_1.json"},{"id":"panda_v6_r0QnRw55t8I_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_r0QnRw55t8I_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_r0QnRw55t8I_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_r0QnRw55t8I_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"occlusion_containment","spatialAbility":"occlusion_containment, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is washing their hands under running water in a kitchen sink.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_r0QnRw55t8I_0.json"},{"id":"panda_v6_rNzOgheVkPM_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_rNzOgheVkPM_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_rNzOgheVkPM_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_rNzOgheVkPM_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"human_object_interaction","spatialAbility":"human_object_interaction, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"The model is wearing a pink bikini and walking on a runway in front of a crowd of people.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_rNzOgheVkPM_0.json"},{"id":"panda_v6_rsKM0GO5hVU_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_rsKM0GO5hVU_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_rsKM0GO5hVU_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_rsKM0GO5hVU_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"occlusion_containment","spatialAbility":"occlusion_containment, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"There is a person standing in a kitchen and the lights under the cabinets are motion activated, they will turn on for 20 seconds when the person is close to them and will turn off if the person moves away.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_rsKM0GO5hVU_2.json"},{"id":"panda_v6_ruRoXDboNAU_2","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_ruRoXDboNAU_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_ruRoXDboNAU_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_ruRoXDboNAU_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"human interaction","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"A person is frying eggplant slices in a pan and turning them over with a spatula.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_ruRoXDboNAU_2.json"},{"id":"panda_v6_RzVOf7kUdUk_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_RzVOf7kUdUk_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_RzVOf7kUdUk_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_RzVOf7kUdUk_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"reflection_surface","spatialAbility":"reflection_surface, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A person is riding on a wakeboard and performing jumps in the water.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_RzVOf7kUdUk_2.json"},{"id":"panda_v6_S0Zcse5Xxvk_0","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_S0Zcse5Xxvk_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_S0Zcse5Xxvk_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_S0Zcse5Xxvk_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"A young woman is walking her black and white dog on a sidewalk next to the water.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_S0Zcse5Xxvk_0.json"},{"id":"panda_v6_S14_tP_SDwI_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_S14_tP_SDwI_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_S14_tP_SDwI_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_S14_tP_SDwI_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"human_object_interaction","spatialAbility":"human_object_interaction, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A person is walking on a carpet and the camera follows the movement of the carpet as it moves.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_S14_tP_SDwI_1.json"},{"id":"panda_v6_Sbb3mEthusA_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_Sbb3mEthusA_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_Sbb3mEthusA_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_Sbb3mEthusA_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"reflection_surface","spatialAbility":"reflection_surface, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A man walking on a boardwalk near a body of water.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_Sbb3mEthusA_1.json"},{"id":"panda_v6_sc6j-p7rdSE_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_sc6j-p7rdSE_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_sc6j-p7rdSE_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_sc6j-p7rdSE_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"topology_navigation","spatialAbility":"topology_navigation, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"The camera is mounted on a moving car, driving on a highway and passing through a bridge.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_sc6j-p7rdSE_2.json"},{"id":"panda_v6_sgI4Vj7noC4_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_sgI4Vj7noC4_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_sgI4Vj7noC4_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_sgI4Vj7noC4_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"human_object_interaction","spatialAbility":"human_object_interaction, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is riding a horse in a riding arena, and the horse is performing a gait called \"side gait\" where the horse moves its legs sideways.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_sgI4Vj7noC4_2.json"},{"id":"panda_v6_sGZ2YQ9WCXg_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_sGZ2YQ9WCXg_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_sGZ2YQ9WCXg_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_sGZ2YQ9WCXg_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"occlusion_containment","spatialAbility":"occlusion_containment, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A person is walking along a path in the countryside, passing through fields of flowers and bushes.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_sGZ2YQ9WCXg_1.json"},{"id":"panda_v6_sikynSkFs3o_2","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_sikynSkFs3o_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_sikynSkFs3o_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_sikynSkFs3o_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"human interaction","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"A person pouring oil into a pan on a stove.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_sikynSkFs3o_2.json"},{"id":"panda_v6_sisKaEI3ztU_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_sisKaEI3ztU_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_sisKaEI3ztU_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_sisKaEI3ztU_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"human_object_interaction","spatialAbility":"human_object_interaction, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"It is night time and there is a carnival ride called the sizzler at a fair. people are riding on the ride and enjoying themselves.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_sisKaEI3ztU_0.json"},{"id":"panda_v6_SJiMcat00xA_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_SJiMcat00xA_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_SJiMcat00xA_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_SJiMcat00xA_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"support_rolling_contact","spatialAbility":"support_rolling_contact, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A man is walking on a wooden floor in a white shirt and black pants.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_SJiMcat00xA_1.json"},{"id":"panda_v6_sl5vUJsU-Dg_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_sl5vUJsU-Dg_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_sl5vUJsU-Dg_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_sl5vUJsU-Dg_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"sports_trajectory","spatialAbility":"sports_trajectory, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A man in red pants walking on a green golf course.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_sl5vUJsU-Dg_2.json"},{"id":"panda_v6_ssDpBlzK8f4_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_ssDpBlzK8f4_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_ssDpBlzK8f4_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_ssDpBlzK8f4_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"sports_trajectory","spatialAbility":"sports_trajectory, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"The player is riding on a roller coaster in a virtual world.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_ssDpBlzK8f4_2.json"},{"id":"panda_v6_svpjRzr7JH0_2","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_svpjRzr7JH0_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_svpjRzr7JH0_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_svpjRzr7JH0_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"human interaction","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"A person is washing blue flip flops in a sink with water and detergent.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_svpjRzr7JH0_2.json"},{"id":"panda_v6_SXNkJ3nMe_E_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_SXNkJ3nMe_E_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_SXNkJ3nMe_E_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_SXNkJ3nMe_E_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"sports_trajectory","spatialAbility":"sports_trajectory, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A skateboarder is riding a skateboard in a skate park and performing various tricks.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_SXNkJ3nMe_E_1.json"},{"id":"panda_v6_te127NCQPBg_2","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_te127NCQPBg_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_te127NCQPBg_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_te127NCQPBg_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"human interaction","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"A person making a purple flower on a cutting mat.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_te127NCQPBg_2.json"},{"id":"panda_v6_tFDqQ0Y1YYA_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_tFDqQ0Y1YYA_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_tFDqQ0Y1YYA_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_tFDqQ0Y1YYA_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"sports_trajectory","spatialAbility":"sports_trajectory, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"There is a soccer game being played on a stadium, the camera pans out to show the whole stadium and the players running on the field.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_tFDqQ0Y1YYA_0.json"},{"id":"panda_v6_tgarfnEpsSE_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_tgarfnEpsSE_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_tgarfnEpsSE_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_tgarfnEpsSE_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"support_rolling_contact","spatialAbility":"support_rolling_contact, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A group of panda bears are walking on the ground in an enclosure.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_tgarfnEpsSE_2.json"},{"id":"panda_v6_TiFxhP7A-1Y_0","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_TiFxhP7A-1Y_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_TiFxhP7A-1Y_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_TiFxhP7A-1Y_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled motion","scene":"driving","spatialAbility":"Direction and Trajectory, Relative and Coupled Motion","perspective":"Egocentric","caption":"A person is driving a tractor on a dirt road, and the view from the driver's seat is of a field with grass.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_TiFxhP7A-1Y_0.json"},{"id":"panda_v6_To2GYvhbdQQ_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_To2GYvhbdQQ_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_To2GYvhbdQQ_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_To2GYvhbdQQ_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"tool_contact_state_change","spatialAbility":"tool_contact_state_change, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"The person is walking on a wooden plank with blue paint peeling off.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_To2GYvhbdQQ_0.json"},{"id":"panda_v6_tRDycKXSrLI_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_tRDycKXSrLI_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_tRDycKXSrLI_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_tRDycKXSrLI_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"reflection_surface","spatialAbility":"reflection_surface, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"There is a white goose walking on the sidewalk near a lake.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_tRDycKXSrLI_1.json"},{"id":"panda_v6_TsvHnD4p0mc_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_TsvHnD4p0mc_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_TsvHnD4p0mc_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_TsvHnD4p0mc_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"reflection_surface","spatialAbility":"reflection_surface, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is walking in a dark cave and the camera follows him as he moves towards a light source.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_TsvHnD4p0mc_2.json"},{"id":"panda_v6_ttMYlbMjprs_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_ttMYlbMjprs_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_ttMYlbMjprs_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_ttMYlbMjprs_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"sports_trajectory","spatialAbility":"sports_trajectory, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A skateboarder is riding his skateboard in an outdoor skate park at night and performing various tricks.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_ttMYlbMjprs_0.json"},{"id":"panda_v6_TuWBUKIqB5U_0","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_TuWBUKIqB5U_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_TuWBUKIqB5U_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_TuWBUKIqB5U_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"human interaction","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"A person is using a tablet computer to access the internet and enter their password.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_TuWBUKIqB5U_0.json"},{"id":"panda_v6_tzkb9ShEZU0_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_tzkb9ShEZU0_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_tzkb9ShEZU0_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_tzkb9ShEZU0_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"sports_trajectory","spatialAbility":"sports_trajectory, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"The skateboarder is riding his skateboard inside a skate park and performing various tricks.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_tzkb9ShEZU0_1.json"},{"id":"panda_v6_u8RoPjAjawA_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_u8RoPjAjawA_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_u8RoPjAjawA_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_u8RoPjAjawA_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"support_rolling_contact","spatialAbility":"support_rolling_contact, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A man is sitting in the driver's seat of a rolls- royce cullinan at an auto show.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_u8RoPjAjawA_1.json"},{"id":"panda_v6_uaSdiFAsGKA_0","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_uaSdiFAsGKA_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_uaSdiFAsGKA_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_uaSdiFAsGKA_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"human interaction","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"A person is using a smartphone in the dark with water droplets on the screen.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_uaSdiFAsGKA_0.json"},{"id":"panda_v6_UbFX7XoN1xA_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_UbFX7XoN1xA_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_UbFX7XoN1xA_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_UbFX7XoN1xA_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"human_object_interaction","spatialAbility":"human_object_interaction, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"The person is cooking sausages on a grill pan, turning up the heat to high to medium/high, and using a little bit of olive oil to warm up the pan before cooking the sausages.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_UbFX7XoN1xA_2.json"},{"id":"panda_v6_ubphKfMUl_g_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_ubphKfMUl_g_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_ubphKfMUl_g_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_ubphKfMUl_g_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"support_rolling_contact","spatialAbility":"support_rolling_contact, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person pouring flour into a bundt pan on a cutting board.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_ubphKfMUl_g_0.json"},{"id":"panda_v6_uCpjDi6BGdw_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_uCpjDi6BGdw_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_uCpjDi6BGdw_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_uCpjDi6BGdw_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"topology_navigation","spatialAbility":"topology_navigation, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"The driver and co-driver of a rally car are preparing for a race, with the driver wearing a helmet and communicating with the co-driver through a microphone.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_uCpjDi6BGdw_2.json"},{"id":"panda_v6_UKG0lmB3HwA_2","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_UKG0lmB3HwA_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_UKG0lmB3HwA_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_UKG0lmB3HwA_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"A person is climbing on an indoor rock climbing wall.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_UKG0lmB3HwA_2.json"},{"id":"panda_v6_ukRlxOIlAfo_0","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_ukRlxOIlAfo_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_ukRlxOIlAfo_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_ukRlxOIlAfo_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"driving","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"A group of young people are riding in a boat on a water ride. they are having fun and enjoying the ride.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_ukRlxOIlAfo_0.json"},{"id":"panda_v6_UN8UNwrDqSM_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_UN8UNwrDqSM_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_UN8UNwrDqSM_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_UN8UNwrDqSM_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"reflection_surface","spatialAbility":"reflection_surface, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"There is a pond with ducks and swans in it, surrounded by trees. people are also seen walking around the pond, some of them feeding the birds.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_UN8UNwrDqSM_2.json"},{"id":"panda_v6_uNycBf7AN64_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_uNycBf7AN64_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_uNycBf7AN64_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_uNycBf7AN64_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"sports_trajectory","spatialAbility":"sports_trajectory, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"There is a football game in progress, with the quarterback throwing a pass to a receiver who catches it and runs it for a touchdown.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_uNycBf7AN64_0.json"},{"id":"panda_v6_uROqYBtIz_M_2","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_uROqYBtIz_M_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_uROqYBtIz_M_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_uROqYBtIz_M_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled motion","scene":"living space","spatialAbility":"Direction and Trajectory, Relative and Coupled Motion","perspective":"Egocentric","caption":"A long-haired cat is walking on a wooden floor in a living room.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_uROqYBtIz_M_2.json"},{"id":"panda_v6_UTWrCtGaxeY_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_UTWrCtGaxeY_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_UTWrCtGaxeY_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_UTWrCtGaxeY_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"reflection_surface","spatialAbility":"reflection_surface, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is washing a small white dog in a sink with running water.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_UTWrCtGaxeY_0.json"},{"id":"panda_v6_uXF4_fJLVNA_2","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_uXF4_fJLVNA_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_uXF4_fJLVNA_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_uXF4_fJLVNA_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"human interaction","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"The person is demonstrating how to move the yo-yo onto the string and roll it to the outside to create extra string, then rolling it back onto the string from the bottom up.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_uXF4_fJLVNA_2.json"},{"id":"panda_v6_v2rcuVtCcSg_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_v2rcuVtCcSg_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_v2rcuVtCcSg_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_v2rcuVtCcSg_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"topology_navigation","spatialAbility":"topology_navigation, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A car is driving on a race track and the driver is accelerating, braking, and turning.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_v2rcuVtCcSg_1.json"},{"id":"panda_v6_V5kd3LW5Pf8_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_V5kd3LW5Pf8_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_V5kd3LW5Pf8_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_V5kd3LW5Pf8_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"sports_trajectory","spatialAbility":"sports_trajectory, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A young man is riding his skateboard at a skate park. he performs various tricks and stunts on the skateboard, showing off his skills to the camera.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_V5kd3LW5Pf8_1.json"},{"id":"panda_v6_v5VvVRO4HOQ_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_v5VvVRO4HOQ_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_v5VvVRO4HOQ_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_v5VvVRO4HOQ_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"support_rolling_contact","spatialAbility":"support_rolling_contact, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A man is walking on a path in front of an old church with a cross on the ground.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_v5VvVRO4HOQ_2.json"},{"id":"panda_v6_vDBQ0CJ_Lu4_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_vDBQ0CJ_Lu4_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_vDBQ0CJ_Lu4_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_vDBQ0CJ_Lu4_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"support_rolling_contact","spatialAbility":"support_rolling_contact, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is using a pastry cutter to cut gnocchi into small bite-sized pieces, then rolling each piece along the back of a floured fork to make indentations.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_vDBQ0CJ_Lu4_2.json"},{"id":"panda_v6_vSwMCitsnhY_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_vSwMCitsnhY_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_vSwMCitsnhY_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_vSwMCitsnhY_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"topology_navigation","spatialAbility":"topology_navigation, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is wearing roller skates and rolling on the street.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_vSwMCitsnhY_2.json"},{"id":"panda_v6_VT1TXTQM0b0_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_VT1TXTQM0b0_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_VT1TXTQM0b0_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_VT1TXTQM0b0_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"occlusion_containment","spatialAbility":"occlusion_containment, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is using scissors to cut the corners and curves of a christmas tree skirt, turning it inside out through a hole, and then closing the hole.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_VT1TXTQM0b0_1.json"},{"id":"panda_v6_VV5KFgNgKNc_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_VV5KFgNgKNc_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_VV5KFgNgKNc_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_VV5KFgNgKNc_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"tool_contact_state_change","spatialAbility":"tool_contact_state_change, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is pouring a liquid into a pan of pancakes.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_VV5KFgNgKNc_1.json"},{"id":"panda_v6_W18qIStab3s_0","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_W18qIStab3s_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_W18qIStab3s_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_W18qIStab3s_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"human interaction","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"A person is holding white flowers on a table. the flowers are made of plastic, and there is also a vase of flowers on the table.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_W18qIStab3s_0.json"},{"id":"panda_v6_WaU-Wkfz_9w_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_WaU-Wkfz_9w_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_WaU-Wkfz_9w_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_WaU-Wkfz_9w_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"reflection_surface","spatialAbility":"reflection_surface, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A person is walking on a carpet in front of a glass door.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_WaU-Wkfz_9w_0.json"},{"id":"panda_v6_wg6YV5HYuS0_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_wg6YV5HYuS0_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_wg6YV5HYuS0_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_wg6YV5HYuS0_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"tool_contact_state_change","spatialAbility":"tool_contact_state_change, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is cooking food in a pan on a stove and pouring milk into the pan.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_wg6YV5HYuS0_2.json"},{"id":"panda_v6_wImnFx8x-j8_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_wImnFx8x-j8_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_wImnFx8x-j8_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_wImnFx8x-j8_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"reflection_surface","spatialAbility":"reflection_surface, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A raccoon is walking along the edge of a pond in a forest, looking for food.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_wImnFx8x-j8_2.json"},{"id":"panda_v6_Wn7f1mAlFKw_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_Wn7f1mAlFKw_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_Wn7f1mAlFKw_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_Wn7f1mAlFKw_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"reflection_surface","spatialAbility":"reflection_surface, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is washing dirty dishes in a kitchen sink with running water.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_Wn7f1mAlFKw_0.json"},{"id":"panda_v6_wQNfWJRFNmA_0","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_wQNfWJRFNmA_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_wQNfWJRFNmA_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_wQNfWJRFNmA_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"human interaction","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"A person is washing a small dog in a sink with water.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_wQNfWJRFNmA_0.json"},{"id":"panda_v6_wXtHDSSSsb8_1","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_wXtHDSSSsb8_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_wXtHDSSSsb8_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_wXtHDSSSsb8_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"A young man with a green helmet rides a skateboard on a ramp at a skate park.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_wXtHDSSSsb8_1.json"},{"id":"panda_v6_WYaZBwXI1EQ_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_WYaZBwXI1EQ_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_WYaZBwXI1EQ_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_WYaZBwXI1EQ_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"support_rolling_contact","spatialAbility":"support_rolling_contact, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is cutting apples and vegetables in a frying pan on a wooden cutting board.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_WYaZBwXI1EQ_1.json"},{"id":"panda_v6_X9kPFGxoxjQ_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_X9kPFGxoxjQ_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_X9kPFGxoxjQ_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_X9kPFGxoxjQ_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"occlusion_containment","spatialAbility":"occlusion_containment, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A young man is walking through a garden filled with various types of flowers, including sunflowers and orange flowers.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_X9kPFGxoxjQ_1.json"},{"id":"panda_v6_xaAyTwYqLXc_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_xaAyTwYqLXc_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_xaAyTwYqLXc_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_xaAyTwYqLXc_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"occlusion_containment","spatialAbility":"occlusion_containment, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A person is walking on a grassy lawn and the camera pans to reveal that the grass has been mowed unevenly.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_xaAyTwYqLXc_0.json"},{"id":"panda_v6_XaE9h66i6aM_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_XaE9h66i6aM_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_XaE9h66i6aM_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_XaE9h66i6aM_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"occlusion_containment","spatialAbility":"occlusion_containment, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is adjusting the tension on the driver's side and passenger's side of a truck bed cover using an xt dial tension adjuster.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_XaE9h66i6aM_0.json"},{"id":"panda_v6_XI47xnGFTBE_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_XI47xnGFTBE_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_XI47xnGFTBE_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_XI47xnGFTBE_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"sports_trajectory","spatialAbility":"sports_trajectory, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A young man is riding a skateboard on different ramps at a skate park.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_XI47xnGFTBE_1.json"},{"id":"panda_v6_xIN5btgHP5k_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_xIN5btgHP5k_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_xIN5btgHP5k_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_xIN5btgHP5k_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"reflection_surface","spatialAbility":"reflection_surface, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person in a red shirt and pants is in a sink with dirty water.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_xIN5btgHP5k_2.json"},{"id":"panda_v6_XP7D5lN4-As_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_XP7D5lN4-As_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_XP7D5lN4-As_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_XP7D5lN4-As_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"topology_navigation","spatialAbility":"topology_navigation, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A person is driving through a residential neighborhood and passing by trees, bushes, and flowers.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_XP7D5lN4-As_0.json"},{"id":"panda_v6_XUxAGsL8b0o_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_XUxAGsL8b0o_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_XUxAGsL8b0o_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_XUxAGsL8b0o_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"occlusion_containment","spatialAbility":"occlusion_containment, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"Person is falling from the sky with a cape flowing behind him.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_XUxAGsL8b0o_0.json"},{"id":"panda_v6_Xw1vQddyPfY_0","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_Xw1vQddyPfY_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_Xw1vQddyPfY_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_Xw1vQddyPfY_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"human interaction","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"Person is pouring oil into a pan on a stove.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_Xw1vQddyPfY_0.json"},{"id":"panda_v6_Y-smWJllNi8_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_Y-smWJllNi8_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_Y-smWJllNi8_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_Y-smWJllNi8_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"occlusion_containment","spatialAbility":"occlusion_containment, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"There is a man in a suit walking down a hallway with other people following behind him.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_Y-smWJllNi8_2.json"},{"id":"panda_v6_y07inrkJiMo_0","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_y07inrkJiMo_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_y07inrkJiMo_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_y07inrkJiMo_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"A young man is riding a skateboard at a skate park while wearing sunglasses and a helmet.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_y07inrkJiMo_0.json"},{"id":"panda_v6_YahLK3jrQuA_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_YahLK3jrQuA_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_YahLK3jrQuA_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_YahLK3jrQuA_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"sports_trajectory","spatialAbility":"sports_trajectory, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"The player is riding a horse in a virtual world, and the horse is running and jumping over various obstacles in the game.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_YahLK3jrQuA_1.json"},{"id":"panda_v6_YK6H2mPQM5w_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_YK6H2mPQM5w_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_YK6H2mPQM5w_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_YK6H2mPQM5w_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"support_rolling_contact","spatialAbility":"support_rolling_contact, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A cute white puppy is walking on the ground and looking around.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_YK6H2mPQM5w_1.json"},{"id":"panda_v6_yqKvg6H8hLg_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_yqKvg6H8hLg_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_yqKvg6H8hLg_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_yqKvg6H8hLg_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"reflection_surface","spatialAbility":"reflection_surface, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is using duct tape to outline the edges of heavy duty foil and then dropping it down to reflect light back.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_yqKvg6H8hLg_1.json"},{"id":"panda_v6_YqPpWnWOzA8_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_YqPpWnWOzA8_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_YqPpWnWOzA8_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_YqPpWnWOzA8_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"sports_trajectory","spatialAbility":"sports_trajectory, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"Two baseball players are walking on the field and one of them is congratulated by his teammates after scoring a run.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_YqPpWnWOzA8_0.json"},{"id":"panda_v6_YrNQEX72C8A_0","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_YrNQEX72C8A_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_YrNQEX72C8A_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_YrNQEX72C8A_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"human interaction","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"A person is using a rolling pin to roll out a piece of dough on a cutting board.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_YrNQEX72C8A_0.json"},{"id":"panda_v6_ysEnSF-rZjk_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_ysEnSF-rZjk_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_ysEnSF-rZjk_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_ysEnSF-rZjk_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"reflection_surface","spatialAbility":"reflection_surface, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is replacing a toilet valve by turning it to the right and then turning it off to empty the tank of water.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_ysEnSF-rZjk_1.json"},{"id":"panda_v6_YSw3g-KcUO8_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_YSw3g-KcUO8_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_YSw3g-KcUO8_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_YSw3g-KcUO8_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"support_rolling_contact","spatialAbility":"support_rolling_contact, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A person is using a rolling pin to roll out dough on a wooden cutting board in the kitchen.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_YSw3g-KcUO8_1.json"},{"id":"panda_v6_YVvv3YwvHeU_2","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_YVvv3YwvHeU_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_YVvv3YwvHeU_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_YVvv3YwvHeU_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"human interaction","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"A person is walking in a cemetery at night and the camera is following them.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_YVvv3YwvHeU_2.json"},{"id":"panda_v6_Yvzd6bx-gSI_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_Yvzd6bx-gSI_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_Yvzd6bx-gSI_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_Yvzd6bx-gSI_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"human_object_interaction","spatialAbility":"human_object_interaction, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A group of people riding on a ride at an amusement park.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_Yvzd6bx-gSI_0.json"},{"id":"panda_v6_YwGbgw3PQUA_2","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_YwGbgw3PQUA_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_YwGbgw3PQUA_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_YwGbgw3PQUA_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"human interaction","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"A person is holding a packet of flower fertilizer in front of a flower garden.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_YwGbgw3PQUA_2.json"},{"id":"panda_v6_Yy1gncKTI2U_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_Yy1gncKTI2U_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_Yy1gncKTI2U_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_Yy1gncKTI2U_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"support_rolling_contact","spatialAbility":"support_rolling_contact, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A dog is walking through a forest with fallen leaves on the ground and trees.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_Yy1gncKTI2U_1.json"},{"id":"panda_v6_yZzBwqufJjQ_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_yZzBwqufJjQ_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/third_person/panda_v6_yZzBwqufJjQ_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_yZzBwqufJjQ_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"scene_motion","scene":"topology_navigation","spatialAbility":"topology_navigation, direction, relative_distance, contact_or_occlusion","perspective":"third-person observer camera","caption":"A young man is riding his skateboard down a ramp at a skate park during sunset.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_yZzBwqufJjQ_2.json"},{"id":"panda_v6_Z4feb7JxRNY_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_Z4feb7JxRNY_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_Z4feb7JxRNY_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_Z4feb7JxRNY_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"tool_contact_state_change","spatialAbility":"tool_contact_state_change, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"There is a red machine with a glass window on it, and the camera moves towards the machine from the side.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_Z4feb7JxRNY_1.json"},{"id":"panda_v6_z55CLavGHT4_1","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_z55CLavGHT4_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_z55CLavGHT4_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_z55CLavGHT4_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"sports_trajectory","spatialAbility":"sports_trajectory, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"There is a person riding on a skateboard in a skate park with graffiti on the wall.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_z55CLavGHT4_1.json"},{"id":"panda_v6_Z7j--o-0foY_0","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_Z7j--o-0foY_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_Z7j--o-0foY_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_Z7j--o-0foY_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"topology_navigation","spatialAbility":"topology_navigation, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"A person is riding a motorcycle and driving through the city, passing by cars and other vehicles.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_Z7j--o-0foY_0.json"},{"id":"panda_v6_zbbqhZ7iQ24_0","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_zbbqhZ7iQ24_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_zbbqhZ7iQ24_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_zbbqhZ7iQ24_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"There is a man riding a bicycle on a skateboard ramp in a skate park.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_zbbqhZ7iQ24_0.json"},{"id":"panda_v6_zBUbEOhrAuU_1","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_zBUbEOhrAuU_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_zBUbEOhrAuU_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_zBUbEOhrAuU_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"A young man is riding his skateboard at night in a skate park.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_zBUbEOhrAuU_1.json"},{"id":"panda_v6_zca_zC3Eg2E_2","videoPath":"curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_zca_zC3Eg2E_2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/videos/first_person/panda_v6_zca_zC3Eg2E_2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v6/panda-70m-expansion/initial_frames/panda_v6_zca_zC3Eg2E_2.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled_motion","scene":"sports_trajectory","spatialAbility":"sports_trajectory, direction, relative_distance, contact_or_occlusion","perspective":"first-person/egocentric camera","caption":"The player is in a minecraft game, and they are walking through a field with trees and flowers.","annotationPath":"curated/spatial-world-model/v6/panda-70m-expansion/annotations/panda_v6_zca_zC3Eg2E_2.json"},{"id":"panda_v6_zfBF9VaFTJk_1","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_zfBF9VaFTJk_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_zfBF9VaFTJk_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_zfBF9VaFTJk_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled motion","scene":"human interaction","spatialAbility":"Direction and Trajectory, Relative and Coupled Motion","perspective":"Egocentric","caption":"A group of people are walking on a rocky beach and entering a hole in the rock.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_zfBF9VaFTJk_1.json"},{"id":"panda_v6_ZsRzeOsZDYc_1","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_ZsRzeOsZDYc_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_ZsRzeOsZDYc_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_ZsRzeOsZDYc_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled motion","scene":"driving","spatialAbility":"Direction and Trajectory, Relative and Coupled Motion","perspective":"Egocentric","caption":"The video is a walkthrough of the legend of zelda: ocarina of time, with a character named link walking through a temple.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_ZsRzeOsZDYc_1.json"},{"id":"panda_v6_ZwDln7riRug_0","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_ZwDln7riRug_0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/first_person/panda_v6_ZwDln7riRug_0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_ZwDln7riRug_0.jpg","sourceDataset":"Panda-70M","suggestedTrack":"coupled motion","scene":"object physics","spatialAbility":"Direction and Trajectory, Relative and Coupled Motion","perspective":"Egocentric","caption":"The character is walking through a grassy field and picking up a pink flower.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_ZwDln7riRug_0.json"},{"id":"panda_v6_zXdsyijmdb4_1","videoPath":"curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_zXdsyijmdb4_1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/videos/third_person/panda_v6_zXdsyijmdb4_1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v11/panda-70m-expansion/initial_frames/panda_v6_zXdsyijmdb4_1.jpg","sourceDataset":"Panda-70M","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"There is a young man riding a skateboard in a skate park. he is wearing a red shirt and a helmet.","annotationPath":"curated/spatial-world-model/v11/panda-70m-expansion/annotations/panda_v6_zXdsyijmdb4_1.json"},{"id":"physics_iq_original_t1_center_0005_ball_behind_rotating_paper","videoPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0005_ball_behind_rotating_paper.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0005_ball_behind_rotating_paper.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/initial_frames/scene_motion/physics_iq_original_t1_center_0005_ball_behind_rotating_paper.jpg","sourceDataset":"Physics-IQ","suggestedTrack":"scene_motion","scene":"rigid_object","spatialAbility":"occlusion, visibility, depth_order, direction","perspective":"exocentric","caption":"Rotate the paper board so that it occludes the ball.","annotationPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/annotations/scene_motion/physics_iq_original_t1_center_0005_ball_behind_rotating_paper.json"},{"id":"physics_iq_original_t1_center_0008_ball_hits_duck","videoPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0008_ball_hits_duck.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0008_ball_hits_duck.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/initial_frames/scene_motion/physics_iq_original_t1_center_0008_ball_hits_duck.jpg","sourceDataset":"Physics-IQ","suggestedTrack":"scene_motion","scene":"rigid_object","spatialAbility":"direction, distance, contact, relative_motion","perspective":"exocentric","caption":"Roll the ball into the duck.","annotationPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/annotations/scene_motion/physics_iq_original_t1_center_0008_ball_hits_duck.json"},{"id":"physics_iq_original_t1_center_0014_ball_in_basket","videoPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0014_ball_in_basket.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0014_ball_in_basket.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/initial_frames/scene_motion/physics_iq_original_t1_center_0014_ball_in_basket.jpg","sourceDataset":"Physics-IQ","suggestedTrack":"scene_motion","scene":"rigid_object","spatialAbility":"direction, containment, contact, support","perspective":"exocentric","caption":"Drop the ball into the basket.","annotationPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/annotations/scene_motion/physics_iq_original_t1_center_0014_ball_in_basket.json"},{"id":"physics_iq_original_t1_center_0017_ball_in_sand","videoPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0017_ball_in_sand.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0017_ball_in_sand.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/initial_frames/scene_motion/physics_iq_original_t1_center_0017_ball_in_sand.jpg","sourceDataset":"Physics-IQ","suggestedTrack":"scene_motion","scene":"rigid_object","spatialAbility":"direction, distance, contact, support, containment","perspective":"exocentric","caption":"Drop the blue ball into the sand.","annotationPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/annotations/scene_motion/physics_iq_original_t1_center_0017_ball_in_sand.json"},{"id":"physics_iq_original_t1_center_0020_ball_ramp","videoPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0020_ball_ramp.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0020_ball_ramp.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/initial_frames/scene_motion/physics_iq_original_t1_center_0020_ball_ramp.jpg","sourceDataset":"Physics-IQ","suggestedTrack":"scene_motion","scene":"rigid_object","spatialAbility":"direction, distance, support","perspective":"exocentric","caption":"Let the green ball roll down the ramp.","annotationPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/annotations/scene_motion/physics_iq_original_t1_center_0020_ball_ramp.json"},{"id":"physics_iq_original_t1_center_0023_ball_rolls_off","videoPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0023_ball_rolls_off.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0023_ball_rolls_off.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/initial_frames/scene_motion/physics_iq_original_t1_center_0023_ball_rolls_off.jpg","sourceDataset":"Physics-IQ","suggestedTrack":"scene_motion","scene":"rigid_object","spatialAbility":"direction, distance, support, entry_exit","perspective":"exocentric","caption":"Roll the ball until it falls off the edge.","annotationPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/annotations/scene_motion/physics_iq_original_t1_center_0023_ball_rolls_off.json"},{"id":"physics_iq_original_t1_center_0026_ball_rolls_on_glass","videoPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0026_ball_rolls_on_glass.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0026_ball_rolls_on_glass.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/initial_frames/scene_motion/physics_iq_original_t1_center_0026_ball_rolls_on_glass.jpg","sourceDataset":"Physics-IQ","suggestedTrack":"scene_motion","scene":"rigid_object","spatialAbility":"direction, distance, support","perspective":"exocentric","caption":"Roll the blue ball across the glass surface.","annotationPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/annotations/scene_motion/physics_iq_original_t1_center_0026_ball_rolls_on_glass.json"},{"id":"physics_iq_original_t1_center_0032_balls_collide","videoPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0032_balls_collide.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0032_balls_collide.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/initial_frames/scene_motion/physics_iq_original_t1_center_0032_balls_collide.jpg","sourceDataset":"Physics-IQ","suggestedTrack":"scene_motion","scene":"rigid_object","spatialAbility":"direction, distance, contact, relative_motion","perspective":"exocentric","caption":"Send the two balls toward each other so they collide.","annotationPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/annotations/scene_motion/physics_iq_original_t1_center_0032_balls_collide.json"},{"id":"physics_iq_original_t1_center_0035_block_domino","videoPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0035_block_domino.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0035_block_domino.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/initial_frames/scene_motion/physics_iq_original_t1_center_0035_block_domino.jpg","sourceDataset":"Physics-IQ","suggestedTrack":"scene_motion","scene":"rigid_object","spatialAbility":"direction, contact, support, relative_motion","perspective":"exocentric","caption":"Topple the first block into the domino row.","annotationPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/annotations/scene_motion/physics_iq_original_t1_center_0035_block_domino.json"},{"id":"physics_iq_original_t1_center_0050_dominos_with_space","videoPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0050_dominos_with_space.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0050_dominos_with_space.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/initial_frames/scene_motion/physics_iq_original_t1_center_0050_dominos_with_space.jpg","sourceDataset":"Physics-IQ","suggestedTrack":"scene_motion","scene":"rigid_object","spatialAbility":"direction, contact, support, relative_motion","perspective":"exocentric","caption":"Topple the first domino so the chain falls across the table.","annotationPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/annotations/scene_motion/physics_iq_original_t1_center_0050_dominos_with_space.json"},{"id":"physics_iq_original_t1_center_0065_fill_glass_red_drink","videoPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0065_fill_glass_red_drink.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0065_fill_glass_red_drink.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/initial_frames/scene_motion/physics_iq_original_t1_center_0065_fill_glass_red_drink.jpg","sourceDataset":"Physics-IQ","suggestedTrack":"scene_motion","scene":"fluid_dynamics","spatialAbility":"direction, containment, contact, distance","perspective":"exocentric","caption":"Fill the glass with red liquid.","annotationPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/annotations/scene_motion/physics_iq_original_t1_center_0065_fill_glass_red_drink.json"},{"id":"physics_iq_original_t1_center_0071_juice_in_water","videoPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0071_juice_in_water.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0071_juice_in_water.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/initial_frames/scene_motion/physics_iq_original_t1_center_0071_juice_in_water.jpg","sourceDataset":"Physics-IQ","suggestedTrack":"scene_motion","scene":"fluid_dynamics","spatialAbility":"direction, containment, contact, visibility","perspective":"exocentric","caption":"Pour the colored juice into the water.","annotationPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/annotations/scene_motion/physics_iq_original_t1_center_0071_juice_in_water.json"},{"id":"physics_iq_original_t1_center_0086_liquid_on_duck","videoPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0086_liquid_on_duck.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0086_liquid_on_duck.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/initial_frames/scene_motion/physics_iq_original_t1_center_0086_liquid_on_duck.jpg","sourceDataset":"Physics-IQ","suggestedTrack":"scene_motion","scene":"fluid_dynamics, rigid_object","spatialAbility":"direction, containment, contact, visibility","perspective":"exocentric","caption":"Pour red liquid into the tray around the duck.","annotationPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/annotations/scene_motion/physics_iq_original_t1_center_0086_liquid_on_duck.json"},{"id":"physics_iq_original_t1_center_0089_liquid_overfill","videoPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0089_liquid_overfill.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0089_liquid_overfill.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/initial_frames/scene_motion/physics_iq_original_t1_center_0089_liquid_overfill.jpg","sourceDataset":"Physics-IQ","suggestedTrack":"scene_motion","scene":"fluid_dynamics","spatialAbility":"direction, containment, entry_exit, contact","perspective":"exocentric","caption":"Continue filling the container until the liquid overflows.","annotationPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/annotations/scene_motion/physics_iq_original_t1_center_0089_liquid_overfill.json"},{"id":"physics_iq_original_t1_center_0104_marble_run_x","videoPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0104_marble_run_x.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0104_marble_run_x.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/initial_frames/scene_motion/physics_iq_original_t1_center_0104_marble_run_x.jpg","sourceDataset":"Physics-IQ","suggestedTrack":"scene_motion","scene":"rigid_object","spatialAbility":"direction, distance, support, contact","perspective":"exocentric","caption":"Release the marble into the zigzag track.","annotationPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/annotations/scene_motion/physics_iq_original_t1_center_0104_marble_run_x.json"},{"id":"physics_iq_original_t1_center_0107_marble_run_y","videoPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0107_marble_run_y.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0107_marble_run_y.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/initial_frames/scene_motion/physics_iq_original_t1_center_0107_marble_run_y.jpg","sourceDataset":"Physics-IQ","suggestedTrack":"scene_motion","scene":"rigid_object","spatialAbility":"direction, distance, support, contact","perspective":"exocentric","caption":"Release the marble into the vertical track.","annotationPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/annotations/scene_motion/physics_iq_original_t1_center_0107_marble_run_y.json"},{"id":"physics_iq_original_t1_center_0146_roll_behind_box","videoPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0146_roll_behind_box.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0146_roll_behind_box.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/initial_frames/scene_motion/physics_iq_original_t1_center_0146_roll_behind_box.jpg","sourceDataset":"Physics-IQ","suggestedTrack":"scene_motion","scene":"rigid_object","spatialAbility":"direction, depth_order, occlusion, visibility","perspective":"exocentric","caption":"Roll the ball behind the box.","annotationPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/annotations/scene_motion/physics_iq_original_t1_center_0146_roll_behind_box.json"},{"id":"physics_iq_original_t1_center_0149_roll_front_box","videoPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0149_roll_front_box.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0149_roll_front_box.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/initial_frames/scene_motion/physics_iq_original_t1_center_0149_roll_front_box.jpg","sourceDataset":"Physics-IQ","suggestedTrack":"scene_motion","scene":"rigid_object","spatialAbility":"direction, depth_order, distance","perspective":"exocentric","caption":"Roll the ball in front of the box.","annotationPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/annotations/scene_motion/physics_iq_original_t1_center_0149_roll_front_box.json"},{"id":"physics_iq_original_t1_center_0152_roll_in_box","videoPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0152_roll_in_box.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0152_roll_in_box.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/initial_frames/scene_motion/physics_iq_original_t1_center_0152_roll_in_box.jpg","sourceDataset":"Physics-IQ","suggestedTrack":"scene_motion","scene":"rigid_object","spatialAbility":"direction, containment, contact, support","perspective":"exocentric","caption":"Roll the ball into the box.","annotationPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/annotations/scene_motion/physics_iq_original_t1_center_0152_roll_in_box.json"},{"id":"physics_iq_original_t1_center_0155_rolling_reflection","videoPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0155_rolling_reflection.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0155_rolling_reflection.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/initial_frames/scene_motion/physics_iq_original_t1_center_0155_rolling_reflection.jpg","sourceDataset":"Physics-IQ","suggestedTrack":"scene_motion","scene":"rigid_object","spatialAbility":"direction, distance, visibility","perspective":"exocentric","caption":"Roll the green ball in front of the reflective panel.","annotationPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/annotations/scene_motion/physics_iq_original_t1_center_0155_rolling_reflection.json"},{"id":"physics_iq_original_t1_center_0164_siphon","videoPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0164_siphon.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0164_siphon.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/initial_frames/scene_motion/physics_iq_original_t1_center_0164_siphon.jpg","sourceDataset":"Physics-IQ","suggestedTrack":"scene_motion","scene":"fluid_dynamics","spatialAbility":"direction, containment, contact, distance","perspective":"exocentric","caption":"Start the siphon so liquid transfers between the vessels.","annotationPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/annotations/scene_motion/physics_iq_original_t1_center_0164_siphon.json"},{"id":"physics_iq_original_t1_center_0170_solid_ball_peakaboo","videoPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0170_solid_ball_peakaboo.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0170_solid_ball_peakaboo.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/initial_frames/scene_motion/physics_iq_original_t1_center_0170_solid_ball_peakaboo.jpg","sourceDataset":"Physics-IQ","suggestedTrack":"scene_motion","scene":"rigid_object","spatialAbility":"direction, occlusion, visibility, depth_order","perspective":"exocentric","caption":"Move the ball behind the hanging object.","annotationPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/annotations/scene_motion/physics_iq_original_t1_center_0170_solid_ball_peakaboo.json"},{"id":"physics_iq_original_t1_center_0179_two_balls_pass","videoPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0179_two_balls_pass.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0179_two_balls_pass.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/initial_frames/scene_motion/physics_iq_original_t1_center_0179_two_balls_pass.jpg","sourceDataset":"Physics-IQ","suggestedTrack":"scene_motion","scene":"rigid_object","spatialAbility":"direction, distance, relative_motion, crossing","perspective":"exocentric","caption":"Roll the two balls so they pass each other.","annotationPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/annotations/scene_motion/physics_iq_original_t1_center_0179_two_balls_pass.json"},{"id":"physics_iq_original_t1_center_0182_unstable_block_stack","videoPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0182_unstable_block_stack.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0182_unstable_block_stack.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/initial_frames/scene_motion/physics_iq_original_t1_center_0182_unstable_block_stack.jpg","sourceDataset":"Physics-IQ","suggestedTrack":"scene_motion","scene":"rigid_object","spatialAbility":"direction, support, contact, distance","perspective":"exocentric","caption":"Let the unstable block stack collapse.","annotationPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/annotations/scene_motion/physics_iq_original_t1_center_0182_unstable_block_stack.json"},{"id":"physics_iq_original_t1_center_0185_water_in_juice","videoPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0185_water_in_juice.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0185_water_in_juice.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/initial_frames/scene_motion/physics_iq_original_t1_center_0185_water_in_juice.jpg","sourceDataset":"Physics-IQ","suggestedTrack":"scene_motion","scene":"fluid_dynamics","spatialAbility":"direction, containment, contact, visibility","perspective":"exocentric","caption":"Pour water into the colored juice.","annotationPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/annotations/scene_motion/physics_iq_original_t1_center_0185_water_in_juice.json"},{"id":"physics_iq_original_t1_center_0194_weight_on_pillow","videoPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0194_weight_on_pillow.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/videos/scene_motion/physics_iq_original_t1_center_0194_weight_on_pillow.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/initial_frames/scene_motion/physics_iq_original_t1_center_0194_weight_on_pillow.jpg","sourceDataset":"Physics-IQ","suggestedTrack":"scene_motion","scene":"rigid_object","spatialAbility":"direction, contact, support, distance","perspective":"exocentric","caption":"Lower the weight onto the pillow.","annotationPath":"curated/spatial-world-model/v4/stage-b/physics-iq-original-batch-003/annotations/scene_motion/physics_iq_original_t1_center_0194_weight_on_pillow.json"},{"id":"sekai_coupled_-6i_5LrS2l8_0051665_0053465","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_-6i_5LrS2l8_0051665_0053465.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_-6i_5LrS2l8_0051665_0053465.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_-6i_5LrS2l8_0051665_0053465.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Printemps Haussmann?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_-6i_5LrS2l8_0051665_0053465.json"},{"id":"sekai_coupled_-bsCFBIBEg8_0093631_0095431","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_-bsCFBIBEg8_0093631_0095431.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_-bsCFBIBEg8_0093631_0095431.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_-bsCFBIBEg8_0093631_0095431.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Medellín?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_-bsCFBIBEg8_0093631_0095431.json"},{"id":"sekai_coupled_-DjpVar5SS8_0019215_0021015","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_-DjpVar5SS8_0019215_0021015.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_-DjpVar5SS8_0019215_0021015.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_-DjpVar5SS8_0019215_0021015.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Nanning Downtown?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_-DjpVar5SS8_0019215_0021015.json"},{"id":"sekai_coupled_-ENFJU6Vwxw_0014550_0016350","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_-ENFJU6Vwxw_0014550_0016350.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_-ENFJU6Vwxw_0014550_0016350.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_-ENFJU6Vwxw_0014550_0016350.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Shibuya?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_-ENFJU6Vwxw_0014550_0016350.json"},{"id":"sekai_coupled_-GUPd7QaySU_0211111_0212911","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_-GUPd7QaySU_0211111_0212911.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_-GUPd7QaySU_0211111_0212911.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_-GUPd7QaySU_0211111_0212911.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Manhattan?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_-GUPd7QaySU_0211111_0212911.json"},{"id":"sekai_coupled_-isPhTzx3lg_0058824_0060624","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_-isPhTzx3lg_0058824_0060624.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_-isPhTzx3lg_0058824_0060624.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_-isPhTzx3lg_0058824_0060624.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Prague?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_-isPhTzx3lg_0058824_0060624.json"},{"id":"sekai_coupled_-KIcfT7Vk7I_0022653_0024453","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_-KIcfT7Vk7I_0022653_0024453.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_-KIcfT7Vk7I_0022653_0024453.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_-KIcfT7Vk7I_0022653_0024453.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Republic Street?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_-KIcfT7Vk7I_0022653_0024453.json"},{"id":"sekai_coupled_-maaonZV67U_0032550_0034350","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_-maaonZV67U_0032550_0034350.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_-maaonZV67U_0032550_0034350.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_-maaonZV67U_0032550_0034350.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Gangnam Street?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_-maaonZV67U_0032550_0034350.json"},{"id":"sekai_coupled_-n99SR4cpuQ_0085099_0086899","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_-n99SR4cpuQ_0085099_0086899.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_-n99SR4cpuQ_0085099_0086899.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_-n99SR4cpuQ_0085099_0086899.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Budapest Christmas Markets?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_-n99SR4cpuQ_0085099_0086899.json"},{"id":"sekai_coupled_-NNoJ26XRSo_0094241_0096041","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_-NNoJ26XRSo_0094241_0096041.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_-NNoJ26XRSo_0094241_0096041.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_-NNoJ26XRSo_0094241_0096041.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Central London?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_-NNoJ26XRSo_0094241_0096041.json"},{"id":"sekai_coupled_-nzKUKEjHug_0028950_0030750","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_-nzKUKEjHug_0028950_0030750.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_-nzKUKEjHug_0028950_0030750.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_-nzKUKEjHug_0028950_0030750.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Bogota?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_-nzKUKEjHug_0028950_0030750.json"},{"id":"sekai_coupled_-OBxM3WqiNs_0025350_0027150","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_-OBxM3WqiNs_0025350_0027150.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_-OBxM3WqiNs_0025350_0027150.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_-OBxM3WqiNs_0025350_0027150.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Mumbai?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_-OBxM3WqiNs_0025350_0027150.json"},{"id":"sekai_coupled_-P0GAnQZChw_0080059_0081859","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_-P0GAnQZChw_0080059_0081859.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_-P0GAnQZChw_0080059_0081859.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_-P0GAnQZChw_0080059_0081859.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Hunters Point?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_-P0GAnQZChw_0080059_0081859.json"},{"id":"sekai_coupled_-sMY-FroYzc_0183540_0185340","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_-sMY-FroYzc_0183540_0185340.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_-sMY-FroYzc_0183540_0185340.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_-sMY-FroYzc_0183540_0185340.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Downtown Manhattan?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_-sMY-FroYzc_0183540_0185340.json"},{"id":"sekai_coupled_-TO0nWO178g_0151771_0153571","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_-TO0nWO178g_0151771_0153571.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_-TO0nWO178g_0151771_0153571.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_-TO0nWO178g_0151771_0153571.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through South Audley Street?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_-TO0nWO178g_0151771_0153571.json"},{"id":"sekai_coupled_-YmDhFlqPV8_0021750_0023550","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_-YmDhFlqPV8_0021750_0023550.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_-YmDhFlqPV8_0021750_0023550.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_-YmDhFlqPV8_0021750_0023550.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Apgujeong-Dong?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_-YmDhFlqPV8_0021750_0023550.json"},{"id":"sekai_coupled_0h0vHA4-XG4_0276210_0278010","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_0h0vHA4-XG4_0276210_0278010.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_0h0vHA4-XG4_0276210_0278010.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_0h0vHA4-XG4_0276210_0278010.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Nice Port?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_0h0vHA4-XG4_0276210_0278010.json"},{"id":"sekai_coupled_0w2CCZ8Lvw0_0163746_0165546","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_0w2CCZ8Lvw0_0163746_0165546.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_0w2CCZ8Lvw0_0163746_0165546.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_0w2CCZ8Lvw0_0163746_0165546.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians move relative to one another while traveling through Manhattan?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_0w2CCZ8Lvw0_0163746_0165546.json"},{"id":"sekai_coupled_0ZDU3iAQLx8_0010950_0012750","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_0ZDU3iAQLx8_0010950_0012750.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_0ZDU3iAQLx8_0010950_0012750.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_0ZDU3iAQLx8_0010950_0012750.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through King Abdullah Financial District (Kafd)?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_0ZDU3iAQLx8_0010950_0012750.json"},{"id":"sekai_coupled_1PnGQeFf2bs_0018150_0019950","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_1PnGQeFf2bs_0018150_0019950.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_1PnGQeFf2bs_0018150_0019950.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_1PnGQeFf2bs_0018150_0019950.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Koto Ward Office?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_1PnGQeFf2bs_0018150_0019950.json"},{"id":"sekai_coupled_1V8Vn8O5EJc_0053573_0055373","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_1V8Vn8O5EJc_0053573_0055373.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_1V8Vn8O5EJc_0053573_0055373.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_1V8Vn8O5EJc_0053573_0055373.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Midtown Manhattan?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_1V8Vn8O5EJc_0053573_0055373.json"},{"id":"sekai_coupled_1vvgvsqhBTw_0043350_0045150","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_1vvgvsqhBTw_0043350_0045150.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_1vvgvsqhBTw_0043350_0045150.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_1vvgvsqhBTw_0043350_0045150.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Gibraltar?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_1vvgvsqhBTw_0043350_0045150.json"},{"id":"sekai_coupled_1xmGN4pI1oM_0041359_0043159","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_1xmGN4pI1oM_0041359_0043159.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_1xmGN4pI1oM_0041359_0043159.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_1xmGN4pI1oM_0041359_0043159.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Rue De Rennes?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_1xmGN4pI1oM_0041359_0043159.json"},{"id":"sekai_coupled_1ySjJfzMToA_0104550_0106350","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_1ySjJfzMToA_0104550_0106350.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_1ySjJfzMToA_0104550_0106350.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_1ySjJfzMToA_0104550_0106350.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Insa-Dong And Eulji-Ro?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_1ySjJfzMToA_0104550_0106350.json"},{"id":"sekai_coupled_2-Vny1ybLHo_0016350_0018150","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_2-Vny1ybLHo_0016350_0018150.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_2-Vny1ybLHo_0016350_0018150.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_2-Vny1ybLHo_0016350_0018150.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Jalalabad?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_2-Vny1ybLHo_0016350_0018150.json"},{"id":"sekai_coupled_21parmhaEjk_0016350_0018150","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_21parmhaEjk_0016350_0018150.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_21parmhaEjk_0016350_0018150.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_21parmhaEjk_0016350_0018150.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Dongseongro & Modern Alley?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_21parmhaEjk_0016350_0018150.json"},{"id":"sekai_coupled_23cKuGD7dws_0026509_0028309","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_23cKuGD7dws_0026509_0028309.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_23cKuGD7dws_0026509_0028309.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_23cKuGD7dws_0026509_0028309.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Topanwala Bazaar?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_23cKuGD7dws_0026509_0028309.json"},{"id":"sekai_coupled_24t9lxkBEfc_0023725_0025525","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_24t9lxkBEfc_0023725_0025525.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_24t9lxkBEfc_0023725_0025525.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_24t9lxkBEfc_0023725_0025525.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Bryant Park?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_24t9lxkBEfc_0023725_0025525.json"},{"id":"sekai_coupled_27U867zCtVY_0038246_0040046","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_27U867zCtVY_0038246_0040046.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_27U867zCtVY_0038246_0040046.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_27U867zCtVY_0038246_0040046.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Edinburgh Castle?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_27U867zCtVY_0038246_0040046.json"},{"id":"sekai_coupled_2aZlTVnq2eQ_0295022_0296822","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_2aZlTVnq2eQ_0295022_0296822.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_2aZlTVnq2eQ_0295022_0296822.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_2aZlTVnq2eQ_0295022_0296822.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Piazza Di San Lorenzo?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_2aZlTVnq2eQ_0295022_0296822.json"},{"id":"sekai_coupled_2dG23zlXlNA_0508407_0510207","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_2dG23zlXlNA_0508407_0510207.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_2dG23zlXlNA_0508407_0510207.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_2dG23zlXlNA_0508407_0510207.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Brooklyn?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_2dG23zlXlNA_0508407_0510207.json"},{"id":"sekai_coupled_2dr6dsRoQ_4_0033121_0034921","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_2dr6dsRoQ_4_0033121_0034921.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_2dr6dsRoQ_4_0033121_0034921.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_2dr6dsRoQ_4_0033121_0034921.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Carnaby Street?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_2dr6dsRoQ_4_0033121_0034921.json"},{"id":"sekai_coupled_2EE0fk9N8Ek_0052350_0054150","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_2EE0fk9N8Ek_0052350_0054150.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_2EE0fk9N8Ek_0052350_0054150.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_2EE0fk9N8Ek_0052350_0054150.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Alanya?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_2EE0fk9N8Ek_0052350_0054150.json"},{"id":"sekai_coupled_2hTRqUYTaxw_0094692_0096492","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_2hTRqUYTaxw_0094692_0096492.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_2hTRqUYTaxw_0094692_0096492.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_2hTRqUYTaxw_0094692_0096492.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through La Gran Galeria De Salento Food Market?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_2hTRqUYTaxw_0094692_0096492.json"},{"id":"sekai_coupled_2IXHD25Gvsc_0205515_0207315","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_2IXHD25Gvsc_0205515_0207315.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_2IXHD25Gvsc_0205515_0207315.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_2IXHD25Gvsc_0205515_0207315.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through London?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_2IXHD25Gvsc_0205515_0207315.json"},{"id":"sekai_coupled_2kY9mYGAdeo_0037950_0039750","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_2kY9mYGAdeo_0037950_0039750.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_2kY9mYGAdeo_0037950_0039750.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_2kY9mYGAdeo_0037950_0039750.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Bar Street Along The Guard?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_2kY9mYGAdeo_0037950_0039750.json"},{"id":"sekai_coupled_2vvHMVlB0wc_0009150_0010950","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_2vvHMVlB0wc_0009150_0010950.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_2vvHMVlB0wc_0009150_0010950.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_2vvHMVlB0wc_0009150_0010950.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Warsaw?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_2vvHMVlB0wc_0009150_0010950.json"},{"id":"sekai_coupled_2wxJMygHzQw_0095106_0096906","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_2wxJMygHzQw_0095106_0096906.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_2wxJMygHzQw_0095106_0096906.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_2wxJMygHzQw_0095106_0096906.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians move relative to one another while traveling through Fulton St?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_2wxJMygHzQw_0095106_0096906.json"},{"id":"sekai_coupled_310iHU-N5OU_0007350_0009150","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_310iHU-N5OU_0007350_0009150.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_310iHU-N5OU_0007350_0009150.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_310iHU-N5OU_0007350_0009150.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Jamsil Railway Bridge?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_310iHU-N5OU_0007350_0009150.json"},{"id":"sekai_coupled_32Ck-6Dnk0w_0060616_0062416","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_32Ck-6Dnk0w_0060616_0062416.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_32Ck-6Dnk0w_0060616_0062416.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_32Ck-6Dnk0w_0060616_0062416.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Great Portland Street To Oxford Street?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_32Ck-6Dnk0w_0060616_0062416.json"},{"id":"sekai_coupled_3902i4Sbwp0_0036746_0038546","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_3902i4Sbwp0_0036746_0038546.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_3902i4Sbwp0_0036746_0038546.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_3902i4Sbwp0_0036746_0038546.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians move relative to one another while traveling through Nakano?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_3902i4Sbwp0_0036746_0038546.json"},{"id":"sekai_coupled_3aFIYNiOBlg_0095582_0097382","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_3aFIYNiOBlg_0095582_0097382.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_3aFIYNiOBlg_0095582_0097382.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_3aFIYNiOBlg_0095582_0097382.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Midtown Manhattan?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_3aFIYNiOBlg_0095582_0097382.json"},{"id":"sekai_coupled_3RSOX_8qqOo_0018150_0019950","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_3RSOX_8qqOo_0018150_0019950.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_3RSOX_8qqOo_0018150_0019950.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_3RSOX_8qqOo_0018150_0019950.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Yeonhui-Dong Alley?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_3RSOX_8qqOo_0018150_0019950.json"},{"id":"sekai_coupled_3vQ0crCyCak_0003750_0005550","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_3vQ0crCyCak_0003750_0005550.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_3vQ0crCyCak_0003750_0005550.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_3vQ0crCyCak_0003750_0005550.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Sloane Square?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_3vQ0crCyCak_0003750_0005550.json"},{"id":"sekai_coupled_3WCu7DA6LsA_0039750_0041550","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_3WCu7DA6LsA_0039750_0041550.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_3WCu7DA6LsA_0039750_0041550.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_3WCu7DA6LsA_0039750_0041550.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Montmartre?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_3WCu7DA6LsA_0039750_0041550.json"},{"id":"sekai_coupled_43LJyGY3L_w_0065943_0067743","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_43LJyGY3L_w_0065943_0067743.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_43LJyGY3L_w_0065943_0067743.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_43LJyGY3L_w_0065943_0067743.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through West Street Ancient Market?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_43LJyGY3L_w_0065943_0067743.json"},{"id":"sekai_coupled_46dcN1B3VrQ_0009150_0010950","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_46dcN1B3VrQ_0009150_0010950.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_46dcN1B3VrQ_0009150_0010950.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_46dcN1B3VrQ_0009150_0010950.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Xinyi District?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_46dcN1B3VrQ_0009150_0010950.json"},{"id":"sekai_coupled_48CyXuhIrE8_0079350_0081150","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_48CyXuhIrE8_0079350_0081150.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_48CyXuhIrE8_0079350_0081150.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_48CyXuhIrE8_0079350_0081150.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Dublin?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_48CyXuhIrE8_0079350_0081150.json"},{"id":"sekai_coupled_4f17VQJ1rqA_0054891_0056691","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_4f17VQJ1rqA_0054891_0056691.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_4f17VQJ1rqA_0054891_0056691.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_4f17VQJ1rqA_0054891_0056691.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Shibuya?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_4f17VQJ1rqA_0054891_0056691.json"},{"id":"sekai_coupled_4Ke2XKxmHCo_0050550_0052350","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_4Ke2XKxmHCo_0050550_0052350.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_4Ke2XKxmHCo_0050550_0052350.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_4Ke2XKxmHCo_0050550_0052350.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Teheran-Ro Streets?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_4Ke2XKxmHCo_0050550_0052350.json"},{"id":"sekai_coupled_4nFzzRnEZac_0137333_0139133","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_4nFzzRnEZac_0137333_0139133.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_4nFzzRnEZac_0137333_0139133.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_4nFzzRnEZac_0137333_0139133.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians move relative to one another while traveling through Tokyo Station?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_4nFzzRnEZac_0137333_0139133.json"},{"id":"sekai_coupled_4NN7qfn60Sw_0065983_0067783","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_4NN7qfn60Sw_0065983_0067783.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_4NN7qfn60Sw_0065983_0067783.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_4NN7qfn60Sw_0065983_0067783.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Canary Wharf?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_4NN7qfn60Sw_0065983_0067783.json"},{"id":"sekai_coupled_4Of_OevsO54_0098909_0100709","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_4Of_OevsO54_0098909_0100709.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_4Of_OevsO54_0098909_0100709.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_4Of_OevsO54_0098909_0100709.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Farringdon Station To Liverpool Street?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_4Of_OevsO54_0098909_0100709.json"},{"id":"sekai_coupled_4Pga3DqeLCs_0019950_0021750","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_4Pga3DqeLCs_0019950_0021750.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_4Pga3DqeLCs_0019950_0021750.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_4Pga3DqeLCs_0019950_0021750.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Reykjavik?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_4Pga3DqeLCs_0019950_0021750.json"},{"id":"sekai_coupled_4W8N4jC856M_0057750_0059550","videoPath":"curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_4W8N4jC856M_0057750_0059550.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/videos/sekai_coupled_4W8N4jC856M_0057750_0059550.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v12/sekai-walking-coupled/initial_frames/sekai_coupled_4W8N4jC856M_0057750_0059550.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"coupled motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Visibility and Occlusion, Viewpoint Geometry, Relative and Coupled Motion","perspective":"Egocentric","caption":"How do the camera wearer and nearby pedestrians and vehicles move relative to one another while traveling through Reykjavik?","annotationPath":"curated/spatial-world-model/v12/sekai-walking-coupled/annotations/sekai_coupled_4W8N4jC856M_0057750_0059550.json"},{"id":"sekai_walking_-0Gb7_LZg4M_0030898_0032698","videoPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_-0Gb7_LZg4M_0030898_0032698.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_-0Gb7_LZg4M_0030898_0032698.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/initial_frames/viewpoint_motion/sekai_walking_-0Gb7_LZg4M_0030898_0032698.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"viewpoint_motion","scene":"outdoor-natural","spatialAbility":"camera_translation, camera_rotation, depth_order, relative_position","perspective":"egocentric_or_handheld","caption":"Move forward through the scene and turn to reveal the surrounding geometry.","annotationPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/annotations/viewpoint_motion/sekai_walking_-0Gb7_LZg4M_0030898_0032698.json"},{"id":"sekai_walking_-BgZJ38obds_0009443_0011243","videoPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_-BgZJ38obds_0009443_0011243.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_-BgZJ38obds_0009443_0011243.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/initial_frames/viewpoint_motion/sekai_walking_-BgZJ38obds_0009443_0011243.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"viewpoint_motion","scene":"indoor-modern","spatialAbility":"camera_translation, camera_rotation, depth_order, relative_position","perspective":"egocentric_or_handheld","caption":"Move forward through the scene and turn to reveal the surrounding geometry.","annotationPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/annotations/viewpoint_motion/sekai_walking_-BgZJ38obds_0009443_0011243.json"},{"id":"sekai_walking_-E7QZ0kz7lw_0066608_0068408","videoPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_-E7QZ0kz7lw_0066608_0068408.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_-E7QZ0kz7lw_0066608_0068408.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/initial_frames/viewpoint_motion/sekai_walking_-E7QZ0kz7lw_0066608_0068408.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"viewpoint_motion","scene":"indoor-ancient","spatialAbility":"camera_translation, camera_rotation, depth_order, relative_position","perspective":"egocentric_or_handheld","caption":"Move forward through the scene and turn to reveal the surrounding geometry.","annotationPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/annotations/viewpoint_motion/sekai_walking_-E7QZ0kz7lw_0066608_0068408.json"},{"id":"sekai_walking_-h3yz8BMwtU_0006821_0008621","videoPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_-h3yz8BMwtU_0006821_0008621.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_-h3yz8BMwtU_0006821_0008621.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/initial_frames/viewpoint_motion/sekai_walking_-h3yz8BMwtU_0006821_0008621.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"viewpoint_motion","scene":"indoor-ancient","spatialAbility":"camera_translation, camera_rotation, depth_order, relative_position","perspective":"egocentric_or_handheld","caption":"Move forward through the scene and turn to reveal the surrounding geometry.","annotationPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/annotations/viewpoint_motion/sekai_walking_-h3yz8BMwtU_0006821_0008621.json"},{"id":"sekai_walking_-jQ4igHgVac_0018150_0019950","videoPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_-jQ4igHgVac_0018150_0019950.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_-jQ4igHgVac_0018150_0019950.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/initial_frames/viewpoint_motion/sekai_walking_-jQ4igHgVac_0018150_0019950.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"viewpoint_motion","scene":"outdoor-urban","spatialAbility":"camera_translation, camera_rotation, depth_order, relative_position","perspective":"egocentric_or_handheld","caption":"Move forward through the scene and turn to reveal the surrounding geometry.","annotationPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/annotations/viewpoint_motion/sekai_walking_-jQ4igHgVac_0018150_0019950.json"},{"id":"sekai_walking_-K6K5Raz6tg_0055141_0056941","videoPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_-K6K5Raz6tg_0055141_0056941.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_-K6K5Raz6tg_0055141_0056941.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/initial_frames/viewpoint_motion/sekai_walking_-K6K5Raz6tg_0055141_0056941.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"viewpoint_motion","scene":"outdoor-urban","spatialAbility":"camera_translation, camera_rotation, depth_order, relative_position","perspective":"egocentric_or_handheld","caption":"Move forward through the scene and turn to reveal the surrounding geometry.","annotationPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/annotations/viewpoint_motion/sekai_walking_-K6K5Raz6tg_0055141_0056941.json"},{"id":"sekai_walking_-l3ZLLemjvk_0047264_0049064","videoPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_-l3ZLLemjvk_0047264_0049064.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_-l3ZLLemjvk_0047264_0049064.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/initial_frames/viewpoint_motion/sekai_walking_-l3ZLLemjvk_0047264_0049064.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"viewpoint_motion","scene":"indoor-ancient","spatialAbility":"camera_translation, camera_rotation, depth_order, relative_position","perspective":"egocentric_or_handheld","caption":"Move forward through the scene and turn to reveal the surrounding geometry.","annotationPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/annotations/viewpoint_motion/sekai_walking_-l3ZLLemjvk_0047264_0049064.json"},{"id":"sekai_walking_-Lh_H3kNIU4_0201305_0203105","videoPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_-Lh_H3kNIU4_0201305_0203105.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_-Lh_H3kNIU4_0201305_0203105.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/initial_frames/viewpoint_motion/sekai_walking_-Lh_H3kNIU4_0201305_0203105.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"viewpoint_motion","scene":"indoor-ancient","spatialAbility":"camera_translation, camera_rotation, depth_order, relative_position","perspective":"egocentric_or_handheld","caption":"Move forward through the scene and turn to reveal the surrounding geometry.","annotationPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/annotations/viewpoint_motion/sekai_walking_-Lh_H3kNIU4_0201305_0203105.json"},{"id":"sekai_walking_-NNqAxcoHbc_0055519_0057319","videoPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_-NNqAxcoHbc_0055519_0057319.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_-NNqAxcoHbc_0055519_0057319.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/initial_frames/viewpoint_motion/sekai_walking_-NNqAxcoHbc_0055519_0057319.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"viewpoint_motion","scene":"indoor-modern","spatialAbility":"camera_translation, camera_rotation, depth_order, relative_position","perspective":"egocentric_or_handheld","caption":"Move forward through the scene and turn to reveal the surrounding geometry.","annotationPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/annotations/viewpoint_motion/sekai_walking_-NNqAxcoHbc_0055519_0057319.json"},{"id":"sekai_walking_-OBxM3WqiNs_0016350_0018150","videoPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_-OBxM3WqiNs_0016350_0018150.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_-OBxM3WqiNs_0016350_0018150.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/initial_frames/viewpoint_motion/sekai_walking_-OBxM3WqiNs_0016350_0018150.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"viewpoint_motion","scene":"indoor-modern","spatialAbility":"camera_translation, camera_rotation, depth_order, relative_position","perspective":"egocentric_or_handheld","caption":"Move forward through the scene and turn to reveal the surrounding geometry.","annotationPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/annotations/viewpoint_motion/sekai_walking_-OBxM3WqiNs_0016350_0018150.json"},{"id":"sekai_walking_-S4wpZdVqaM_0048453_0050253","videoPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_-S4wpZdVqaM_0048453_0050253.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_-S4wpZdVqaM_0048453_0050253.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/initial_frames/viewpoint_motion/sekai_walking_-S4wpZdVqaM_0048453_0050253.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"viewpoint_motion","scene":"outdoor-urban","spatialAbility":"camera_translation, camera_rotation, depth_order, relative_position","perspective":"egocentric_or_handheld","caption":"Move forward through the scene and turn to reveal the surrounding geometry.","annotationPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/annotations/viewpoint_motion/sekai_walking_-S4wpZdVqaM_0048453_0050253.json"},{"id":"sekai_walking_-sMY-FroYzc_0028115_0029915","videoPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_-sMY-FroYzc_0028115_0029915.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_-sMY-FroYzc_0028115_0029915.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/initial_frames/viewpoint_motion/sekai_walking_-sMY-FroYzc_0028115_0029915.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"viewpoint_motion","scene":"indoor-modern","spatialAbility":"camera_translation, camera_rotation, depth_order, relative_position","perspective":"egocentric_or_handheld","caption":"Move forward through the scene and turn to reveal the surrounding geometry.","annotationPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/annotations/viewpoint_motion/sekai_walking_-sMY-FroYzc_0028115_0029915.json"},{"id":"sekai_walking_01xoRyv25LQ_0095402_0097202","videoPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_01xoRyv25LQ_0095402_0097202.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_01xoRyv25LQ_0095402_0097202.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/initial_frames/viewpoint_motion/sekai_walking_01xoRyv25LQ_0095402_0097202.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"viewpoint_motion","scene":"outdoor-urban","spatialAbility":"camera_translation, camera_rotation, depth_order, relative_position","perspective":"egocentric_or_handheld","caption":"Move forward through the scene and turn to reveal the surrounding geometry.","annotationPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/annotations/viewpoint_motion/sekai_walking_01xoRyv25LQ_0095402_0097202.json"},{"id":"sekai_walking_09yi1wNAntw_0208972_0210772","videoPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_09yi1wNAntw_0208972_0210772.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_09yi1wNAntw_0208972_0210772.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/initial_frames/viewpoint_motion/sekai_walking_09yi1wNAntw_0208972_0210772.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"viewpoint_motion","scene":"indoor-ancient","spatialAbility":"camera_translation, camera_rotation, depth_order, relative_position","perspective":"egocentric_or_handheld","caption":"Move forward through the scene and turn to reveal the surrounding geometry.","annotationPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/annotations/viewpoint_motion/sekai_walking_09yi1wNAntw_0208972_0210772.json"},{"id":"sekai_walking_0bIHXSZKVAA_0066750_0068550","videoPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_0bIHXSZKVAA_0066750_0068550.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_0bIHXSZKVAA_0066750_0068550.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/initial_frames/viewpoint_motion/sekai_walking_0bIHXSZKVAA_0066750_0068550.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"viewpoint_motion","scene":"indoor-ancient","spatialAbility":"camera_translation, camera_rotation, depth_order, relative_position","perspective":"egocentric_or_handheld","caption":"Move forward through the scene and turn to reveal the surrounding geometry.","annotationPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/annotations/viewpoint_motion/sekai_walking_0bIHXSZKVAA_0066750_0068550.json"},{"id":"sekai_walking_0Bp7Jti40Uc_0145232_0147032","videoPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_0Bp7Jti40Uc_0145232_0147032.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_0Bp7Jti40Uc_0145232_0147032.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/initial_frames/viewpoint_motion/sekai_walking_0Bp7Jti40Uc_0145232_0147032.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"viewpoint_motion","scene":"indoor-modern","spatialAbility":"camera_translation, camera_rotation, depth_order, relative_position","perspective":"egocentric_or_handheld","caption":"Move forward through the scene and turn to reveal the surrounding geometry.","annotationPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/annotations/viewpoint_motion/sekai_walking_0Bp7Jti40Uc_0145232_0147032.json"},{"id":"sekai_walking_0h0vHA4-XG4_0169311_0171111","videoPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_0h0vHA4-XG4_0169311_0171111.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_0h0vHA4-XG4_0169311_0171111.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/initial_frames/viewpoint_motion/sekai_walking_0h0vHA4-XG4_0169311_0171111.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"viewpoint_motion","scene":"outdoor-natural","spatialAbility":"camera_translation, camera_rotation, depth_order, relative_position","perspective":"egocentric_or_handheld","caption":"Move forward through the scene and turn to reveal the surrounding geometry.","annotationPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/annotations/viewpoint_motion/sekai_walking_0h0vHA4-XG4_0169311_0171111.json"},{"id":"sekai_walking_0joF0FYOneU_0067207_0069007","videoPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_0joF0FYOneU_0067207_0069007.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_0joF0FYOneU_0067207_0069007.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/initial_frames/viewpoint_motion/sekai_walking_0joF0FYOneU_0067207_0069007.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"viewpoint_motion","scene":"outdoor-natural","spatialAbility":"camera_translation, camera_rotation, depth_order, relative_position","perspective":"egocentric_or_handheld","caption":"Move forward through the scene and turn to reveal the surrounding geometry.","annotationPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/annotations/viewpoint_motion/sekai_walking_0joF0FYOneU_0067207_0069007.json"},{"id":"sekai_walking_0Pb9G3RJ8Pg_0054898_0056698","videoPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_0Pb9G3RJ8Pg_0054898_0056698.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_0Pb9G3RJ8Pg_0054898_0056698.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/initial_frames/viewpoint_motion/sekai_walking_0Pb9G3RJ8Pg_0054898_0056698.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"viewpoint_motion","scene":"outdoor-natural","spatialAbility":"camera_translation, camera_rotation, depth_order, relative_position","perspective":"egocentric_or_handheld","caption":"Move forward through the scene and turn to reveal the surrounding geometry.","annotationPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/annotations/viewpoint_motion/sekai_walking_0Pb9G3RJ8Pg_0054898_0056698.json"},{"id":"sekai_walking_0ScG4n437mM_0026278_0028078","videoPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_0ScG4n437mM_0026278_0028078.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_0ScG4n437mM_0026278_0028078.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/initial_frames/viewpoint_motion/sekai_walking_0ScG4n437mM_0026278_0028078.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"viewpoint_motion","scene":"indoor-modern","spatialAbility":"camera_translation, camera_rotation, depth_order, relative_position","perspective":"egocentric_or_handheld","caption":"Move forward through the scene and turn to reveal the surrounding geometry.","annotationPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/annotations/viewpoint_motion/sekai_walking_0ScG4n437mM_0026278_0028078.json"},{"id":"sekai_walking_0votdFf4HoU_0030138_0031938","videoPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_0votdFf4HoU_0030138_0031938.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_0votdFf4HoU_0030138_0031938.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/initial_frames/viewpoint_motion/sekai_walking_0votdFf4HoU_0030138_0031938.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"viewpoint_motion","scene":"outdoor-natural","spatialAbility":"camera_translation, camera_rotation, depth_order, relative_position","perspective":"egocentric_or_handheld","caption":"Move forward through the scene and turn to reveal the surrounding geometry.","annotationPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/annotations/viewpoint_motion/sekai_walking_0votdFf4HoU_0030138_0031938.json"},{"id":"sekai_walking_0ZDU3iAQLx8_0028950_0030750","videoPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_0ZDU3iAQLx8_0028950_0030750.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_0ZDU3iAQLx8_0028950_0030750.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/initial_frames/viewpoint_motion/sekai_walking_0ZDU3iAQLx8_0028950_0030750.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"viewpoint_motion","scene":"outdoor-urban","spatialAbility":"camera_translation, camera_rotation, depth_order, relative_position","perspective":"egocentric_or_handheld","caption":"Move forward through the scene and turn to reveal the surrounding geometry.","annotationPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/annotations/viewpoint_motion/sekai_walking_0ZDU3iAQLx8_0028950_0030750.json"},{"id":"sekai_walking_1mzMcKwLQ-E_0021750_0023550","videoPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_1mzMcKwLQ-E_0021750_0023550.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_1mzMcKwLQ-E_0021750_0023550.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/initial_frames/viewpoint_motion/sekai_walking_1mzMcKwLQ-E_0021750_0023550.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"viewpoint_motion","scene":"indoor-modern","spatialAbility":"camera_translation, camera_rotation, depth_order, relative_position","perspective":"egocentric_or_handheld","caption":"Move forward through the scene and turn to reveal the surrounding geometry.","annotationPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/annotations/viewpoint_motion/sekai_walking_1mzMcKwLQ-E_0021750_0023550.json"},{"id":"sekai_walking_1TlIYIxHzs4_0026150_0027950","videoPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_1TlIYIxHzs4_0026150_0027950.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_1TlIYIxHzs4_0026150_0027950.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/initial_frames/viewpoint_motion/sekai_walking_1TlIYIxHzs4_0026150_0027950.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"viewpoint_motion","scene":"indoor-modern","spatialAbility":"camera_translation, camera_rotation, depth_order, relative_position","perspective":"egocentric_or_handheld","caption":"Move forward through the scene and turn to reveal the surrounding geometry.","annotationPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/annotations/viewpoint_motion/sekai_walking_1TlIYIxHzs4_0026150_0027950.json"},{"id":"sekai_walking_1UFmQNXAdkk_0103406_0105206","videoPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_1UFmQNXAdkk_0103406_0105206.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_1UFmQNXAdkk_0103406_0105206.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/initial_frames/viewpoint_motion/sekai_walking_1UFmQNXAdkk_0103406_0105206.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"viewpoint_motion","scene":"indoor-modern","spatialAbility":"camera_translation, camera_rotation, depth_order, relative_position","perspective":"egocentric_or_handheld","caption":"Move forward through the scene and turn to reveal the surrounding geometry.","annotationPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/annotations/viewpoint_motion/sekai_walking_1UFmQNXAdkk_0103406_0105206.json"},{"id":"sekai_walking_1Vde3l1vqhE_0131410_0133210","videoPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_1Vde3l1vqhE_0131410_0133210.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_1Vde3l1vqhE_0131410_0133210.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/initial_frames/viewpoint_motion/sekai_walking_1Vde3l1vqhE_0131410_0133210.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"viewpoint_motion","scene":"indoor-modern","spatialAbility":"camera_translation, camera_rotation, depth_order, relative_position","perspective":"egocentric_or_handheld","caption":"Move forward through the scene and turn to reveal the surrounding geometry.","annotationPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/annotations/viewpoint_motion/sekai_walking_1Vde3l1vqhE_0131410_0133210.json"},{"id":"sekai_walking_2-Vny1ybLHo_0064244_0066044","videoPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_2-Vny1ybLHo_0064244_0066044.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_2-Vny1ybLHo_0064244_0066044.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/initial_frames/viewpoint_motion/sekai_walking_2-Vny1ybLHo_0064244_0066044.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"viewpoint_motion","scene":"outdoor-natural","spatialAbility":"camera_translation, camera_rotation, depth_order, relative_position","perspective":"egocentric_or_handheld","caption":"Move forward through the scene and turn to reveal the surrounding geometry.","annotationPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/annotations/viewpoint_motion/sekai_walking_2-Vny1ybLHo_0064244_0066044.json"},{"id":"sekai_walking_21parmhaEjk_0082709_0084509","videoPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_21parmhaEjk_0082709_0084509.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_21parmhaEjk_0082709_0084509.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/initial_frames/viewpoint_motion/sekai_walking_21parmhaEjk_0082709_0084509.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"viewpoint_motion","scene":"outdoor-urban","spatialAbility":"camera_translation, camera_rotation, depth_order, relative_position","perspective":"egocentric_or_handheld","caption":"Move forward through the scene and turn to reveal the surrounding geometry.","annotationPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/annotations/viewpoint_motion/sekai_walking_21parmhaEjk_0082709_0084509.json"},{"id":"sekai_walking_2dG23zlXlNA_0580492_0582292","videoPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_2dG23zlXlNA_0580492_0582292.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_2dG23zlXlNA_0580492_0582292.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/initial_frames/viewpoint_motion/sekai_walking_2dG23zlXlNA_0580492_0582292.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"viewpoint_motion","scene":"outdoor-urban","spatialAbility":"camera_translation, camera_rotation, depth_order, relative_position","perspective":"egocentric_or_handheld","caption":"Move forward through the scene and turn to reveal the surrounding geometry.","annotationPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/annotations/viewpoint_motion/sekai_walking_2dG23zlXlNA_0580492_0582292.json"},{"id":"sekai_walking_2GKwV_Da7BA_0059444_0061244","videoPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_2GKwV_Da7BA_0059444_0061244.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_2GKwV_Da7BA_0059444_0061244.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/initial_frames/viewpoint_motion/sekai_walking_2GKwV_Da7BA_0059444_0061244.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"viewpoint_motion","scene":"indoor-modern","spatialAbility":"camera_translation, camera_rotation, depth_order, relative_position","perspective":"egocentric_or_handheld","caption":"Move forward through the scene and turn to reveal the surrounding geometry.","annotationPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/annotations/viewpoint_motion/sekai_walking_2GKwV_Da7BA_0059444_0061244.json"},{"id":"sekai_walking_2mGAKmK2zTk_0423293_0425093","videoPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_2mGAKmK2zTk_0423293_0425093.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_2mGAKmK2zTk_0423293_0425093.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/initial_frames/viewpoint_motion/sekai_walking_2mGAKmK2zTk_0423293_0425093.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"viewpoint_motion","scene":"indoor-ancient","spatialAbility":"camera_translation, camera_rotation, depth_order, relative_position","perspective":"egocentric_or_handheld","caption":"Move forward through the scene and turn to reveal the surrounding geometry.","annotationPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/annotations/viewpoint_motion/sekai_walking_2mGAKmK2zTk_0423293_0425093.json"},{"id":"sekai_walking_2mulVGR0VTk_0013545_0015345","videoPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_2mulVGR0VTk_0013545_0015345.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_2mulVGR0VTk_0013545_0015345.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/initial_frames/viewpoint_motion/sekai_walking_2mulVGR0VTk_0013545_0015345.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"viewpoint_motion","scene":"indoor-ancient","spatialAbility":"camera_translation, camera_rotation, depth_order, relative_position","perspective":"egocentric_or_handheld","caption":"Move forward through the scene and turn to reveal the surrounding geometry.","annotationPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/annotations/viewpoint_motion/sekai_walking_2mulVGR0VTk_0013545_0015345.json"},{"id":"sekai_walking_39erXlAjHb8_0082950_0084750","videoPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_39erXlAjHb8_0082950_0084750.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_39erXlAjHb8_0082950_0084750.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/initial_frames/viewpoint_motion/sekai_walking_39erXlAjHb8_0082950_0084750.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"viewpoint_motion","scene":"indoor-ancient","spatialAbility":"camera_translation, camera_rotation, depth_order, relative_position","perspective":"egocentric_or_handheld","caption":"Move forward through the scene and turn to reveal the surrounding geometry.","annotationPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/annotations/viewpoint_motion/sekai_walking_39erXlAjHb8_0082950_0084750.json"},{"id":"sekai_walking_3aas-RT7Ul8_0108560_0110360","videoPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_3aas-RT7Ul8_0108560_0110360.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_3aas-RT7Ul8_0108560_0110360.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/initial_frames/viewpoint_motion/sekai_walking_3aas-RT7Ul8_0108560_0110360.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"viewpoint_motion","scene":"indoor-modern","spatialAbility":"camera_translation, camera_rotation, depth_order, relative_position","perspective":"egocentric_or_handheld","caption":"Move forward through the scene and turn to reveal the surrounding geometry.","annotationPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/annotations/viewpoint_motion/sekai_walking_3aas-RT7Ul8_0108560_0110360.json"},{"id":"sekai_walking_3cEBVoersiE_0010950_0012750","videoPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_3cEBVoersiE_0010950_0012750.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_3cEBVoersiE_0010950_0012750.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/initial_frames/viewpoint_motion/sekai_walking_3cEBVoersiE_0010950_0012750.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"viewpoint_motion","scene":"outdoor-urban","spatialAbility":"camera_translation, camera_rotation, depth_order, relative_position","perspective":"egocentric_or_handheld","caption":"Move forward through the scene and turn to reveal the surrounding geometry.","annotationPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/annotations/viewpoint_motion/sekai_walking_3cEBVoersiE_0010950_0012750.json"},{"id":"sekai_walking_3iNd4e0j4mE_0033140_0034940","videoPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_3iNd4e0j4mE_0033140_0034940.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_3iNd4e0j4mE_0033140_0034940.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/initial_frames/viewpoint_motion/sekai_walking_3iNd4e0j4mE_0033140_0034940.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"viewpoint_motion","scene":"indoor-ancient","spatialAbility":"camera_translation, camera_rotation, depth_order, relative_position","perspective":"egocentric_or_handheld","caption":"Move forward through the scene and turn to reveal the surrounding geometry.","annotationPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/annotations/viewpoint_motion/sekai_walking_3iNd4e0j4mE_0033140_0034940.json"},{"id":"sekai_walking_3mvWjli3X5g_0028758_0030558","videoPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_3mvWjli3X5g_0028758_0030558.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_3mvWjli3X5g_0028758_0030558.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/initial_frames/viewpoint_motion/sekai_walking_3mvWjli3X5g_0028758_0030558.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"viewpoint_motion","scene":"outdoor-urban","spatialAbility":"camera_translation, camera_rotation, depth_order, relative_position","perspective":"egocentric_or_handheld","caption":"Move forward through the scene and turn to reveal the surrounding geometry.","annotationPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/annotations/viewpoint_motion/sekai_walking_3mvWjli3X5g_0028758_0030558.json"},{"id":"sekai_walking_43LJyGY3L_w_0016605_0018405","videoPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_43LJyGY3L_w_0016605_0018405.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_43LJyGY3L_w_0016605_0018405.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/initial_frames/viewpoint_motion/sekai_walking_43LJyGY3L_w_0016605_0018405.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"viewpoint_motion","scene":"outdoor-urban","spatialAbility":"camera_translation, camera_rotation, depth_order, relative_position","perspective":"egocentric_or_handheld","caption":"Move forward through the scene and turn to reveal the surrounding geometry.","annotationPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/annotations/viewpoint_motion/sekai_walking_43LJyGY3L_w_0016605_0018405.json"},{"id":"sekai_walking_48CyXuhIrE8_0050550_0052350","videoPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_48CyXuhIrE8_0050550_0052350.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_48CyXuhIrE8_0050550_0052350.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/initial_frames/viewpoint_motion/sekai_walking_48CyXuhIrE8_0050550_0052350.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"viewpoint_motion","scene":"outdoor-urban","spatialAbility":"camera_translation, camera_rotation, depth_order, relative_position","perspective":"egocentric_or_handheld","caption":"Move forward through the scene and turn to reveal the surrounding geometry.","annotationPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/annotations/viewpoint_motion/sekai_walking_48CyXuhIrE8_0050550_0052350.json"},{"id":"sekai_walking_4BDQvDsQMKg_0175276_0177076","videoPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_4BDQvDsQMKg_0175276_0177076.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_4BDQvDsQMKg_0175276_0177076.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/initial_frames/viewpoint_motion/sekai_walking_4BDQvDsQMKg_0175276_0177076.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"viewpoint_motion","scene":"indoor-ancient","spatialAbility":"camera_translation, camera_rotation, depth_order, relative_position","perspective":"egocentric_or_handheld","caption":"Move forward through the scene and turn to reveal the surrounding geometry.","annotationPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/annotations/viewpoint_motion/sekai_walking_4BDQvDsQMKg_0175276_0177076.json"},{"id":"sekai_walking_4fuBhkQGtfk_0014550_0016350","videoPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_4fuBhkQGtfk_0014550_0016350.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_4fuBhkQGtfk_0014550_0016350.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/initial_frames/viewpoint_motion/sekai_walking_4fuBhkQGtfk_0014550_0016350.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"viewpoint_motion","scene":"indoor-modern","spatialAbility":"camera_translation, camera_rotation, depth_order, relative_position","perspective":"egocentric_or_handheld","caption":"Move forward through the scene and turn to reveal the surrounding geometry.","annotationPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/annotations/viewpoint_motion/sekai_walking_4fuBhkQGtfk_0014550_0016350.json"},{"id":"sekai_walking_4LfT08Soc70_0042696_0044496","videoPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_4LfT08Soc70_0042696_0044496.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_4LfT08Soc70_0042696_0044496.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/initial_frames/viewpoint_motion/sekai_walking_4LfT08Soc70_0042696_0044496.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"viewpoint_motion","scene":"indoor-ancient","spatialAbility":"camera_translation, camera_rotation, depth_order, relative_position","perspective":"egocentric_or_handheld","caption":"Move forward through the scene and turn to reveal the surrounding geometry.","annotationPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/annotations/viewpoint_motion/sekai_walking_4LfT08Soc70_0042696_0044496.json"},{"id":"sekai_walking_4LZ6lZOacvI_0036150_0037950","videoPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_4LZ6lZOacvI_0036150_0037950.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_4LZ6lZOacvI_0036150_0037950.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/initial_frames/viewpoint_motion/sekai_walking_4LZ6lZOacvI_0036150_0037950.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"viewpoint_motion","scene":"indoor-ancient","spatialAbility":"camera_translation, camera_rotation, depth_order, relative_position","perspective":"egocentric_or_handheld","caption":"Move forward through the scene and turn to reveal the surrounding geometry.","annotationPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/annotations/viewpoint_motion/sekai_walking_4LZ6lZOacvI_0036150_0037950.json"},{"id":"sekai_walking_4W8N4jC856M_0028950_0030750","videoPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_4W8N4jC856M_0028950_0030750.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/videos/viewpoint_motion/sekai_walking_4W8N4jC856M_0028950_0030750.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/initial_frames/viewpoint_motion/sekai_walking_4W8N4jC856M_0028950_0030750.jpg","sourceDataset":"Sekai Walking","suggestedTrack":"viewpoint_motion","scene":"outdoor-urban","spatialAbility":"camera_translation, camera_rotation, depth_order, relative_position","perspective":"egocentric_or_handheld","caption":"Move forward through the scene and turn to reveal the surrounding geometry.","annotationPath":"curated/spatial-world-model/v4/stage-b/sekai-walking-batch-004/annotations/viewpoint_motion/sekai_walking_4W8N4jC856M_0028950_0030750.json"},{"id":"spatialvid_diverse_09b33a98-cf75-592a-8b20-6c2a4db10687","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_09b33a98-cf75-592a-8b20-6c2a4db10687.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_09b33a98-cf75-592a-8b20-6c2a4db10687.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_diverse_09b33a98-cf75-592a-8b20-6c2a4db10687.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's motion through this Interior;Modern Home Interior scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_diverse_09b33a98-cf75-592a-8b20-6c2a4db10687.json"},{"id":"spatialvid_diverse_170cdfd6-1b68-59c2-abf2-1a36cbe70553","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_170cdfd6-1b68-59c2-abf2-1a36cbe70553.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_170cdfd6-1b68-59c2-abf2-1a36cbe70553.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_diverse_170cdfd6-1b68-59c2-abf2-1a36cbe70553.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"urban","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's motion through this Urban;Street Scene scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_diverse_170cdfd6-1b68-59c2-abf2-1a36cbe70553.json"},{"id":"spatialvid_diverse_2048f14d-f56b-551b-9712-23f050d8c46f","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_2048f14d-f56b-551b-9712-23f050d8c46f.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_2048f14d-f56b-551b-9712-23f050d8c46f.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_diverse_2048f14d-f56b-551b-9712-23f050d8c46f.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's motion through this Interior;Modern Home Interior scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_diverse_2048f14d-f56b-551b-9712-23f050d8c46f.json"},{"id":"spatialvid_diverse_2259d5a0-bf66-54bc-b72c-b67589922d98","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_2259d5a0-bf66-54bc-b72c-b67589922d98.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_2259d5a0-bf66-54bc-b72c-b67589922d98.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_diverse_2259d5a0-bf66-54bc-b72c-b67589922d98.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"urban","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's motion through this Urban;Residential Street scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_diverse_2259d5a0-bf66-54bc-b72c-b67589922d98.json"},{"id":"spatialvid_diverse_258b6f7d-f6b7-5e5f-8ce9-1c3ce28f06de","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_258b6f7d-f6b7-5e5f-8ce9-1c3ce28f06de.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_258b6f7d-f6b7-5e5f-8ce9-1c3ce28f06de.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_diverse_258b6f7d-f6b7-5e5f-8ce9-1c3ce28f06de.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's motion through this Interior;Luxury Home scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_diverse_258b6f7d-f6b7-5e5f-8ce9-1c3ce28f06de.json"},{"id":"spatialvid_diverse_2710f36c-d0e1-5811-9260-52a8676d6dc6","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_2710f36c-d0e1-5811-9260-52a8676d6dc6.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_2710f36c-d0e1-5811-9260-52a8676d6dc6.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_diverse_2710f36c-d0e1-5811-9260-52a8676d6dc6.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's motion through this Interior;Open-Concept Kitchen and Living Area scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_diverse_2710f36c-d0e1-5811-9260-52a8676d6dc6.json"},{"id":"spatialvid_diverse_29a2d59c-1422-5faf-a1ae-f25e0b48c9e6","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_29a2d59c-1422-5faf-a1ae-f25e0b48c9e6.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_29a2d59c-1422-5faf-a1ae-f25e0b48c9e6.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_diverse_29a2d59c-1422-5faf-a1ae-f25e0b48c9e6.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's motion through this Waterfront;Coastal Path scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_diverse_29a2d59c-1422-5faf-a1ae-f25e0b48c9e6.json"},{"id":"spatialvid_diverse_30255e62-5e8e-561b-9889-af7590a3ec66","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_30255e62-5e8e-561b-9889-af7590a3ec66.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_30255e62-5e8e-561b-9889-af7590a3ec66.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_diverse_30255e62-5e8e-561b-9889-af7590a3ec66.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"urban","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's motion through this Urban;Street Scene scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_diverse_30255e62-5e8e-561b-9889-af7590a3ec66.json"},{"id":"spatialvid_diverse_3f16c8e8-4891-52d5-9dba-3cd76afe0700","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_3f16c8e8-4891-52d5-9dba-3cd76afe0700.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_3f16c8e8-4891-52d5-9dba-3cd76afe0700.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_diverse_3f16c8e8-4891-52d5-9dba-3cd76afe0700.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's motion through this Rural;Vineyard scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_diverse_3f16c8e8-4891-52d5-9dba-3cd76afe0700.json"},{"id":"spatialvid_diverse_410beea5-b036-571e-b697-ba9423f223da","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_410beea5-b036-571e-b697-ba9423f223da.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_410beea5-b036-571e-b697-ba9423f223da.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_diverse_410beea5-b036-571e-b697-ba9423f223da.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's motion through this Rural;Traditional Village scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_diverse_410beea5-b036-571e-b697-ba9423f223da.json"},{"id":"spatialvid_diverse_48d573b9-fc79-5545-aeb3-1295cce2378e","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_48d573b9-fc79-5545-aeb3-1295cce2378e.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_48d573b9-fc79-5545-aeb3-1295cce2378e.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_diverse_48d573b9-fc79-5545-aeb3-1295cce2378e.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's motion through this Natural Landscape;Lake and Hillside View scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_diverse_48d573b9-fc79-5545-aeb3-1295cce2378e.json"},{"id":"spatialvid_diverse_4cee6efb-a71e-5769-b897-e83e48b9bc94","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_4cee6efb-a71e-5769-b897-e83e48b9bc94.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_4cee6efb-a71e-5769-b897-e83e48b9bc94.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_diverse_4cee6efb-a71e-5769-b897-e83e48b9bc94.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's motion through this Waterfront;Bridge and River scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_diverse_4cee6efb-a71e-5769-b897-e83e48b9bc94.json"},{"id":"spatialvid_diverse_50baf988-174b-57d5-b2fa-e9ab3f7919ff","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_50baf988-174b-57d5-b2fa-e9ab3f7919ff.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_50baf988-174b-57d5-b2fa-e9ab3f7919ff.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_diverse_50baf988-174b-57d5-b2fa-e9ab3f7919ff.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's motion through this Rural;Mountain Road scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_diverse_50baf988-174b-57d5-b2fa-e9ab3f7919ff.json"},{"id":"spatialvid_diverse_5143978b-d1f9-57f6-8d4e-aed5e8ee1b9b","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_5143978b-d1f9-57f6-8d4e-aed5e8ee1b9b.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_5143978b-d1f9-57f6-8d4e-aed5e8ee1b9b.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_diverse_5143978b-d1f9-57f6-8d4e-aed5e8ee1b9b.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's motion through this Waterfront;Lagoon Resort scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_diverse_5143978b-d1f9-57f6-8d4e-aed5e8ee1b9b.json"},{"id":"spatialvid_diverse_53ecfc6a-f8a6-55f4-b79c-a5622a8cf96f","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_53ecfc6a-f8a6-55f4-b79c-a5622a8cf96f.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_53ecfc6a-f8a6-55f4-b79c-a5622a8cf96f.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_diverse_53ecfc6a-f8a6-55f4-b79c-a5622a8cf96f.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"urban","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's motion through this Urban;Street Scene scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_diverse_53ecfc6a-f8a6-55f4-b79c-a5622a8cf96f.json"},{"id":"spatialvid_diverse_5c1e71b4-669f-5909-a355-bf8b0d0cb4e6","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_5c1e71b4-669f-5909-a355-bf8b0d0cb4e6.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_5c1e71b4-669f-5909-a355-bf8b0d0cb4e6.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_diverse_5c1e71b4-669f-5909-a355-bf8b0d0cb4e6.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's motion through this Waterfront;Canal Town scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_diverse_5c1e71b4-669f-5909-a355-bf8b0d0cb4e6.json"},{"id":"spatialvid_diverse_606d6091-0577-523c-9082-8f783a1b9056","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_606d6091-0577-523c-9082-8f783a1b9056.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_606d6091-0577-523c-9082-8f783a1b9056.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_diverse_606d6091-0577-523c-9082-8f783a1b9056.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's motion through this Natural Landscape;Alpine Roadway scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_diverse_606d6091-0577-523c-9082-8f783a1b9056.json"},{"id":"spatialvid_diverse_8414da34-3665-5d34-9a4f-37f9fa1b7805","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_8414da34-3665-5d34-9a4f-37f9fa1b7805.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_8414da34-3665-5d34-9a4f-37f9fa1b7805.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_diverse_8414da34-3665-5d34-9a4f-37f9fa1b7805.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"urban","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's motion through this Urban;Town with Running Route scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_diverse_8414da34-3665-5d34-9a4f-37f9fa1b7805.json"},{"id":"spatialvid_diverse_8e84afca-f440-5c8a-833f-259ab3c68258","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_8e84afca-f440-5c8a-833f-259ab3c68258.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_8e84afca-f440-5c8a-833f-259ab3c68258.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_diverse_8e84afca-f440-5c8a-833f-259ab3c68258.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's motion through this Natural Landscape;Cliff and Shoreline scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_diverse_8e84afca-f440-5c8a-833f-259ab3c68258.json"},{"id":"spatialvid_diverse_98b65e20-9d87-585c-86e8-932cb9afeac5","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_98b65e20-9d87-585c-86e8-932cb9afeac5.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_98b65e20-9d87-585c-86e8-932cb9afeac5.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_diverse_98b65e20-9d87-585c-86e8-932cb9afeac5.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's motion through this Natural Landscape;Mountain and Ocean View scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_diverse_98b65e20-9d87-585c-86e8-932cb9afeac5.json"},{"id":"spatialvid_diverse_a6b2f339-4bf3-5a11-b2ba-e4f2877a628a","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_a6b2f339-4bf3-5a11-b2ba-e4f2877a628a.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_a6b2f339-4bf3-5a11-b2ba-e4f2877a628a.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_diverse_a6b2f339-4bf3-5a11-b2ba-e4f2877a628a.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's motion through this Natural Landscape;Coastal Cliff scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_diverse_a6b2f339-4bf3-5a11-b2ba-e4f2877a628a.json"},{"id":"spatialvid_diverse_b183274d-9e89-5185-b728-371623df82b1","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_b183274d-9e89-5185-b728-371623df82b1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_b183274d-9e89-5185-b728-371623df82b1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_diverse_b183274d-9e89-5185-b728-371623df82b1.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's motion through this Natural Landscape;Mountain Train Track scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_diverse_b183274d-9e89-5185-b728-371623df82b1.json"},{"id":"spatialvid_diverse_b55979a8-a35f-5fc7-ae61-09e59581b0b2","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_b55979a8-a35f-5fc7-ae61-09e59581b0b2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_b55979a8-a35f-5fc7-ae61-09e59581b0b2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_diverse_b55979a8-a35f-5fc7-ae61-09e59581b0b2.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's motion through this Interior;Bedroom scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_diverse_b55979a8-a35f-5fc7-ae61-09e59581b0b2.json"},{"id":"spatialvid_diverse_c9bb81e8-4baa-5ca5-add4-4f82fa973ebd","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_c9bb81e8-4baa-5ca5-add4-4f82fa973ebd.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_c9bb81e8-4baa-5ca5-add4-4f82fa973ebd.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_diverse_c9bb81e8-4baa-5ca5-add4-4f82fa973ebd.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's motion through this Rural;Village Street scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_diverse_c9bb81e8-4baa-5ca5-add4-4f82fa973ebd.json"},{"id":"spatialvid_diverse_cc1338cb-3213-5017-9396-f8823ac54768","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_cc1338cb-3213-5017-9396-f8823ac54768.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_cc1338cb-3213-5017-9396-f8823ac54768.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_diverse_cc1338cb-3213-5017-9396-f8823ac54768.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's motion through this Waterfront;Beach Resort scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_diverse_cc1338cb-3213-5017-9396-f8823ac54768.json"},{"id":"spatialvid_diverse_d0354fc7-0ece-57f1-8feb-06f4a3d9ada7","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_d0354fc7-0ece-57f1-8feb-06f4a3d9ada7.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_d0354fc7-0ece-57f1-8feb-06f4a3d9ada7.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_diverse_d0354fc7-0ece-57f1-8feb-06f4a3d9ada7.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"urban","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's motion through this Urban;Street Scene scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_diverse_d0354fc7-0ece-57f1-8feb-06f4a3d9ada7.json"},{"id":"spatialvid_diverse_dc41c480-ded7-5639-8070-c0b2f756557e","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_dc41c480-ded7-5639-8070-c0b2f756557e.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_dc41c480-ded7-5639-8070-c0b2f756557e.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_diverse_dc41c480-ded7-5639-8070-c0b2f756557e.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's motion through this Rural;Running Trail scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_diverse_dc41c480-ded7-5639-8070-c0b2f756557e.json"},{"id":"spatialvid_diverse_f0643334-7ed2-5238-b372-2d40f17bae8d","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_f0643334-7ed2-5238-b372-2d40f17bae8d.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_f0643334-7ed2-5238-b372-2d40f17bae8d.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_diverse_f0643334-7ed2-5238-b372-2d40f17bae8d.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's motion through this Interior;Modern Gallery/Office Hallway scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_diverse_f0643334-7ed2-5238-b372-2d40f17bae8d.json"},{"id":"spatialvid_diverse_f8407235-60fb-556f-9ad5-921678977bf7","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_f8407235-60fb-556f-9ad5-921678977bf7.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_f8407235-60fb-556f-9ad5-921678977bf7.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_diverse_f8407235-60fb-556f-9ad5-921678977bf7.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's motion through this Waterfront;Lakeside Town scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_diverse_f8407235-60fb-556f-9ad5-921678977bf7.json"},{"id":"spatialvid_diverse_fd69983e-25be-5393-928f-531aa29e4a84","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_fd69983e-25be-5393-928f-531aa29e4a84.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_diverse_fd69983e-25be-5393-928f-531aa29e4a84.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_diverse_fd69983e-25be-5393-928f-531aa29e4a84.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's motion through this Rural;Pastoral Landscape scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_diverse_fd69983e-25be-5393-928f-531aa29e4a84.json"},{"id":"spatialvid_io_038a3521-138f-5217-978d-1212a382ae16","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_038a3521-138f-5217-978d-1212a382ae16.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_038a3521-138f-5217-978d-1212a382ae16.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_038a3521-138f-5217-978d-1212a382ae16.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Natural Landscape;Mountainous Terrain scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_038a3521-138f-5217-978d-1212a382ae16.json"},{"id":"spatialvid_io_03b8c819-3883-52bf-acf0-3396936ebe6f","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_03b8c819-3883-52bf-acf0-3396936ebe6f.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_03b8c819-3883-52bf-acf0-3396936ebe6f.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_03b8c819-3883-52bf-acf0-3396936ebe6f.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Boat Workshop scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_03b8c819-3883-52bf-acf0-3396936ebe6f.json"},{"id":"spatialvid_io_04ecfb30-e4c4-50ea-bebb-e8e54c6b52a1","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_04ecfb30-e4c4-50ea-bebb-e8e54c6b52a1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_04ecfb30-e4c4-50ea-bebb-e8e54c6b52a1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_04ecfb30-e4c4-50ea-bebb-e8e54c6b52a1.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Waterfront;Canal View scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_04ecfb30-e4c4-50ea-bebb-e8e54c6b52a1.json"},{"id":"spatialvid_io_053cccb2-afdf-53a9-ba52-c8927308b8b0","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_053cccb2-afdf-53a9-ba52-c8927308b8b0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_053cccb2-afdf-53a9-ba52-c8927308b8b0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_053cccb2-afdf-53a9-ba52-c8927308b8b0.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Home Interior scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_053cccb2-afdf-53a9-ba52-c8927308b8b0.json"},{"id":"spatialvid_io_05877c0b-208e-5611-b76b-181be732509e","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_05877c0b-208e-5611-b76b-181be732509e.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_05877c0b-208e-5611-b76b-181be732509e.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_05877c0b-208e-5611-b76b-181be732509e.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Cabin scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_05877c0b-208e-5611-b76b-181be732509e.json"},{"id":"spatialvid_io_06f5f508-83aa-5887-ad1f-7905b70f3587","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_06f5f508-83aa-5887-ad1f-7905b70f3587.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_06f5f508-83aa-5887-ad1f-7905b70f3587.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_06f5f508-83aa-5887-ad1f-7905b70f3587.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Greenhouse scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_06f5f508-83aa-5887-ad1f-7905b70f3587.json"},{"id":"spatialvid_io_08464429-198d-586c-be3f-8685a1c61921","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_08464429-198d-586c-be3f-8685a1c61921.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_08464429-198d-586c-be3f-8685a1c61921.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_08464429-198d-586c-be3f-8685a1c61921.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Home Office scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_08464429-198d-586c-be3f-8685a1c61921.json"},{"id":"spatialvid_io_0cf97ab4-ab15-51da-b99c-fd5e654b3307","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_0cf97ab4-ab15-51da-b99c-fd5e654b3307.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_0cf97ab4-ab15-51da-b99c-fd5e654b3307.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_0cf97ab4-ab15-51da-b99c-fd5e654b3307.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Game Room scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_0cf97ab4-ab15-51da-b99c-fd5e654b3307.json"},{"id":"spatialvid_io_0daaaa8e-6c24-5570-9ac8-98481f0a6cce","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_0daaaa8e-6c24-5570-9ac8-98481f0a6cce.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_0daaaa8e-6c24-5570-9ac8-98481f0a6cce.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_0daaaa8e-6c24-5570-9ac8-98481f0a6cce.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Apartment scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_0daaaa8e-6c24-5570-9ac8-98481f0a6cce.json"},{"id":"spatialvid_io_1d3478f7-28d3-5fb3-9d38-009bf257a75b","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_1d3478f7-28d3-5fb3-9d38-009bf257a75b.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_1d3478f7-28d3-5fb3-9d38-009bf257a75b.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_1d3478f7-28d3-5fb3-9d38-009bf257a75b.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Natural Landscape;Snowy Forest scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_1d3478f7-28d3-5fb3-9d38-009bf257a75b.json"},{"id":"spatialvid_io_211bed0b-af7d-56bd-9aeb-71457ff00daf","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_211bed0b-af7d-56bd-9aeb-71457ff00daf.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_211bed0b-af7d-56bd-9aeb-71457ff00daf.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_211bed0b-af7d-56bd-9aeb-71457ff00daf.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Cafe scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_211bed0b-af7d-56bd-9aeb-71457ff00daf.json"},{"id":"spatialvid_io_24dcbe34-cd45-5242-b1a9-fb200fb30f55","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_24dcbe34-cd45-5242-b1a9-fb200fb30f55.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_24dcbe34-cd45-5242-b1a9-fb200fb30f55.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_24dcbe34-cd45-5242-b1a9-fb200fb30f55.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Courtyard scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_24dcbe34-cd45-5242-b1a9-fb200fb30f55.json"},{"id":"spatialvid_io_24e78263-72e0-5a64-b78e-8716ca6e76e5","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_24e78263-72e0-5a64-b78e-8716ca6e76e5.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_24e78263-72e0-5a64-b78e-8716ca6e76e5.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_24e78263-72e0-5a64-b78e-8716ca6e76e5.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Natural Landscape;Ruins scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_24e78263-72e0-5a64-b78e-8716ca6e76e5.json"},{"id":"spatialvid_io_27fa731c-f581-5526-bba2-e3f199ae1724","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_27fa731c-f581-5526-bba2-e3f199ae1724.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_27fa731c-f581-5526-bba2-e3f199ae1724.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_27fa731c-f581-5526-bba2-e3f199ae1724.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Antique Shop scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_27fa731c-f581-5526-bba2-e3f199ae1724.json"},{"id":"spatialvid_io_28837ea2-2ae3-56ff-bdd7-b0fcdb2b8789","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_28837ea2-2ae3-56ff-bdd7-b0fcdb2b8789.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_28837ea2-2ae3-56ff-bdd7-b0fcdb2b8789.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_28837ea2-2ae3-56ff-bdd7-b0fcdb2b8789.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Airport Terminal scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_28837ea2-2ae3-56ff-bdd7-b0fcdb2b8789.json"},{"id":"spatialvid_io_2885e2b2-eefb-5e1d-bdee-421435b296d4","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_2885e2b2-eefb-5e1d-bdee-421435b296d4.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_2885e2b2-eefb-5e1d-bdee-421435b296d4.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_2885e2b2-eefb-5e1d-bdee-421435b296d4.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Bedroom scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_2885e2b2-eefb-5e1d-bdee-421435b296d4.json"},{"id":"spatialvid_io_2be1b371-2180-5d2b-a158-7b7c8ae1efcf","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_2be1b371-2180-5d2b-a158-7b7c8ae1efcf.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_2be1b371-2180-5d2b-a158-7b7c8ae1efcf.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_2be1b371-2180-5d2b-a158-7b7c8ae1efcf.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Rural;Traditional Japanese Village scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_2be1b371-2180-5d2b-a158-7b7c8ae1efcf.json"},{"id":"spatialvid_io_2d420bd4-7bca-5be3-adc9-88b12cb6ccdb","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_2d420bd4-7bca-5be3-adc9-88b12cb6ccdb.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_2d420bd4-7bca-5be3-adc9-88b12cb6ccdb.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_2d420bd4-7bca-5be3-adc9-88b12cb6ccdb.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Dining Room scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_2d420bd4-7bca-5be3-adc9-88b12cb6ccdb.json"},{"id":"spatialvid_io_3064b819-de06-5663-9c50-b03332fe7223","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_3064b819-de06-5663-9c50-b03332fe7223.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_3064b819-de06-5663-9c50-b03332fe7223.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_3064b819-de06-5663-9c50-b03332fe7223.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Natural Landscape;Forest Path scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_3064b819-de06-5663-9c50-b03332fe7223.json"},{"id":"spatialvid_io_30ea6273-fa9a-5710-bc3d-4e2c22f48cf9","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_30ea6273-fa9a-5710-bc3d-4e2c22f48cf9.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_30ea6273-fa9a-5710-bc3d-4e2c22f48cf9.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_30ea6273-fa9a-5710-bc3d-4e2c22f48cf9.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Rural;Country Road scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_30ea6273-fa9a-5710-bc3d-4e2c22f48cf9.json"},{"id":"spatialvid_io_321c2c12-2147-5ddf-b439-a4650f50a73c","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_321c2c12-2147-5ddf-b439-a4650f50a73c.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_321c2c12-2147-5ddf-b439-a4650f50a73c.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_321c2c12-2147-5ddf-b439-a4650f50a73c.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Bathroom and Bedroom scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_321c2c12-2147-5ddf-b439-a4650f50a73c.json"},{"id":"spatialvid_io_3548df95-d539-5ddc-88b0-9a5dd89c8661","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_3548df95-d539-5ddc-88b0-9a5dd89c8661.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_3548df95-d539-5ddc-88b0-9a5dd89c8661.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_3548df95-d539-5ddc-88b0-9a5dd89c8661.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Natural Landscape;Alpine Terrain scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_3548df95-d539-5ddc-88b0-9a5dd89c8661.json"},{"id":"spatialvid_io_38e6dd84-e8d6-5035-b136-1c47e9bdb793","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_38e6dd84-e8d6-5035-b136-1c47e9bdb793.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_38e6dd84-e8d6-5035-b136-1c47e9bdb793.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_38e6dd84-e8d6-5035-b136-1c47e9bdb793.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Bedroom and Bathroom scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_38e6dd84-e8d6-5035-b136-1c47e9bdb793.json"},{"id":"spatialvid_io_3a38ba16-9b2f-5802-b77c-277d37d44022","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_3a38ba16-9b2f-5802-b77c-277d37d44022.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_3a38ba16-9b2f-5802-b77c-277d37d44022.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_3a38ba16-9b2f-5802-b77c-277d37d44022.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Rural;Mountain Village scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_3a38ba16-9b2f-5802-b77c-277d37d44022.json"},{"id":"spatialvid_io_3a65088d-8bd1-57ca-8619-ca7d5f4141e6","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_3a65088d-8bd1-57ca-8619-ca7d5f4141e6.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_3a65088d-8bd1-57ca-8619-ca7d5f4141e6.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_3a65088d-8bd1-57ca-8619-ca7d5f4141e6.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Kitchen scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_3a65088d-8bd1-57ca-8619-ca7d5f4141e6.json"},{"id":"spatialvid_io_3aee0b14-3339-56f9-bde5-f1bb97225b93","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_3aee0b14-3339-56f9-bde5-f1bb97225b93.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_3aee0b14-3339-56f9-bde5-f1bb97225b93.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_3aee0b14-3339-56f9-bde5-f1bb97225b93.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Boat Cabin scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_3aee0b14-3339-56f9-bde5-f1bb97225b93.json"},{"id":"spatialvid_io_3b196645-27b0-5937-befd-d13ed02b81c1","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_3b196645-27b0-5937-befd-d13ed02b81c1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_3b196645-27b0-5937-befd-d13ed02b81c1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_3b196645-27b0-5937-befd-d13ed02b81c1.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Art Gallery scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_3b196645-27b0-5937-befd-d13ed02b81c1.json"},{"id":"spatialvid_io_3bb5152d-3eb7-571d-8819-857904594ce9","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_3bb5152d-3eb7-571d-8819-857904594ce9.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_3bb5152d-3eb7-571d-8819-857904594ce9.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_3bb5152d-3eb7-571d-8819-857904594ce9.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Natural Landscape;Riverbank scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_3bb5152d-3eb7-571d-8819-857904594ce9.json"},{"id":"spatialvid_io_3c7c8e9d-6e32-52e6-8cba-3244a33c0541","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_3c7c8e9d-6e32-52e6-8cba-3244a33c0541.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_3c7c8e9d-6e32-52e6-8cba-3244a33c0541.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_3c7c8e9d-6e32-52e6-8cba-3244a33c0541.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Open-Concept Kitchen and Living Area scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_3c7c8e9d-6e32-52e6-8cba-3244a33c0541.json"},{"id":"spatialvid_io_3ff4b387-1688-5a20-8ad5-794f677fde88","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_3ff4b387-1688-5a20-8ad5-794f677fde88.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_3ff4b387-1688-5a20-8ad5-794f677fde88.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_3ff4b387-1688-5a20-8ad5-794f677fde88.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Natural Landscape;Forest Road scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_3ff4b387-1688-5a20-8ad5-794f677fde88.json"},{"id":"spatialvid_io_4084031e-4b09-58ad-a24e-76f5c606ece4","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_4084031e-4b09-58ad-a24e-76f5c606ece4.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_4084031e-4b09-58ad-a24e-76f5c606ece4.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_4084031e-4b09-58ad-a24e-76f5c606ece4.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Department Store scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_4084031e-4b09-58ad-a24e-76f5c606ece4.json"},{"id":"spatialvid_io_41179fca-27be-58a0-a699-33cc9e599717","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_41179fca-27be-58a0-a699-33cc9e599717.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_41179fca-27be-58a0-a699-33cc9e599717.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_41179fca-27be-58a0-a699-33cc9e599717.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Modern Living Room scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_41179fca-27be-58a0-a699-33cc9e599717.json"},{"id":"spatialvid_io_4163a3c2-15af-563b-bb46-093748305173","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_4163a3c2-15af-563b-bb46-093748305173.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_4163a3c2-15af-563b-bb46-093748305173.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_4163a3c2-15af-563b-bb46-093748305173.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Modern Home scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_4163a3c2-15af-563b-bb46-093748305173.json"},{"id":"spatialvid_io_42137d1d-8c65-5057-badb-f2782962c5c5","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_42137d1d-8c65-5057-badb-f2782962c5c5.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_42137d1d-8c65-5057-badb-f2782962c5c5.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_42137d1d-8c65-5057-badb-f2782962c5c5.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Natural Landscape;Enchanted Forest scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_42137d1d-8c65-5057-badb-f2782962c5c5.json"},{"id":"spatialvid_io_43245015-a471-5f4f-8040-315e0122936e","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_43245015-a471-5f4f-8040-315e0122936e.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_43245015-a471-5f4f-8040-315e0122936e.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_43245015-a471-5f4f-8040-315e0122936e.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Rural;Traditional Village scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_43245015-a471-5f4f-8040-315e0122936e.json"},{"id":"spatialvid_io_451e3077-902d-5566-9da8-2f0308199fa4","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_451e3077-902d-5566-9da8-2f0308199fa4.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_451e3077-902d-5566-9da8-2f0308199fa4.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_451e3077-902d-5566-9da8-2f0308199fa4.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Natural Landscape;Mountain Landscape scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_451e3077-902d-5566-9da8-2f0308199fa4.json"},{"id":"spatialvid_io_482f1933-6d70-5dfc-b868-c47d8f7db675","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_482f1933-6d70-5dfc-b868-c47d8f7db675.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_482f1933-6d70-5dfc-b868-c47d8f7db675.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_482f1933-6d70-5dfc-b868-c47d8f7db675.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Rural;Village Road scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_482f1933-6d70-5dfc-b868-c47d8f7db675.json"},{"id":"spatialvid_io_5277abd0-72b8-5bd1-aabe-a448ea3aa1ea","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_5277abd0-72b8-5bd1-aabe-a448ea3aa1ea.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_5277abd0-72b8-5bd1-aabe-a448ea3aa1ea.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_5277abd0-72b8-5bd1-aabe-a448ea3aa1ea.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Waterfront;Harbor scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_5277abd0-72b8-5bd1-aabe-a448ea3aa1ea.json"},{"id":"spatialvid_io_53a9ec72-96a0-5425-87b0-1e959fa98334","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_53a9ec72-96a0-5425-87b0-1e959fa98334.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_53a9ec72-96a0-5425-87b0-1e959fa98334.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_53a9ec72-96a0-5425-87b0-1e959fa98334.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Open-Concept Kitchen and Living Space scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_53a9ec72-96a0-5425-87b0-1e959fa98334.json"},{"id":"spatialvid_io_559575e0-6428-5ca4-ad3f-1c3878f973c4","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_559575e0-6428-5ca4-ad3f-1c3878f973c4.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_559575e0-6428-5ca4-ad3f-1c3878f973c4.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_559575e0-6428-5ca4-ad3f-1c3878f973c4.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Natural Landscape;Dense Forest scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_559575e0-6428-5ca4-ad3f-1c3878f973c4.json"},{"id":"spatialvid_io_581710fe-c4cd-5f67-a826-22369e0a80a0","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_581710fe-c4cd-5f67-a826-22369e0a80a0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_581710fe-c4cd-5f67-a826-22369e0a80a0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_581710fe-c4cd-5f67-a826-22369e0a80a0.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Boat Inspection Area scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_581710fe-c4cd-5f67-a826-22369e0a80a0.json"},{"id":"spatialvid_io_5c3b7502-0d90-52fc-8f5c-22aa5c28f3d1","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_5c3b7502-0d90-52fc-8f5c-22aa5c28f3d1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_5c3b7502-0d90-52fc-8f5c-22aa5c28f3d1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_5c3b7502-0d90-52fc-8f5c-22aa5c28f3d1.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Rural;Quaint Village scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_5c3b7502-0d90-52fc-8f5c-22aa5c28f3d1.json"},{"id":"spatialvid_io_5fcc425c-a71a-54f6-ab73-b0ed84cf108d","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_5fcc425c-a71a-54f6-ab73-b0ed84cf108d.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_5fcc425c-a71a-54f6-ab73-b0ed84cf108d.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_5fcc425c-a71a-54f6-ab73-b0ed84cf108d.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Hallway scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_5fcc425c-a71a-54f6-ab73-b0ed84cf108d.json"},{"id":"spatialvid_io_61cf32de-5142-53a2-a4cc-67f02e22de90","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_61cf32de-5142-53a2-a4cc-67f02e22de90.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_61cf32de-5142-53a2-a4cc-67f02e22de90.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_61cf32de-5142-53a2-a4cc-67f02e22de90.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Living Room scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_61cf32de-5142-53a2-a4cc-67f02e22de90.json"},{"id":"spatialvid_io_64513cb1-0ccd-5810-afc0-5618ca33fddf","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_64513cb1-0ccd-5810-afc0-5618ca33fddf.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_64513cb1-0ccd-5810-afc0-5618ca33fddf.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_64513cb1-0ccd-5810-afc0-5618ca33fddf.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Natural Landscape;Mountain Pass scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_64513cb1-0ccd-5810-afc0-5618ca33fddf.json"},{"id":"spatialvid_io_663ba965-ce2c-59f1-9416-876388f66d5c","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_663ba965-ce2c-59f1-9416-876388f66d5c.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_663ba965-ce2c-59f1-9416-876388f66d5c.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_663ba965-ce2c-59f1-9416-876388f66d5c.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Natural Landscape;Mountain Lake scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_663ba965-ce2c-59f1-9416-876388f66d5c.json"},{"id":"spatialvid_io_6812037a-227e-55f8-9c86-59c345f424d3","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_6812037a-227e-55f8-9c86-59c345f424d3.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_6812037a-227e-55f8-9c86-59c345f424d3.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_6812037a-227e-55f8-9c86-59c345f424d3.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Dressing Room scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_6812037a-227e-55f8-9c86-59c345f424d3.json"},{"id":"spatialvid_io_69bc3b06-8311-595e-8d4d-fcaeb8e772b7","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_69bc3b06-8311-595e-8d4d-fcaeb8e772b7.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_69bc3b06-8311-595e-8d4d-fcaeb8e772b7.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_69bc3b06-8311-595e-8d4d-fcaeb8e772b7.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Natural Landscape;Mountain Range scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_69bc3b06-8311-595e-8d4d-fcaeb8e772b7.json"},{"id":"spatialvid_io_6ed0396f-ebe9-5fdc-96e9-307e141812cd","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_6ed0396f-ebe9-5fdc-96e9-307e141812cd.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_6ed0396f-ebe9-5fdc-96e9-307e141812cd.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_6ed0396f-ebe9-5fdc-96e9-307e141812cd.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Natural Landscape;Redwood Forest scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_6ed0396f-ebe9-5fdc-96e9-307e141812cd.json"},{"id":"spatialvid_io_733aa99a-6c36-53f1-a875-5c07eb5bf3a8","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_733aa99a-6c36-53f1-a875-5c07eb5bf3a8.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_733aa99a-6c36-53f1-a875-5c07eb5bf3a8.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_733aa99a-6c36-53f1-a875-5c07eb5bf3a8.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Open-Concept Kitchen and Living Room scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_733aa99a-6c36-53f1-a875-5c07eb5bf3a8.json"},{"id":"spatialvid_io_75992096-cfc5-5d40-ac1c-fee23a6f1450","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_75992096-cfc5-5d40-ac1c-fee23a6f1450.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_75992096-cfc5-5d40-ac1c-fee23a6f1450.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_75992096-cfc5-5d40-ac1c-fee23a6f1450.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Natural Landscape;Lakeside View scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_75992096-cfc5-5d40-ac1c-fee23a6f1450.json"},{"id":"spatialvid_io_77105d5b-95ce-5e51-8352-bc8dae0b8915","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_77105d5b-95ce-5e51-8352-bc8dae0b8915.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_77105d5b-95ce-5e51-8352-bc8dae0b8915.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_77105d5b-95ce-5e51-8352-bc8dae0b8915.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Natural Landscape;Waterfall scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_77105d5b-95ce-5e51-8352-bc8dae0b8915.json"},{"id":"spatialvid_io_77c72425-109b-5290-9f08-1ff1a2122e86","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_77c72425-109b-5290-9f08-1ff1a2122e86.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_77c72425-109b-5290-9f08-1ff1a2122e86.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_77c72425-109b-5290-9f08-1ff1a2122e86.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Bathroom and Closet scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_77c72425-109b-5290-9f08-1ff1a2122e86.json"},{"id":"spatialvid_io_7b650255-d2f6-5f48-ab5d-e7ebf9635eeb","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_7b650255-d2f6-5f48-ab5d-e7ebf9635eeb.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_7b650255-d2f6-5f48-ab5d-e7ebf9635eeb.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_7b650255-d2f6-5f48-ab5d-e7ebf9635eeb.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Control Room scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_7b650255-d2f6-5f48-ab5d-e7ebf9635eeb.json"},{"id":"spatialvid_io_7e691100-38bf-5af1-a2ca-ddc686a92253","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_7e691100-38bf-5af1-a2ca-ddc686a92253.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_7e691100-38bf-5af1-a2ca-ddc686a92253.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_7e691100-38bf-5af1-a2ca-ddc686a92253.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Laundry Room scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_7e691100-38bf-5af1-a2ca-ddc686a92253.json"},{"id":"spatialvid_io_82906d09-3e08-5eb1-b083-85343766aaef","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_82906d09-3e08-5eb1-b083-85343766aaef.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_82906d09-3e08-5eb1-b083-85343766aaef.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_82906d09-3e08-5eb1-b083-85343766aaef.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Bathroom scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_82906d09-3e08-5eb1-b083-85343766aaef.json"},{"id":"spatialvid_io_85d2f58b-28b1-532c-bd6b-e5f8067867ee","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_85d2f58b-28b1-532c-bd6b-e5f8067867ee.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_85d2f58b-28b1-532c-bd6b-e5f8067867ee.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_85d2f58b-28b1-532c-bd6b-e5f8067867ee.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Natural Landscape;Canyon scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_85d2f58b-28b1-532c-bd6b-e5f8067867ee.json"},{"id":"spatialvid_io_89c977b2-fd78-502a-a3e7-4d37cbfd2af9","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_89c977b2-fd78-502a-a3e7-4d37cbfd2af9.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_89c977b2-fd78-502a-a3e7-4d37cbfd2af9.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_89c977b2-fd78-502a-a3e7-4d37cbfd2af9.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Walk-in Closet scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_89c977b2-fd78-502a-a3e7-4d37cbfd2af9.json"},{"id":"spatialvid_io_8ba7c701-a475-5e7c-a973-d97b6665ef75","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_8ba7c701-a475-5e7c-a973-d97b6665ef75.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_8ba7c701-a475-5e7c-a973-d97b6665ef75.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_8ba7c701-a475-5e7c-a973-d97b6665ef75.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Modern Kitchen scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_8ba7c701-a475-5e7c-a973-d97b6665ef75.json"},{"id":"spatialvid_io_8bcbcbe6-be23-52da-b826-d91c634f352f","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_8bcbcbe6-be23-52da-b826-d91c634f352f.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_8bcbcbe6-be23-52da-b826-d91c634f352f.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_8bcbcbe6-be23-52da-b826-d91c634f352f.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Natural Landscape;Forest Trail scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_8bcbcbe6-be23-52da-b826-d91c634f352f.json"},{"id":"spatialvid_io_8ce64844-f8bf-5c42-a14c-23dd2d98cdec","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_8ce64844-f8bf-5c42-a14c-23dd2d98cdec.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_8ce64844-f8bf-5c42-a14c-23dd2d98cdec.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_8ce64844-f8bf-5c42-a14c-23dd2d98cdec.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Church scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_8ce64844-f8bf-5c42-a14c-23dd2d98cdec.json"},{"id":"spatialvid_io_9072b719-779c-580d-983c-c404ad4b40ca","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_9072b719-779c-580d-983c-c404ad4b40ca.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_9072b719-779c-580d-983c-c404ad4b40ca.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_9072b719-779c-580d-983c-c404ad4b40ca.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Decorated Room scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_9072b719-779c-580d-983c-c404ad4b40ca.json"},{"id":"spatialvid_io_9122de36-4620-5c58-ae2a-897a7e2404de","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_9122de36-4620-5c58-ae2a-897a7e2404de.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_9122de36-4620-5c58-ae2a-897a7e2404de.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_9122de36-4620-5c58-ae2a-897a7e2404de.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Rural;Alpine Village scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_9122de36-4620-5c58-ae2a-897a7e2404de.json"},{"id":"spatialvid_io_93b2c4f4-6d8c-5a9c-a967-e75d231a1a46","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_93b2c4f4-6d8c-5a9c-a967-e75d231a1a46.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_93b2c4f4-6d8c-5a9c-a967-e75d231a1a46.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_93b2c4f4-6d8c-5a9c-a967-e75d231a1a46.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Office/Study scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_93b2c4f4-6d8c-5a9c-a967-e75d231a1a46.json"},{"id":"spatialvid_io_94b9a6d3-2d78-5f7f-b332-78dc21bff039","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_94b9a6d3-2d78-5f7f-b332-78dc21bff039.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_94b9a6d3-2d78-5f7f-b332-78dc21bff039.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_94b9a6d3-2d78-5f7f-b332-78dc21bff039.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Ancient Corridor scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_94b9a6d3-2d78-5f7f-b332-78dc21bff039.json"},{"id":"spatialvid_io_98a9afdb-cf81-5e75-9596-157fc8d7dc0d","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_98a9afdb-cf81-5e75-9596-157fc8d7dc0d.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_98a9afdb-cf81-5e75-9596-157fc8d7dc0d.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_98a9afdb-cf81-5e75-9596-157fc8d7dc0d.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Waterfront;Boat Ride scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_98a9afdb-cf81-5e75-9596-157fc8d7dc0d.json"},{"id":"spatialvid_io_98b6d969-274b-50e9-91b2-0d708862dd4b","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_98b6d969-274b-50e9-91b2-0d708862dd4b.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_98b6d969-274b-50e9-91b2-0d708862dd4b.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_98b6d969-274b-50e9-91b2-0d708862dd4b.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Rural;Countryside Road scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_98b6d969-274b-50e9-91b2-0d708862dd4b.json"},{"id":"spatialvid_io_9ef0f29f-2965-5264-962e-8b3fa7b58b94","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_9ef0f29f-2965-5264-962e-8b3fa7b58b94.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_9ef0f29f-2965-5264-962e-8b3fa7b58b94.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_9ef0f29f-2965-5264-962e-8b3fa7b58b94.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Construction Site scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_9ef0f29f-2965-5264-962e-8b3fa7b58b94.json"},{"id":"spatialvid_io_a4e96ed0-8e2f-5c17-ba01-6f0ee9097f8f","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_a4e96ed0-8e2f-5c17-ba01-6f0ee9097f8f.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_a4e96ed0-8e2f-5c17-ba01-6f0ee9097f8f.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_a4e96ed0-8e2f-5c17-ba01-6f0ee9097f8f.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Natural Landscape;Forest scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_a4e96ed0-8e2f-5c17-ba01-6f0ee9097f8f.json"},{"id":"spatialvid_io_a91a559d-cf75-5557-a6ba-6af526644a13","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_a91a559d-cf75-5557-a6ba-6af526644a13.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_a91a559d-cf75-5557-a6ba-6af526644a13.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_a91a559d-cf75-5557-a6ba-6af526644a13.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Natural Landscape;Alpine Valley scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_a91a559d-cf75-5557-a6ba-6af526644a13.json"},{"id":"spatialvid_io_aac387bd-87ba-5e4c-91e4-6d4c9d2ee015","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_aac387bd-87ba-5e4c-91e4-6d4c9d2ee015.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_aac387bd-87ba-5e4c-91e4-6d4c9d2ee015.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_aac387bd-87ba-5e4c-91e4-6d4c9d2ee015.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Natural Landscape;Winter Forest scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_aac387bd-87ba-5e4c-91e4-6d4c9d2ee015.json"},{"id":"spatialvid_io_b6656ec5-28a5-5234-8e5a-9fa61f9de012","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_b6656ec5-28a5-5234-8e5a-9fa61f9de012.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_b6656ec5-28a5-5234-8e5a-9fa61f9de012.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_b6656ec5-28a5-5234-8e5a-9fa61f9de012.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Bookstore scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_b6656ec5-28a5-5234-8e5a-9fa61f9de012.json"},{"id":"spatialvid_io_bb1271d1-29a2-5cdd-8b94-7e422cb5662e","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_bb1271d1-29a2-5cdd-8b94-7e422cb5662e.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_bb1271d1-29a2-5cdd-8b94-7e422cb5662e.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_bb1271d1-29a2-5cdd-8b94-7e422cb5662e.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Natural Landscape;Japanese Garden scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_bb1271d1-29a2-5cdd-8b94-7e422cb5662e.json"},{"id":"spatialvid_io_bb12e2e1-9c39-50a2-a582-c56b2a30fbce","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_bb12e2e1-9c39-50a2-a582-c56b2a30fbce.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_bb12e2e1-9c39-50a2-a582-c56b2a30fbce.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_bb12e2e1-9c39-50a2-a582-c56b2a30fbce.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Rural;Countryside Landscape scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_bb12e2e1-9c39-50a2-a582-c56b2a30fbce.json"},{"id":"spatialvid_io_bb32de23-3e7b-5a91-8a43-c59adff87c72","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_bb32de23-3e7b-5a91-8a43-c59adff87c72.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_bb32de23-3e7b-5a91-8a43-c59adff87c72.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_bb32de23-3e7b-5a91-8a43-c59adff87c72.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Open-Concept Home scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_bb32de23-3e7b-5a91-8a43-c59adff87c72.json"},{"id":"spatialvid_io_bbb15518-0d4a-5c00-96dc-801e4b534bb8","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_bbb15518-0d4a-5c00-96dc-801e4b534bb8.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_bbb15518-0d4a-5c00-96dc-801e4b534bb8.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_bbb15518-0d4a-5c00-96dc-801e4b534bb8.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Natural Landscape;Forest Floor scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_bbb15518-0d4a-5c00-96dc-801e4b534bb8.json"},{"id":"spatialvid_io_bdb4442f-b451-5646-9b59-80f47117360a","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_bdb4442f-b451-5646-9b59-80f47117360a.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_bdb4442f-b451-5646-9b59-80f47117360a.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_bdb4442f-b451-5646-9b59-80f47117360a.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Natural Landscape;Mountain Valley scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_bdb4442f-b451-5646-9b59-80f47117360a.json"},{"id":"spatialvid_io_bec5cc20-9e97-5222-9fa1-10faa4f559ce","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_bec5cc20-9e97-5222-9fa1-10faa4f559ce.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_bec5cc20-9e97-5222-9fa1-10faa4f559ce.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_bec5cc20-9e97-5222-9fa1-10faa4f559ce.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Entryway scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_bec5cc20-9e97-5222-9fa1-10faa4f559ce.json"},{"id":"spatialvid_io_bfb5a449-ee16-56e9-b325-734a9e6ff15b","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_bfb5a449-ee16-56e9-b325-734a9e6ff15b.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_bfb5a449-ee16-56e9-b325-734a9e6ff15b.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_bfb5a449-ee16-56e9-b325-734a9e6ff15b.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Dining Area scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_bfb5a449-ee16-56e9-b325-734a9e6ff15b.json"},{"id":"spatialvid_io_c0222a8f-af37-5f6b-aa93-2a3fae604128","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_c0222a8f-af37-5f6b-aa93-2a3fae604128.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_c0222a8f-af37-5f6b-aa93-2a3fae604128.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_c0222a8f-af37-5f6b-aa93-2a3fae604128.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Rural;Village Scene scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_c0222a8f-af37-5f6b-aa93-2a3fae604128.json"},{"id":"spatialvid_io_c734c9d2-d3ed-53e9-a336-1ab545088dfd","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_c734c9d2-d3ed-53e9-a336-1ab545088dfd.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_c734c9d2-d3ed-53e9-a336-1ab545088dfd.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_c734c9d2-d3ed-53e9-a336-1ab545088dfd.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Natural Landscape;Pastoral scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_c734c9d2-d3ed-53e9-a336-1ab545088dfd.json"},{"id":"spatialvid_io_ca17e00e-6118-52a6-9658-34af2aba16ad","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_ca17e00e-6118-52a6-9658-34af2aba16ad.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_ca17e00e-6118-52a6-9658-34af2aba16ad.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_ca17e00e-6118-52a6-9658-34af2aba16ad.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Natural Landscape;Mountain Road scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_ca17e00e-6118-52a6-9658-34af2aba16ad.json"},{"id":"spatialvid_io_d5f94ad6-a20b-5717-b628-cc720cd412e9","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_d5f94ad6-a20b-5717-b628-cc720cd412e9.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_d5f94ad6-a20b-5717-b628-cc720cd412e9.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_d5f94ad6-a20b-5717-b628-cc720cd412e9.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Rural;Backyard scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_d5f94ad6-a20b-5717-b628-cc720cd412e9.json"},{"id":"spatialvid_io_d6f885b6-e010-520e-812f-047cb83f8cf2","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_d6f885b6-e010-520e-812f-047cb83f8cf2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_d6f885b6-e010-520e-812f-047cb83f8cf2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_d6f885b6-e010-520e-812f-047cb83f8cf2.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Rural;Cottage Garden scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_d6f885b6-e010-520e-812f-047cb83f8cf2.json"},{"id":"spatialvid_io_d75c3a4b-67bd-5234-a16f-1137b016f4bd","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_d75c3a4b-67bd-5234-a16f-1137b016f4bd.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_d75c3a4b-67bd-5234-a16f-1137b016f4bd.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_d75c3a4b-67bd-5234-a16f-1137b016f4bd.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Open-Concept Living Space scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_d75c3a4b-67bd-5234-a16f-1137b016f4bd.json"},{"id":"spatialvid_io_e337845b-1717-553e-9b25-f12b9b736784","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_e337845b-1717-553e-9b25-f12b9b736784.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_e337845b-1717-553e-9b25-f12b9b736784.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_e337845b-1717-553e-9b25-f12b9b736784.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Natural Landscape;Park scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_e337845b-1717-553e-9b25-f12b9b736784.json"},{"id":"spatialvid_io_e4745860-4f99-51d3-a6c9-5b26c1b0b27b","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_e4745860-4f99-51d3-a6c9-5b26c1b0b27b.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_e4745860-4f99-51d3-a6c9-5b26c1b0b27b.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_e4745860-4f99-51d3-a6c9-5b26c1b0b27b.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Luxury Apartment scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_e4745860-4f99-51d3-a6c9-5b26c1b0b27b.json"},{"id":"spatialvid_io_e4e89995-ea34-5363-85fe-457f30655bcf","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_e4e89995-ea34-5363-85fe-457f30655bcf.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_e4e89995-ea34-5363-85fe-457f30655bcf.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_e4e89995-ea34-5363-85fe-457f30655bcf.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Rural;Village scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_e4e89995-ea34-5363-85fe-457f30655bcf.json"},{"id":"spatialvid_io_ea14272f-1356-5aa2-b444-6b3f4aa81dd4","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_ea14272f-1356-5aa2-b444-6b3f4aa81dd4.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_ea14272f-1356-5aa2-b444-6b3f4aa81dd4.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_ea14272f-1356-5aa2-b444-6b3f4aa81dd4.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Natural Landscape;Underwater Reef scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_ea14272f-1356-5aa2-b444-6b3f4aa81dd4.json"},{"id":"spatialvid_io_eba31575-91e6-57c6-bccc-437799dda5fe","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_eba31575-91e6-57c6-bccc-437799dda5fe.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_eba31575-91e6-57c6-bccc-437799dda5fe.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_eba31575-91e6-57c6-bccc-437799dda5fe.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Natural Landscape;Mountain Trail scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_eba31575-91e6-57c6-bccc-437799dda5fe.json"},{"id":"spatialvid_io_f1c59884-a937-555b-b468-54b73b3cb98c","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_f1c59884-a937-555b-b468-54b73b3cb98c.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_f1c59884-a937-555b-b468-54b73b3cb98c.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_f1c59884-a937-555b-b468-54b73b3cb98c.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Rural;Village Landscape scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_f1c59884-a937-555b-b468-54b73b3cb98c.json"},{"id":"spatialvid_io_f445ccd1-2b9b-5cad-a941-5592cd1d7c9f","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_f445ccd1-2b9b-5cad-a941-5592cd1d7c9f.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_f445ccd1-2b9b-5cad-a941-5592cd1d7c9f.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_f445ccd1-2b9b-5cad-a941-5592cd1d7c9f.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Library scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_f445ccd1-2b9b-5cad-a941-5592cd1d7c9f.json"},{"id":"spatialvid_io_f5d9bd2b-70d0-5edf-a77b-74c23c76664e","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_f5d9bd2b-70d0-5edf-a77b-74c23c76664e.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_f5d9bd2b-70d0-5edf-a77b-74c23c76664e.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_f5d9bd2b-70d0-5edf-a77b-74c23c76664e.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Luxury Home scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_f5d9bd2b-70d0-5edf-a77b-74c23c76664e.json"},{"id":"spatialvid_io_f71957c5-cb34-570b-9137-5ec2aff0a9ee","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_f71957c5-cb34-570b-9137-5ec2aff0a9ee.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_f71957c5-cb34-570b-9137-5ec2aff0a9ee.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_f71957c5-cb34-570b-9137-5ec2aff0a9ee.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Rural;Village Street scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_f71957c5-cb34-570b-9137-5ec2aff0a9ee.json"},{"id":"spatialvid_io_f74f4ace-0e4a-5f07-93cb-37a102755f89","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_f74f4ace-0e4a-5f07-93cb-37a102755f89.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_f74f4ace-0e4a-5f07-93cb-37a102755f89.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_f74f4ace-0e4a-5f07-93cb-37a102755f89.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Basement Living Room scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_f74f4ace-0e4a-5f07-93cb-37a102755f89.json"},{"id":"spatialvid_io_f9fb4607-09d0-56ce-8ba1-e2b29f4324bd","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_f9fb4607-09d0-56ce-8ba1-e2b29f4324bd.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_f9fb4607-09d0-56ce-8ba1-e2b29f4324bd.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_f9fb4607-09d0-56ce-8ba1-e2b29f4324bd.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Workshop scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_f9fb4607-09d0-56ce-8ba1-e2b29f4324bd.json"},{"id":"spatialvid_io_fbcb57ec-fc52-5897-8e25-e0ca1d7015f6","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_fbcb57ec-fc52-5897-8e25-e0ca1d7015f6.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_fbcb57ec-fc52-5897-8e25-e0ca1d7015f6.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_fbcb57ec-fc52-5897-8e25-e0ca1d7015f6.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Rural;Outdoor Patio scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_fbcb57ec-fc52-5897-8e25-e0ca1d7015f6.json"},{"id":"spatialvid_io_fd73e76f-030e-5e10-a01c-7ef1130d36ae","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_fd73e76f-030e-5e10-a01c-7ef1130d36ae.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_fd73e76f-030e-5e10-a01c-7ef1130d36ae.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_fd73e76f-030e-5e10-a01c-7ef1130d36ae.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Interior;Kitchen and Dining Area scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_fd73e76f-030e-5e10-a01c-7ef1130d36ae.json"},{"id":"spatialvid_io_fe018429-8649-5d1a-bd9b-86eab0da90bb","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_fe018429-8649-5d1a-bd9b-86eab0da90bb.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_fe018429-8649-5d1a-bd9b-86eab0da90bb.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_fe018429-8649-5d1a-bd9b-86eab0da90bb.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Natural Landscape;Mountain Vista scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_fe018429-8649-5d1a-bd9b-86eab0da90bb.json"},{"id":"spatialvid_io_fe8f2731-b367-579b-84a7-0a9d55746a4c","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_fe8f2731-b367-579b-84a7-0a9d55746a4c.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/spatialvid_io_fe8f2731-b367-579b-84a7-0a9d55746a4c.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/spatialvid_io_fe8f2731-b367-579b-84a7-0a9d55746a4c.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's trajectory through this Rural;Mountain Road scene?","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/spatialvid_io_fe8f2731-b367-579b-84a7-0a9d55746a4c.json"},{"id":"spatialvid_sample1","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/sample1.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry, Visibility and Occlusion","perspective":"Exocentric","caption":"The camera glides smoothly to the right, maintaining a steady forward motion as it reveals a vast landscape. Its path is consistent, with no abrupt changes—only a smooth, continuous translation that emphasizes the expansive scene ahead.","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/sample1.json"},{"id":"spatialvid_sample10","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample10.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample10.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/sample10.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Exocentric","caption":"The camera glides steadily forward along the winding road, with a consistent shift to the left as it follows the path. The movement is smooth and continuous, emphasizing the vast landscape unfolding ahead.","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/sample10.json"},{"id":"spatialvid_sample11","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample11.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample11.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/sample11.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry, Visibility and Occlusion","perspective":"Exocentric","caption":"The camera glides smoothly to the right, revealing the full expanse of the open-concept space. It then moves steadily forward, drawing closer to the large windows and the wooded view beyond. A slight backward drift follows, creating a dynamic yet controlled exploration of the room’s luxurious interior.","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/sample11.json"},{"id":"spatialvid_sample12","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample12.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample12.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/sample12.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Exocentric","caption":"The camera steadily moves forward, gliding along the bridge toward the spillway's opening. The motion is smooth and consistent, with a gradual acceleration as it approaches the structure, emphasizing depth and scale.","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/sample12.json"},{"id":"spatialvid_sample13","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample13.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample13.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/sample13.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry, Visibility and Occlusion","perspective":"Exocentric","caption":"The camera steadily moves forward along the road, maintaining a consistent horizontal position. It glides smoothly through the landscape, with a slight downward tilt as it progresses, capturing the winding path and distant mountains in a steady, unbroken motion.","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/sample13.json"},{"id":"spatialvid_sample14","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample14.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample14.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/sample14.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry, Visibility and Occlusion","perspective":"Exocentric","caption":"The camera glides forward and downward, tracing a dynamic path along the mountain ridge. It shifts slightly right as it descends, revealing the steep drop below. The motion is smooth and continuous, with a steady acceleration that emphasizes the vastness of the landscape.","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/sample14.json"},{"id":"spatialvid_sample15","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample15.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample15.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/sample15.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Exocentric","caption":"The camera steadily moves forward along a winding path, with a subtle shift to the right as it ascends. The trajectory shows a consistent forward translate, with minimal lateral or vertical adjustments, maintaining a smooth and steady motion.","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/sample15.json"},{"id":"spatialvid_sample16","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample16.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample16.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/sample16.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Exocentric","caption":"The camera steadily translates forward along the pier, gliding smoothly past flower-adorned railings and a safety gate. It maintains a consistent direction, gradually slowing as it approaches the lake’s edge, with a subtle shift in elevation as it nears the end of the structure.","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/sample16.json"},{"id":"spatialvid_sample17","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample17.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample17.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/sample17.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Exocentric","caption":"The camera glides smoothly to the right, moving past the desk and toward the window, then continues with a steady rightward translate, capturing the shelving and artwork in focus. The motion is consistent and fluid, with no significant pauses or abrupt changes.","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/sample17.json"},{"id":"spatialvid_sample18","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample18.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample18.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/sample18.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry, Visibility and Occlusion","perspective":"Exocentric","caption":"The camera glides steadily forward, moving smoothly along a winding path. As it progresses, it shifts slightly to the left, maintaining a consistent direction. The motion remains smooth and unbroken, with no abrupt changes in speed or orientation.","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/sample18.json"},{"id":"spatialvid_sample19","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample19.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample19.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/sample19.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Exocentric","caption":"The camera glides steadily to the right, moving through a wet urban landscape at night. It maintains a consistent pace, revealing storefronts and pedestrians under umbrellas, before gradually coming to a halt.","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/sample19.json"},{"id":"spatialvid_sample2","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/sample2.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Exocentric","caption":"The camera slowly moves forward through the stone passageway, gradually ascending as it reveals the village beyond. It maintains a steady forward translate until reaching the courtyard, where it comes to a complete stop, offering a stable view of the serene landscape.","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/sample2.json"},{"id":"spatialvid_sample20","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample20.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample20.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/sample20.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry, Visibility and Occlusion","perspective":"Exocentric","caption":"The camera steadily moves forward along the street, with a slight leftward drift as it progresses. The motion is smooth and consistent, maintaining a stable perspective on the village scene. The forward translate dominates, with minimal lateral adjustment.","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/sample20.json"},{"id":"spatialvid_sample21","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample21.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample21.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/sample21.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Exocentric","caption":"The camera steadily moves forward along a paved village street, gliding smoothly past traditional buildings and bustling pedestrians. Its path remains consistent, with no lateral or vertical shifts, maintaining a stable, forward-facing perspective through the tranquil setting.","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/sample21.json"},{"id":"spatialvid_sample22","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample22.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample22.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/sample22.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Exocentric","caption":"The camera steadily moves forward along a narrow path, with a gradual rightward shift. The motion is smooth and consistent, maintaining a steady pace as it progresses through the rocky terrain.","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/sample22.json"},{"id":"spatialvid_sample23","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample23.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample23.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/sample23.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Exocentric","caption":"The camera steadily moves forward along a snow-covered path, gliding smoothly through the bamboo forest. It maintains a low angle, tracking the distant figure with consistent motion. The trajectory shows a gradual shift to the left, subtly repositioning the frame as it progresses deeper into the scene.","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/sample23.json"},{"id":"spatialvid_sample24","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample24.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample24.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/sample24.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry, Visibility and Occlusion","perspective":"Exocentric","caption":"Starting from a stationary position, the camera translates steadily forward, gradually shifting its gaze to the right. This rightward translation slows as the camera approaches a wooden barn, eventually coming to a halt with a focused view on the barn.","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/sample24.json"},{"id":"spatialvid_sample25","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample25.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample25.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/sample25.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry, Visibility and Occlusion","perspective":"Exocentric","caption":"The camera steadily moves forward through the space, with a smooth, continuous translation. A slight shift to the left is detected mid-trajectory, revealing more of the lounge area. The motion remains consistent and controlled, with no abrupt changes in direction or speed.","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/sample25.json"},{"id":"spatialvid_sample26","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample26.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample26.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/sample26.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Exocentric","caption":"The camera glides smoothly to the right, maintaining a steady forward motion as it reveals a serene alpine village. Its path is consistent, with no abrupt changes in speed, gradually uncovering the landscape and distant snow-capped peaks.","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/sample26.json"},{"id":"spatialvid_sample27","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample27.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample27.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/sample27.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Exocentric","caption":"The camera glides steadily forward along a narrow path, gradually shifting left as it approaches the cottage. It ascends slightly to maintain framing, with smooth, consistent motion throughout the sequence.","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/sample27.json"},{"id":"spatialvid_sample28","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample28.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample28.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/sample28.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Exocentric","caption":"The camera steadily moves forward along the street, with a subtle leftward shift in framing. The motion is smooth and consistent, maintaining a steady pace as it passes shops and cafes, gradually building momentum before coming to a stop.","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/sample28.json"},{"id":"spatialvid_sample29","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample29.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample29.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/sample29.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry, Visibility and Occlusion","perspective":"Exocentric","caption":"The camera steadily moves forward, with a subtle rightward drift, while gradually descending. The motion is smooth and consistent, capturing the vast volcanic expanse as it reveals more of the glowing orange lava river and rugged terrain below.","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/sample29.json"},{"id":"spatialvid_sample3","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample3.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample3.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/sample3.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry, Visibility and Occlusion","perspective":"Exocentric","caption":"The camera glides smoothly forward, gradually revealing the vast interior space. It then shifts left, sweeping across the open living area. The motion slows as it stabilizes, capturing the room’s luxurious details before subtly moving closer to the scene.","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/sample3.json"},{"id":"spatialvid_sample30","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample30.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample30.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/sample30.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry, Visibility and Occlusion","perspective":"Exocentric","caption":"The camera steadily moves forward along the riverbank, maintaining a low angle as it captures the shimmering reflections of the illuminated bridges. Slight right and left panning motions keep the structures in frame, with smooth, continuous motion throughout.","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/sample30.json"},{"id":"spatialvid_sample31","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample31.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample31.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/sample31.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Exocentric","caption":"The camera steadily translates forward, gliding along the central path of the closet. Its movement is smooth and consistent, maintaining a low angle as it progresses through the space, revealing the organized shelves and clothing racks in steady progression.","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/sample31.json"},{"id":"spatialvid_sample33","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample33.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample33.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/sample33.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry, Visibility and Occlusion","perspective":"Exocentric","caption":"The camera steadily moves forward along a snowy road, with a slight rightward drift as it progresses. The motion is smooth and consistent, maintaining a low angle that emphasizes the vast mountainous landscape ahead.","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/sample33.json"},{"id":"spatialvid_sample34","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample34.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample34.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/sample34.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Exocentric","caption":"The camera steadily moves forward along a straight path, gliding smoothly through the quiet market street. Its position shifts consistently to the left as it progresses, maintaining a steady pace with no abrupt changes in direction or speed.","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/sample34.json"},{"id":"spatialvid_sample4","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample4.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample4.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/sample4.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry, Visibility and Occlusion","perspective":"Exocentric","caption":"The camera steadily moves forward along the cobblestone street, with a slight leftward drift as it tracks the center of the path. The motion remains smooth and consistent, with minimal lateral adjustments, maintaining a stable perspective on the traditional shops and lantern-lit environment.","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/sample4.json"},{"id":"spatialvid_sample5","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample5.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample5.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/sample5.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Exocentric","caption":"The camera steadily moves forward, gliding through the rain-soaked crosswalk as it translates leftward, maintaining a consistent eye-level perspective. The motion is smooth and sustained, with a clear forward trajectory that captures the flowing pedestrian movement and glowing cityscape.","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/sample5.json"},{"id":"spatialvid_sample6","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample6.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample6.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/sample6.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Exocentric","caption":"The camera glides steadily forward, moving through a narrow passage as it translates rightward and slightly downward. The motion remains smooth and consistent, gradually revealing an open courtyard with stone steps and potted plants. The forward movement slows as the camera reaches the space, offering a wide view of the historic setting.","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/sample6.json"},{"id":"spatialvid_sample7","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample7.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample7.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/sample7.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Exocentric","caption":"The camera steadily moves forward along the street, maintaining a consistent pace. Its position shifts smoothly in the z-direction, creating a steady dolly effect. The x-coordinate decreases slightly, indicating a subtle leftward drift, while the y-coordinate increases, suggesting a slight downward tilt.","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/sample7.json"},{"id":"spatialvid_sample8","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample8.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample8.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/sample8.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry, Visibility and Occlusion","perspective":"Exocentric","caption":"The camera smoothly translates forward, gradually moving toward the pier while subtly shifting right to maintain the scene's composition. The motion is steady and controlled, with a clear directional shift that brings the viewer closer to the bustling waterfront activity.","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/sample8.json"},{"id":"spatialvid_sample9","videoPath":"curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample9.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/videos/sample9.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v9/spatialvid-public-samples/previews/initial_frames/sample9.jpg","sourceDataset":"SpatialVID","suggestedTrack":"View motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Exocentric","caption":"The camera steadily moves forward along a snowy city sidewalk, maintaining a low angle. Slight lateral shifts keep it aligned with the path, while the steady progression through the scene conveys a calm, continuous motion.","annotationPath":"curated/spatial-world-model/v9/spatialvid-public-samples/annotations/sample9.json"},{"id":"spatialvid_hq_0932762a-b306-5bd3-8209-17f0b0052050","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/0932762a-b306-5bd3-8209-17f0b0052050.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/0932762a-b306-5bd3-8209-17f0b0052050.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/0932762a-b306-5bd3-8209-17f0b0052050.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Natural Landscape;Winter Forest scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/0932762a-b306-5bd3-8209-17f0b0052050.json"},{"id":"spatialvid_hq_0ae61577-dad8-52a4-855d-fde48eaa8a3b","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/0ae61577-dad8-52a4-855d-fde48eaa8a3b.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/0ae61577-dad8-52a4-855d-fde48eaa8a3b.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/0ae61577-dad8-52a4-855d-fde48eaa8a3b.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Natural Landscape;Mountain Road scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/0ae61577-dad8-52a4-855d-fde48eaa8a3b.json"},{"id":"spatialvid_hq_0c67fff7-d37a-5ddd-8a5f-0efbab643830","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/0c67fff7-d37a-5ddd-8a5f-0efbab643830.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/0c67fff7-d37a-5ddd-8a5f-0efbab643830.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/0c67fff7-d37a-5ddd-8a5f-0efbab643830.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Natural Landscape;Mountain Valley Road scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/0c67fff7-d37a-5ddd-8a5f-0efbab643830.json"},{"id":"spatialvid_hq_171e82eb-5ddb-5d73-9894-0b65f7f295e4","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/171e82eb-5ddb-5d73-9894-0b65f7f295e4.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/171e82eb-5ddb-5d73-9894-0b65f7f295e4.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/171e82eb-5ddb-5d73-9894-0b65f7f295e4.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Natural Landscape;Park scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/171e82eb-5ddb-5d73-9894-0b65f7f295e4.json"},{"id":"spatialvid_hq_1b19acc6-5013-56d0-90ca-8b01eb885983","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/1b19acc6-5013-56d0-90ca-8b01eb885983.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/1b19acc6-5013-56d0-90ca-8b01eb885983.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/1b19acc6-5013-56d0-90ca-8b01eb885983.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Natural Landscape;Forest Trail scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/1b19acc6-5013-56d0-90ca-8b01eb885983.json"},{"id":"spatialvid_hq_1c3f790d-d41a-5912-ac06-bad8b751e295","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/1c3f790d-d41a-5912-ac06-bad8b751e295.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/1c3f790d-d41a-5912-ac06-bad8b751e295.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/1c3f790d-d41a-5912-ac06-bad8b751e295.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Natural Landscape;Forest Path scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/1c3f790d-d41a-5912-ac06-bad8b751e295.json"},{"id":"spatialvid_hq_1c921da8-6090-5ca9-8e49-4a59ab4b6ef9","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/1c921da8-6090-5ca9-8e49-4a59ab4b6ef9.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/1c921da8-6090-5ca9-8e49-4a59ab4b6ef9.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/1c921da8-6090-5ca9-8e49-4a59ab4b6ef9.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"urban","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Urban;Plaza scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/1c921da8-6090-5ca9-8e49-4a59ab4b6ef9.json"},{"id":"spatialvid_hq_1cdf4710-e221-5cc5-a63c-3931ab6efbe3","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/1cdf4710-e221-5cc5-a63c-3931ab6efbe3.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/1cdf4710-e221-5cc5-a63c-3931ab6efbe3.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/1cdf4710-e221-5cc5-a63c-3931ab6efbe3.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Natural Landscape;Scenic Railway View scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/1cdf4710-e221-5cc5-a63c-3931ab6efbe3.json"},{"id":"spatialvid_hq_1d9f80aa-6e01-5acc-a162-fa8bc0147772","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/1d9f80aa-6e01-5acc-a162-fa8bc0147772.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/1d9f80aa-6e01-5acc-a162-fa8bc0147772.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/1d9f80aa-6e01-5acc-a162-fa8bc0147772.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"urban","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Urban;Street Scene scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/1d9f80aa-6e01-5acc-a162-fa8bc0147772.json"},{"id":"spatialvid_hq_2221fe54-4e21-5d3d-b188-c1241c1d2cd7","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/2221fe54-4e21-5d3d-b188-c1241c1d2cd7.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/2221fe54-4e21-5d3d-b188-c1241c1d2cd7.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/2221fe54-4e21-5d3d-b188-c1241c1d2cd7.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Rural;Village Street scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/2221fe54-4e21-5d3d-b188-c1241c1d2cd7.json"},{"id":"spatialvid_hq_23b9c63e-7751-5e0b-8820-013648f2843e","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/23b9c63e-7751-5e0b-8820-013648f2843e.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/23b9c63e-7751-5e0b-8820-013648f2843e.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/23b9c63e-7751-5e0b-8820-013648f2843e.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Rural;Lakeside Village scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/23b9c63e-7751-5e0b-8820-013648f2843e.json"},{"id":"spatialvid_hq_263c9363-506a-53db-a2a1-e7103cf5b9ce","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/263c9363-506a-53db-a2a1-e7103cf5b9ce.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/263c9363-506a-53db-a2a1-e7103cf5b9ce.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/263c9363-506a-53db-a2a1-e7103cf5b9ce.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"urban","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Urban;Street Scene scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/263c9363-506a-53db-a2a1-e7103cf5b9ce.json"},{"id":"spatialvid_hq_29665ce2-e423-5b0f-aa16-74d3332535e7","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/29665ce2-e423-5b0f-aa16-74d3332535e7.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/29665ce2-e423-5b0f-aa16-74d3332535e7.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/29665ce2-e423-5b0f-aa16-74d3332535e7.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"urban","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Urban;Street Scene scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/29665ce2-e423-5b0f-aa16-74d3332535e7.json"},{"id":"spatialvid_hq_2e60a5f8-4d52-533a-a89e-57501245628c","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/2e60a5f8-4d52-533a-a89e-57501245628c.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/2e60a5f8-4d52-533a-a89e-57501245628c.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/2e60a5f8-4d52-533a-a89e-57501245628c.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Natural Landscape;Mountain Railway scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/2e60a5f8-4d52-533a-a89e-57501245628c.json"},{"id":"spatialvid_hq_2fa6ae85-c441-5700-9f98-4e08e24bdf9c","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/2fa6ae85-c441-5700-9f98-4e08e24bdf9c.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/2fa6ae85-c441-5700-9f98-4e08e24bdf9c.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/2fa6ae85-c441-5700-9f98-4e08e24bdf9c.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Natural Landscape;Mountainous Forest scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/2fa6ae85-c441-5700-9f98-4e08e24bdf9c.json"},{"id":"spatialvid_hq_2fecbca5-b349-533b-858e-c73ffb484b6f","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/2fecbca5-b349-533b-858e-c73ffb484b6f.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/2fecbca5-b349-533b-858e-c73ffb484b6f.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/2fecbca5-b349-533b-858e-c73ffb484b6f.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Natural Landscape;Highway scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/2fecbca5-b349-533b-858e-c73ffb484b6f.json"},{"id":"spatialvid_hq_32ac42cd-af18-50b4-be43-9761176dbb59","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/32ac42cd-af18-50b4-be43-9761176dbb59.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/32ac42cd-af18-50b4-be43-9761176dbb59.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/32ac42cd-af18-50b4-be43-9761176dbb59.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Rural;Mountain Road scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/32ac42cd-af18-50b4-be43-9761176dbb59.json"},{"id":"spatialvid_hq_3730dbd1-0a29-5bbe-93dc-61ce039172c2","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/3730dbd1-0a29-5bbe-93dc-61ce039172c2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/3730dbd1-0a29-5bbe-93dc-61ce039172c2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/3730dbd1-0a29-5bbe-93dc-61ce039172c2.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Natural Landscape;Scenic Train Ride scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/3730dbd1-0a29-5bbe-93dc-61ce039172c2.json"},{"id":"spatialvid_hq_40ce6d3b-5f26-5c8f-a7b5-2aec5b7c90de","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/40ce6d3b-5f26-5c8f-a7b5-2aec5b7c90de.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/40ce6d3b-5f26-5c8f-a7b5-2aec5b7c90de.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/40ce6d3b-5f26-5c8f-a7b5-2aec5b7c90de.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Natural Landscape;Volcanic Landscape scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/40ce6d3b-5f26-5c8f-a7b5-2aec5b7c90de.json"},{"id":"spatialvid_hq_438c8af8-b3c5-57af-b1c7-8048c1f12821","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/438c8af8-b3c5-57af-b1c7-8048c1f12821.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/438c8af8-b3c5-57af-b1c7-8048c1f12821.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/438c8af8-b3c5-57af-b1c7-8048c1f12821.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Natural Landscape;Mountain Railway scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/438c8af8-b3c5-57af-b1c7-8048c1f12821.json"},{"id":"spatialvid_hq_4c7683ff-9772-5269-bad7-37a2bb24162c","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/4c7683ff-9772-5269-bad7-37a2bb24162c.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/4c7683ff-9772-5269-bad7-37a2bb24162c.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/4c7683ff-9772-5269-bad7-37a2bb24162c.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Rural;Scenic Roadway scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/4c7683ff-9772-5269-bad7-37a2bb24162c.json"},{"id":"spatialvid_hq_4c93bd8f-f664-5dcb-90df-c81afa5bbe15","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/4c93bd8f-f664-5dcb-90df-c81afa5bbe15.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/4c93bd8f-f664-5dcb-90df-c81afa5bbe15.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/4c93bd8f-f664-5dcb-90df-c81afa5bbe15.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Natural Landscape;Mountain Train Journey scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/4c93bd8f-f664-5dcb-90df-c81afa5bbe15.json"},{"id":"spatialvid_hq_4ed74f78-bd2a-56ca-9b0d-1d93c65f63e7","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/4ed74f78-bd2a-56ca-9b0d-1d93c65f63e7.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/4ed74f78-bd2a-56ca-9b0d-1d93c65f63e7.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/4ed74f78-bd2a-56ca-9b0d-1d93c65f63e7.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Natural Landscape;Forest Trail scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/4ed74f78-bd2a-56ca-9b0d-1d93c65f63e7.json"},{"id":"spatialvid_hq_500b851e-b7d5-5ab4-9dcd-d23eb8fafef9","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/500b851e-b7d5-5ab4-9dcd-d23eb8fafef9.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/500b851e-b7d5-5ab4-9dcd-d23eb8fafef9.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/500b851e-b7d5-5ab4-9dcd-d23eb8fafef9.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Natural Landscape;Waterfront scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/500b851e-b7d5-5ab4-9dcd-d23eb8fafef9.json"},{"id":"spatialvid_hq_529a17da-8826-5bf3-885e-b3328545e1f8","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/529a17da-8826-5bf3-885e-b3328545e1f8.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/529a17da-8826-5bf3-885e-b3328545e1f8.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/529a17da-8826-5bf3-885e-b3328545e1f8.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Natural Landscape;Mountain Train View scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/529a17da-8826-5bf3-885e-b3328545e1f8.json"},{"id":"spatialvid_hq_5b7eb05b-f8f3-5131-bc30-ffaf13a7b36b","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/5b7eb05b-f8f3-5131-bc30-ffaf13a7b36b.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/5b7eb05b-f8f3-5131-bc30-ffaf13a7b36b.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/5b7eb05b-f8f3-5131-bc30-ffaf13a7b36b.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Natural Landscape;Mountain Road scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/5b7eb05b-f8f3-5131-bc30-ffaf13a7b36b.json"},{"id":"spatialvid_hq_5e679ddd-1ae1-52ea-8968-7783b4ccae40","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/5e679ddd-1ae1-52ea-8968-7783b4ccae40.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/5e679ddd-1ae1-52ea-8968-7783b4ccae40.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/5e679ddd-1ae1-52ea-8968-7783b4ccae40.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Natural Landscape;Mountain Trail scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/5e679ddd-1ae1-52ea-8968-7783b4ccae40.json"},{"id":"spatialvid_hq_5feff644-01b8-5bf8-9423-82ba8c1f2075","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/5feff644-01b8-5bf8-9423-82ba8c1f2075.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/5feff644-01b8-5bf8-9423-82ba8c1f2075.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/5feff644-01b8-5bf8-9423-82ba8c1f2075.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Rural;Mountain Road scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/5feff644-01b8-5bf8-9423-82ba8c1f2075.json"},{"id":"spatialvid_hq_64c15833-4bd9-5c1a-b776-43a1db02e9b3","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/64c15833-4bd9-5c1a-b776-43a1db02e9b3.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/64c15833-4bd9-5c1a-b776-43a1db02e9b3.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/64c15833-4bd9-5c1a-b776-43a1db02e9b3.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"urban","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Urban;Railway Passage scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/64c15833-4bd9-5c1a-b776-43a1db02e9b3.json"},{"id":"spatialvid_hq_64e99fa1-40c8-54be-905f-a77db2c9db2f","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/64e99fa1-40c8-54be-905f-a77db2c9db2f.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/64e99fa1-40c8-54be-905f-a77db2c9db2f.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/64e99fa1-40c8-54be-905f-a77db2c9db2f.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Natural Landscape;Mountain Road scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/64e99fa1-40c8-54be-905f-a77db2c9db2f.json"},{"id":"spatialvid_hq_6b26813e-a7dd-5fa6-ab30-abd94d829fe3","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/6b26813e-a7dd-5fa6-ab30-abd94d829fe3.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/6b26813e-a7dd-5fa6-ab30-abd94d829fe3.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/6b26813e-a7dd-5fa6-ab30-abd94d829fe3.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Rural;Village Street scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/6b26813e-a7dd-5fa6-ab30-abd94d829fe3.json"},{"id":"spatialvid_hq_6b8e99b7-6a65-5a46-8273-81c7f5d00b47","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/6b8e99b7-6a65-5a46-8273-81c7f5d00b47.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/6b8e99b7-6a65-5a46-8273-81c7f5d00b47.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/6b8e99b7-6a65-5a46-8273-81c7f5d00b47.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Rural;Mountain Road scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/6b8e99b7-6a65-5a46-8273-81c7f5d00b47.json"},{"id":"spatialvid_hq_6db1f4e4-e5cd-5b59-87cf-0a73e3d5245e","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/6db1f4e4-e5cd-5b59-87cf-0a73e3d5245e.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/6db1f4e4-e5cd-5b59-87cf-0a73e3d5245e.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/6db1f4e4-e5cd-5b59-87cf-0a73e3d5245e.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Natural Landscape;Forest Road scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/6db1f4e4-e5cd-5b59-87cf-0a73e3d5245e.json"},{"id":"spatialvid_hq_70f01121-254a-5ddf-a760-274754d4260e","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/70f01121-254a-5ddf-a760-274754d4260e.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/70f01121-254a-5ddf-a760-274754d4260e.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/70f01121-254a-5ddf-a760-274754d4260e.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Natural Landscape;Mountain Road scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/70f01121-254a-5ddf-a760-274754d4260e.json"},{"id":"spatialvid_hq_73e042dc-176a-5151-8199-24084458f9ef","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/73e042dc-176a-5151-8199-24084458f9ef.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/73e042dc-176a-5151-8199-24084458f9ef.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/73e042dc-176a-5151-8199-24084458f9ef.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"urban","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Urban;Train View scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/73e042dc-176a-5151-8199-24084458f9ef.json"},{"id":"spatialvid_hq_7a073961-db8d-5724-9280-eba26562f6ae","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/7a073961-db8d-5724-9280-eba26562f6ae.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/7a073961-db8d-5724-9280-eba26562f6ae.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/7a073961-db8d-5724-9280-eba26562f6ae.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Rural;Village Scene scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/7a073961-db8d-5724-9280-eba26562f6ae.json"},{"id":"spatialvid_hq_82129dcf-a1ba-5738-97e4-61a7547f5567","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/82129dcf-a1ba-5738-97e4-61a7547f5567.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/82129dcf-a1ba-5738-97e4-61a7547f5567.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/82129dcf-a1ba-5738-97e4-61a7547f5567.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Natural Landscape;Mountain River Valley scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/82129dcf-a1ba-5738-97e4-61a7547f5567.json"},{"id":"spatialvid_hq_826f9ee4-9a16-5080-bc8b-00a0daa76310","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/826f9ee4-9a16-5080-bc8b-00a0daa76310.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/826f9ee4-9a16-5080-bc8b-00a0daa76310.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/826f9ee4-9a16-5080-bc8b-00a0daa76310.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Natural Landscape;Mountain Trail scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/826f9ee4-9a16-5080-bc8b-00a0daa76310.json"},{"id":"spatialvid_hq_82f29cf7-09a2-5b08-aaee-88ddef5e1140","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/82f29cf7-09a2-5b08-aaee-88ddef5e1140.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/82f29cf7-09a2-5b08-aaee-88ddef5e1140.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/82f29cf7-09a2-5b08-aaee-88ddef5e1140.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Natural Landscape;Mountain Road scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/82f29cf7-09a2-5b08-aaee-88ddef5e1140.json"},{"id":"spatialvid_hq_84a985b4-88a1-5dbd-b620-b77d37850bcc","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/84a985b4-88a1-5dbd-b620-b77d37850bcc.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/84a985b4-88a1-5dbd-b620-b77d37850bcc.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/84a985b4-88a1-5dbd-b620-b77d37850bcc.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Rural;Mountain Town scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/84a985b4-88a1-5dbd-b620-b77d37850bcc.json"},{"id":"spatialvid_hq_8cb4354a-ebcc-5c6d-84d8-bfb2ddef2f83","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/8cb4354a-ebcc-5c6d-84d8-bfb2ddef2f83.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/8cb4354a-ebcc-5c6d-84d8-bfb2ddef2f83.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/8cb4354a-ebcc-5c6d-84d8-bfb2ddef2f83.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Natural Landscape;Snowy Forest Trail scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/8cb4354a-ebcc-5c6d-84d8-bfb2ddef2f83.json"},{"id":"spatialvid_hq_8f8a9b7b-552f-53c7-9665-59f965d34f6e","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/8f8a9b7b-552f-53c7-9665-59f965d34f6e.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/8f8a9b7b-552f-53c7-9665-59f965d34f6e.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/8f8a9b7b-552f-53c7-9665-59f965d34f6e.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Natural Landscape;Forest Path scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/8f8a9b7b-552f-53c7-9665-59f965d34f6e.json"},{"id":"spatialvid_hq_902c5d3a-70d2-5569-b0a2-8866031531b8","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/902c5d3a-70d2-5569-b0a2-8866031531b8.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/902c5d3a-70d2-5569-b0a2-8866031531b8.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/902c5d3a-70d2-5569-b0a2-8866031531b8.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Rural;Train Track View scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/902c5d3a-70d2-5569-b0a2-8866031531b8.json"},{"id":"spatialvid_hq_98cc1fec-19e4-50cf-a368-8464ee95ae68","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/98cc1fec-19e4-50cf-a368-8464ee95ae68.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/98cc1fec-19e4-50cf-a368-8464ee95ae68.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/98cc1fec-19e4-50cf-a368-8464ee95ae68.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Natural Landscape;Forest Train Journey scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/98cc1fec-19e4-50cf-a368-8464ee95ae68.json"},{"id":"spatialvid_hq_99f753a4-ddf2-5ecb-aa82-98fa2347f366","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/99f753a4-ddf2-5ecb-aa82-98fa2347f366.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/99f753a4-ddf2-5ecb-aa82-98fa2347f366.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/99f753a4-ddf2-5ecb-aa82-98fa2347f366.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Rural;Small Town Street scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/99f753a4-ddf2-5ecb-aa82-98fa2347f366.json"},{"id":"spatialvid_hq_9fc99533-2f9d-5a2c-9be7-49741e60e17d","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/9fc99533-2f9d-5a2c-9be7-49741e60e17d.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/9fc99533-2f9d-5a2c-9be7-49741e60e17d.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/9fc99533-2f9d-5a2c-9be7-49741e60e17d.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Natural Landscape;Valley with River scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/9fc99533-2f9d-5a2c-9be7-49741e60e17d.json"},{"id":"spatialvid_hq_a338cf12-0d48-532a-b3b8-b9c90b73d557","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/a338cf12-0d48-532a-b3b8-b9c90b73d557.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/a338cf12-0d48-532a-b3b8-b9c90b73d557.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/a338cf12-0d48-532a-b3b8-b9c90b73d557.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Rural;Mountain Road scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/a338cf12-0d48-532a-b3b8-b9c90b73d557.json"},{"id":"spatialvid_hq_a3b96268-bbb5-54e3-8fa8-f590f2950a1e","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/a3b96268-bbb5-54e3-8fa8-f590f2950a1e.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/a3b96268-bbb5-54e3-8fa8-f590f2950a1e.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/a3b96268-bbb5-54e3-8fa8-f590f2950a1e.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Natural Landscape;Mountain Train Journey scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/a3b96268-bbb5-54e3-8fa8-f590f2950a1e.json"},{"id":"spatialvid_hq_ae43b45d-74ce-55fa-bf6f-0ea7b49db59c","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/ae43b45d-74ce-55fa-bf6f-0ea7b49db59c.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/ae43b45d-74ce-55fa-bf6f-0ea7b49db59c.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/ae43b45d-74ce-55fa-bf6f-0ea7b49db59c.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Natural Landscape;Forest Path scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/ae43b45d-74ce-55fa-bf6f-0ea7b49db59c.json"},{"id":"spatialvid_hq_ae861461-97fd-5c06-a5eb-3aad832eeaf4","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/ae861461-97fd-5c06-a5eb-3aad832eeaf4.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/ae861461-97fd-5c06-a5eb-3aad832eeaf4.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/ae861461-97fd-5c06-a5eb-3aad832eeaf4.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Rural;Train Journey scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/ae861461-97fd-5c06-a5eb-3aad832eeaf4.json"},{"id":"spatialvid_hq_ba6c0f62-1301-5160-8916-e084e435e8d2","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/ba6c0f62-1301-5160-8916-e084e435e8d2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/ba6c0f62-1301-5160-8916-e084e435e8d2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/ba6c0f62-1301-5160-8916-e084e435e8d2.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Natural Landscape;Forest Road scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/ba6c0f62-1301-5160-8916-e084e435e8d2.json"},{"id":"spatialvid_hq_c4a65f14-99ba-574d-999f-a98606db9324","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/c4a65f14-99ba-574d-999f-a98606db9324.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/c4a65f14-99ba-574d-999f-a98606db9324.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/c4a65f14-99ba-574d-999f-a98606db9324.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Rural;Train Track View scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/c4a65f14-99ba-574d-999f-a98606db9324.json"},{"id":"spatialvid_hq_c9c1dd8b-8197-5c8e-99bc-7693e8a77de9","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/c9c1dd8b-8197-5c8e-99bc-7693e8a77de9.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/c9c1dd8b-8197-5c8e-99bc-7693e8a77de9.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/c9c1dd8b-8197-5c8e-99bc-7693e8a77de9.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Natural Landscape;Forest Trail scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/c9c1dd8b-8197-5c8e-99bc-7693e8a77de9.json"},{"id":"spatialvid_hq_cc51d644-4f14-58f7-93da-f1d666fe170a","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/cc51d644-4f14-58f7-93da-f1d666fe170a.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/cc51d644-4f14-58f7-93da-f1d666fe170a.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/cc51d644-4f14-58f7-93da-f1d666fe170a.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Natural Landscape;River Valley scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/cc51d644-4f14-58f7-93da-f1d666fe170a.json"},{"id":"spatialvid_hq_cd472edb-b7be-5183-86a3-6889abe5bdec","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/cd472edb-b7be-5183-86a3-6889abe5bdec.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/cd472edb-b7be-5183-86a3-6889abe5bdec.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/cd472edb-b7be-5183-86a3-6889abe5bdec.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Rural;Scenic Road scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/cd472edb-b7be-5183-86a3-6889abe5bdec.json"},{"id":"spatialvid_hq_ce9a705d-6dc6-55bb-bce2-0d9d8f490d45","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/ce9a705d-6dc6-55bb-bce2-0d9d8f490d45.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/ce9a705d-6dc6-55bb-bce2-0d9d8f490d45.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/ce9a705d-6dc6-55bb-bce2-0d9d8f490d45.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Natural Landscape;Forest Trail scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/ce9a705d-6dc6-55bb-bce2-0d9d8f490d45.json"},{"id":"spatialvid_hq_cf942462-d269-5cce-a121-abbc597c8a64","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/cf942462-d269-5cce-a121-abbc597c8a64.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/cf942462-d269-5cce-a121-abbc597c8a64.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/cf942462-d269-5cce-a121-abbc597c8a64.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Rural;Village Landscape scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/cf942462-d269-5cce-a121-abbc597c8a64.json"},{"id":"spatialvid_hq_cf9ffc95-3791-5bd7-b6b7-98aca2ef9655","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/cf9ffc95-3791-5bd7-b6b7-98aca2ef9655.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/cf9ffc95-3791-5bd7-b6b7-98aca2ef9655.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/cf9ffc95-3791-5bd7-b6b7-98aca2ef9655.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Natural Landscape;Mountain Trail scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/cf9ffc95-3791-5bd7-b6b7-98aca2ef9655.json"},{"id":"spatialvid_hq_d7f8bf79-d67c-5ca6-82cc-bd4edcc27b41","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/d7f8bf79-d67c-5ca6-82cc-bd4edcc27b41.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/d7f8bf79-d67c-5ca6-82cc-bd4edcc27b41.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/d7f8bf79-d67c-5ca6-82cc-bd4edcc27b41.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Rural;Snow-Covered Village scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/d7f8bf79-d67c-5ca6-82cc-bd4edcc27b41.json"},{"id":"spatialvid_hq_e03c21ba-ca3f-5efb-9198-a3bb3bb8ea4f","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/e03c21ba-ca3f-5efb-9198-a3bb3bb8ea4f.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/e03c21ba-ca3f-5efb-9198-a3bb3bb8ea4f.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/e03c21ba-ca3f-5efb-9198-a3bb3bb8ea4f.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Natural Landscape;Rural Trackway scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/e03c21ba-ca3f-5efb-9198-a3bb3bb8ea4f.json"},{"id":"spatialvid_hq_ea1ed209-d46b-5be8-86b7-fe201bbf3f8c","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/ea1ed209-d46b-5be8-86b7-fe201bbf3f8c.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/ea1ed209-d46b-5be8-86b7-fe201bbf3f8c.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/ea1ed209-d46b-5be8-86b7-fe201bbf3f8c.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Natural Landscape;Mountain Railway scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/ea1ed209-d46b-5be8-86b7-fe201bbf3f8c.json"},{"id":"spatialvid_hq_f085cd21-1698-522e-b17a-e285e50f00b1","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/f085cd21-1698-522e-b17a-e285e50f00b1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/f085cd21-1698-522e-b17a-e285e50f00b1.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/f085cd21-1698-522e-b17a-e285e50f00b1.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Rural;Train Journey scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/f085cd21-1698-522e-b17a-e285e50f00b1.json"},{"id":"spatialvid_hq_f2b1c71e-65d0-50a4-893a-eaf4945ca87a","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/f2b1c71e-65d0-50a4-893a-eaf4945ca87a.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/f2b1c71e-65d0-50a4-893a-eaf4945ca87a.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/f2b1c71e-65d0-50a4-893a-eaf4945ca87a.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Rural;Train Station scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/f2b1c71e-65d0-50a4-893a-eaf4945ca87a.json"},{"id":"spatialvid_hq_f3f5b613-83ca-5153-b4a7-12ff0824cd80","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/f3f5b613-83ca-5153-b4a7-12ff0824cd80.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/f3f5b613-83ca-5153-b4a7-12ff0824cd80.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/f3f5b613-83ca-5153-b4a7-12ff0824cd80.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Natural Landscape;Forest Road scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/f3f5b613-83ca-5153-b4a7-12ff0824cd80.json"},{"id":"spatialvid_hq_fb034d8f-7f2f-52fc-b282-2a6c042f538c","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/fb034d8f-7f2f-52fc-b282-2a6c042f538c.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/fb034d8f-7f2f-52fc-b282-2a6c042f538c.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/fb034d8f-7f2f-52fc-b282-2a6c042f538c.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Natural Landscape;Forest Trail scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/fb034d8f-7f2f-52fc-b282-2a6c042f538c.json"},{"id":"spatialvid_hq_fed06e74-a2aa-5ee7-ae9d-244520ac7b4f","videoPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/fed06e74-a2aa-5ee7-ae9d-244520ac7b4f.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/videos/fed06e74-a2aa-5ee7-ae9d-244520ac7b4f.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v10/spatialvid-hq-group0001/previews/initial_frames/fed06e74-a2aa-5ee7-ae9d-244520ac7b4f.jpg","sourceDataset":"SpatialVID-HQ","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"What is the camera's direction of travel through this Natural Landscape;Mountain River View scene?","annotationPath":"curated/spatial-world-model/v10/spatialvid-hq-group0001/annotations/fed06e74-a2aa-5ee7-ae9d-244520ac7b4f.json"},{"id":"vgenst_bt_e_exo_dyn_0_urban_residential_street","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/coupled_motion/vgenst_bt_e_exo_dyn_0_urban_residential_street.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/coupled_motion/vgenst_bt_e_exo_dyn_0_urban_residential_street.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/coupled_motion/vgenst_bt_e_exo_dyn_0_urban_residential_street.png","sourceDataset":"VGenST-Bench","suggestedTrack":"coupled motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Relative and Coupled Motion","perspective":"Exocentric","caption":"What action does the Blue Sedan Car perform during the video?: A. Continues moving without stopping, B. Comes to a complete stop, C. Turns around and moves backward, D. Waits and resumes moving after a short pause","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/coupled_motion/vgenst_bt_e_exo_dyn_0_urban_residential_street.json"},{"id":"vgenst_bt_e_exo_dyn_12_coastal_cliffside_road","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/coupled_motion/vgenst_bt_e_exo_dyn_12_coastal_cliffside_road.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/coupled_motion/vgenst_bt_e_exo_dyn_12_coastal_cliffside_road.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/coupled_motion/vgenst_bt_e_exo_dyn_12_coastal_cliffside_road.png","sourceDataset":"VGenST-Bench","suggestedTrack":"coupled motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Relative and Coupled Motion","perspective":"Exocentric","caption":"What action does the Silver Convertible Sports Car perform during the video?: A. Continues moving without stopping, B. Comes to a complete stop, C. Turns around and moves backward, D. Waits and resumes moving after a short pause","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/coupled_motion/vgenst_bt_e_exo_dyn_12_coastal_cliffside_road.json"},{"id":"vgenst_bt_e_exo_dyn_23_golf_course_cart_path","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/coupled_motion/vgenst_bt_e_exo_dyn_23_golf_course_cart_path.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/coupled_motion/vgenst_bt_e_exo_dyn_23_golf_course_cart_path.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/coupled_motion/vgenst_bt_e_exo_dyn_23_golf_course_cart_path.png","sourceDataset":"VGenST-Bench","suggestedTrack":"coupled motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Relative and Coupled Motion","perspective":"Exocentric","caption":"What event causes the Cream Golf Cart with Red Golf Bags to react?: A. The Wooden Golf Cart Shelter Pavilion on the side of the path, B. The Fast-Hopping Brown Wild Rabbit entering the path, C. It reacts itself without any external event","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/coupled_motion/vgenst_bt_e_exo_dyn_23_golf_course_cart_path.json"},{"id":"vgenst_bt_e_exo_dyn_29_sculpture_park_lawn","videoPath":"curated/spatial-world-model/v7/vgenst-bench/videos/coupled_motion/vgenst_bt_e_exo_dyn_29_sculpture_park_lawn.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/vgenst-bench/videos/coupled_motion/vgenst_bt_e_exo_dyn_29_sculpture_park_lawn.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/vgenst-bench/initial_frames/coupled_motion/vgenst_bt_e_exo_dyn_29_sculpture_park_lawn.png","sourceDataset":"VGenST-Bench","suggestedTrack":"coupled_motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative and Coupled Motion","perspective":"Exocentric","caption":"What is the order of events in the video?: A. The Yellow Touring Cyclist is moving forward, then the Yellow Touring Cyclist stops, then the Soccer Ball appears on the path, B. The Yellow Touring Cyclist is moving forward, then the Soccer Ball appears on the path, then the Yellow Touring Cyclist stops, C. The Soccer Ball appears on the path, then the Yellow Touring Cyclist is moving forward, then the Yellow Touring Cyclist stops","annotationPath":"curated/spatial-world-model/v7/vgenst-bench/annotations/coupled_motion/vgenst_bt_e_exo_dyn_29_sculpture_park_lawn.json"},{"id":"vgenst_bt_e_exo_dyn_34_lumber_yard_aisle","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/coupled_motion/vgenst_bt_e_exo_dyn_34_lumber_yard_aisle.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/coupled_motion/vgenst_bt_e_exo_dyn_34_lumber_yard_aisle.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/coupled_motion/vgenst_bt_e_exo_dyn_34_lumber_yard_aisle.png","sourceDataset":"VGenST-Bench","suggestedTrack":"coupled motion","scene":"daily activity","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Relative and Coupled Motion","perspective":"Exocentric","caption":"What action does the Red Lumber Yard Forklift perform during the video?: A. Continues moving without stopping, B. Comes to a complete stop, C. Turns around and moves backward, D. Waits and resumes moving after a short pause","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/coupled_motion/vgenst_bt_e_exo_dyn_34_lumber_yard_aisle.json"},{"id":"vgenst_bt_e_exo_dyn_3_riverfront_promenade","videoPath":"curated/spatial-world-model/v7/vgenst-bench/videos/coupled_motion/vgenst_bt_e_exo_dyn_3_riverfront_promenade.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/vgenst-bench/videos/coupled_motion/vgenst_bt_e_exo_dyn_3_riverfront_promenade.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/vgenst-bench/initial_frames/coupled_motion/vgenst_bt_e_exo_dyn_3_riverfront_promenade.png","sourceDataset":"VGenST-Bench","suggestedTrack":"coupled_motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative and Coupled Motion","perspective":"Exocentric","caption":"What event causes the Red Tourism E-Bike with Front Basket to react?: A. The Blue Tourist Information Kiosk on the side of the path, B. The Labrador entering the path, C. It reacts itself without any external event","annotationPath":"curated/spatial-world-model/v7/vgenst-bench/annotations/coupled_motion/vgenst_bt_e_exo_dyn_3_riverfront_promenade.json"},{"id":"vgenst_bt_e_exo_dyn_45_beach_shoreline","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/coupled_motion/vgenst_bt_e_exo_dyn_45_beach_shoreline.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/coupled_motion/vgenst_bt_e_exo_dyn_45_beach_shoreline.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/coupled_motion/vgenst_bt_e_exo_dyn_45_beach_shoreline.png","sourceDataset":"VGenST-Bench","suggestedTrack":"coupled motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Relative and Coupled Motion","perspective":"Exocentric","caption":"What event causes the White Beach ATV with Rider to react?: A. The Wooden Beach Lifeguard Tower on the side of the path, B. The Beach Volleyball entering the path, C. It reacts itself without any external event","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/coupled_motion/vgenst_bt_e_exo_dyn_45_beach_shoreline.json"},{"id":"vgenst_bt_e_exo_dyn_56_outdoor_ice_rink","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/coupled_motion/vgenst_bt_e_exo_dyn_56_outdoor_ice_rink.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/coupled_motion/vgenst_bt_e_exo_dyn_56_outdoor_ice_rink.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/coupled_motion/vgenst_bt_e_exo_dyn_56_outdoor_ice_rink.png","sourceDataset":"VGenST-Bench","suggestedTrack":"coupled motion","scene":"daily activity","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Relative and Coupled Motion","perspective":"Exocentric","caption":"What action does the Black Hockey Player with Stick perform during the video?: A. Continues moving without stopping, B. Comes to a complete stop, C. Turns around and moves backward, D. Waits and resumes moving after a short pause","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/coupled_motion/vgenst_bt_e_exo_dyn_56_outdoor_ice_rink.json"},{"id":"vgenst_bt_e_exo_dyn_67_ocean_regatta_course","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/coupled_motion/vgenst_bt_e_exo_dyn_67_ocean_regatta_course.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/coupled_motion/vgenst_bt_e_exo_dyn_67_ocean_regatta_course.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/coupled_motion/vgenst_bt_e_exo_dyn_67_ocean_regatta_course.png","sourceDataset":"VGenST-Bench","suggestedTrack":"coupled motion","scene":"daily activity","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Relative and Coupled Motion","perspective":"Exocentric","caption":"What event causes the Open Water Marathon Swimmer to react?: A. The Marker Buoy Tower on the side of the path, B. The Leaping Dolphin entering the path, C. It reacts itself without any external event","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/coupled_motion/vgenst_bt_e_exo_dyn_67_ocean_regatta_course.json"},{"id":"vgenst_bt_e_exo_dyn_77_evacuation_tent_aisle","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/coupled_motion/vgenst_bt_e_exo_dyn_77_evacuation_tent_aisle.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/coupled_motion/vgenst_bt_e_exo_dyn_77_evacuation_tent_aisle.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/coupled_motion/vgenst_bt_e_exo_dyn_77_evacuation_tent_aisle.png","sourceDataset":"VGenST-Bench","suggestedTrack":"coupled motion","scene":"driving","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Relative and Coupled Motion","perspective":"Exocentric","caption":"What event causes the Red Cross Volunteer Carrying Box to react?: A. The Stack of Aid Supply Crates on the side of the path, B. The Fallen Folding Chair Pile entering the path, C. It reacts itself without any external event","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/coupled_motion/vgenst_bt_e_exo_dyn_77_evacuation_tent_aisle.json"},{"id":"vgenst_bt_e_exo_dyn_88_ranch_perimeter_road","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/coupled_motion/vgenst_bt_e_exo_dyn_88_ranch_perimeter_road.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/coupled_motion/vgenst_bt_e_exo_dyn_88_ranch_perimeter_road.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/coupled_motion/vgenst_bt_e_exo_dyn_88_ranch_perimeter_road.png","sourceDataset":"VGenST-Bench","suggestedTrack":"coupled motion","scene":"driving","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Relative and Coupled Motion","perspective":"Exocentric","caption":"What action does the White Ranch Pickup Truck perform during the video?: A. Continues moving without stopping, B. Comes to a complete stop, C. Turns around and moves backward, D. Waits and resumes moving after a short pause","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/coupled_motion/vgenst_bt_e_exo_dyn_88_ranch_perimeter_road.json"},{"id":"vgenst_bt_e_exo_dyn_99_alien_planet_trail","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/coupled_motion/vgenst_bt_e_exo_dyn_99_alien_planet_trail.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/coupled_motion/vgenst_bt_e_exo_dyn_99_alien_planet_trail.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/coupled_motion/vgenst_bt_e_exo_dyn_99_alien_planet_trail.png","sourceDataset":"VGenST-Bench","suggestedTrack":"coupled motion","scene":"daily activity","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Relative and Coupled Motion","perspective":"Exocentric","caption":"What event causes the Silver Hover Pod to react?: A. The Crystal Spire Cluster on the side of the path, B. The Alien Creature entering the path, C. It reacts itself without any external event","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/coupled_motion/vgenst_bt_e_exo_dyn_99_alien_planet_trail.json"},{"id":"vgenst_ci_f_exo_sta_0_living_room_table","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_ci_f_exo_sta_0_living_room_table.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_ci_f_exo_sta_0_living_room_table.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_ci_f_exo_sta_0_living_room_table.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Viewpoint Geometry, Relative Spatial Relations, Topology and Containment","perspective":"Exocentric","caption":"How does the camera move throughout the video?: A. It stays fixed at side view, B. It alternates between side view and overhead peeks on each container, C. It rotates 360 degrees around the table, D. It zooms in and out on a single container","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_ci_f_exo_sta_0_living_room_table.json"},{"id":"vgenst_ci_f_exo_sta_12_library_reading_desk","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_ci_f_exo_sta_12_library_reading_desk.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_ci_f_exo_sta_12_library_reading_desk.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_ci_f_exo_sta_12_library_reading_desk.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Viewpoint Geometry, Relative Spatial Relations, Topology and Containment","perspective":"Exocentric","caption":"How does the camera move throughout the video?: A. It stays fixed at side view, B. It alternates between side view and overhead peeks on each container, C. It rotates 360 degrees around the table, D. It zooms in and out on a single container","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_ci_f_exo_sta_12_library_reading_desk.json"},{"id":"vgenst_ci_f_exo_sta_23_auto_mechanic_shop_table","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_ci_f_exo_sta_23_auto_mechanic_shop_table.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_ci_f_exo_sta_23_auto_mechanic_shop_table.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_ci_f_exo_sta_23_auto_mechanic_shop_table.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Viewpoint Geometry, Relative Spatial Relations, Topology and Containment","perspective":"Exocentric","caption":"How does the camera move throughout the video?: A. It stays fixed at side view, B. It alternates between side view and overhead peeks on each container, C. It rotates 360 degrees around the table, D. It zooms in and out on a single container","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_ci_f_exo_sta_23_auto_mechanic_shop_table.json"},{"id":"vgenst_ci_f_exo_sta_2_bedroom_table","videoPath":"curated/spatial-world-model/v7/vgenst-bench/videos/viewpoint_motion/vgenst_ci_f_exo_sta_2_bedroom_table.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/vgenst-bench/videos/viewpoint_motion/vgenst_ci_f_exo_sta_2_bedroom_table.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/vgenst-bench/initial_frames/viewpoint_motion/vgenst_ci_f_exo_sta_2_bedroom_table.png","sourceDataset":"VGenST-Bench","suggestedTrack":"viewpoint_motion","scene":"living space","spatialAbility":"Viewpoint Geometry, Topology and Containment","perspective":"Exocentric","caption":"How many object types appear in both containers (i.e., the number of shared objects types)?: A. 0, B. 1, C. 2, D. 3","annotationPath":"curated/spatial-world-model/v7/vgenst-bench/annotations/viewpoint_motion/vgenst_ci_f_exo_sta_2_bedroom_table.json"},{"id":"vgenst_ci_f_exo_sta_34_holographic_briefing_room_table","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_ci_f_exo_sta_34_holographic_briefing_room_table.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_ci_f_exo_sta_34_holographic_briefing_room_table.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_ci_f_exo_sta_34_holographic_briefing_room_table.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Viewpoint Geometry, Relative Spatial Relations, Topology and Containment","perspective":"Exocentric","caption":"How does the camera move throughout the video?: A. It stays fixed at side view, B. It alternates between side view and overhead peeks on each container, C. It rotates 360 degrees around the table, D. It zooms in and out on a single container","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_ci_f_exo_sta_34_holographic_briefing_room_table.json"},{"id":"vgenst_ci_f_exo_sta_45_gothic_vampire_castle_dining_table","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_ci_f_exo_sta_45_gothic_vampire_castle_dining_table.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_ci_f_exo_sta_45_gothic_vampire_castle_dining_table.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_ci_f_exo_sta_45_gothic_vampire_castle_dining_table.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Viewpoint Geometry, Relative Spatial Relations, Topology and Containment","perspective":"Exocentric","caption":"How does the camera move throughout the video?: A. It stays fixed at side view, B. It alternates between side view and overhead peeks on each container, C. It rotates 360 degrees around the table, D. It zooms in and out on a single container","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_ci_f_exo_sta_45_gothic_vampire_castle_dining_table.json"},{"id":"vgenst_ci_f_exo_sta_55_vintage_train_cabin_table","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_ci_f_exo_sta_55_vintage_train_cabin_table.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_ci_f_exo_sta_55_vintage_train_cabin_table.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_ci_f_exo_sta_55_vintage_train_cabin_table.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Viewpoint Geometry, Relative Spatial Relations, Topology and Containment","perspective":"Exocentric","caption":"How does the camera move throughout the video?: A. It stays fixed at side view, B. It alternates between side view and overhead peeks on each container, C. It rotates 360 degrees around the table, D. It zooms in and out on a single container","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_ci_f_exo_sta_55_vintage_train_cabin_table.json"},{"id":"vgenst_ci_f_exo_sta_66_safari_table","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_ci_f_exo_sta_66_safari_table.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_ci_f_exo_sta_66_safari_table.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_ci_f_exo_sta_66_safari_table.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Viewpoint Geometry, Relative Spatial Relations, Topology and Containment","perspective":"Exocentric","caption":"How does the camera move throughout the video?: A. It stays fixed at side view, B. It alternates between side view and overhead peeks on each container, C. It rotates 360 degrees around the table, D. It zooms in and out on a single container","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_ci_f_exo_sta_66_safari_table.json"},{"id":"vgenst_ci_f_exo_sta_77_makeup_artists_vanity_station","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_ci_f_exo_sta_77_makeup_artists_vanity_station.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_ci_f_exo_sta_77_makeup_artists_vanity_station.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_ci_f_exo_sta_77_makeup_artists_vanity_station.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"driving","spatialAbility":"Viewpoint Geometry, Relative Spatial Relations, Topology and Containment","perspective":"Exocentric","caption":"How does the camera move throughout the video?: A. It stays fixed at side view, B. It alternates between side view and overhead peeks on each container, C. It rotates 360 degrees around the table, D. It zooms in and out on a single container","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_ci_f_exo_sta_77_makeup_artists_vanity_station.json"},{"id":"vgenst_ci_f_exo_sta_88_boxing_gym_equipment_desk","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_ci_f_exo_sta_88_boxing_gym_equipment_desk.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_ci_f_exo_sta_88_boxing_gym_equipment_desk.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_ci_f_exo_sta_88_boxing_gym_equipment_desk.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"driving","spatialAbility":"Viewpoint Geometry, Relative Spatial Relations, Topology and Containment","perspective":"Exocentric","caption":"How does the camera move throughout the video?: A. It stays fixed at side view, B. It alternates between side view and overhead peeks on each container, C. It rotates 360 degrees around the table, D. It zooms in and out on a single container","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_ci_f_exo_sta_88_boxing_gym_equipment_desk.json"},{"id":"vgenst_ci_f_exo_sta_99_magicians_stage_prop_table","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_ci_f_exo_sta_99_magicians_stage_prop_table.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_ci_f_exo_sta_99_magicians_stage_prop_table.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_ci_f_exo_sta_99_magicians_stage_prop_table.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Viewpoint Geometry, Relative Spatial Relations, Topology and Containment","perspective":"Exocentric","caption":"How does the camera move throughout the video?: A. It stays fixed at side view, B. It alternates between side view and overhead peeks on each container, C. It rotates 360 degrees around the table, D. It zooms in and out on a single container","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_ci_f_exo_sta_99_magicians_stage_prop_table.json"},{"id":"vgenst_cm_f_exo_dyn_0_spaceship_bridge_command_console","videoPath":"curated/spatial-world-model/v7/vgenst-bench/videos/scene_motion/vgenst_cm_f_exo_dyn_0_spaceship_bridge_command_console.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/vgenst-bench/videos/scene_motion/vgenst_cm_f_exo_dyn_0_spaceship_bridge_command_console.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/vgenst-bench/initial_frames/scene_motion/vgenst_cm_f_exo_dyn_0_spaceship_bridge_command_console.png","sourceDataset":"VGenST-Bench","suggestedTrack":"scene_motion","scene":"object physics","spatialAbility":"Relative Spatial Relations, Relative and Coupled Motion","perspective":"Exocentric","caption":"If the agent had pressed the command button on the right first instead of the one on the left, which status pillar would activate first?: A. The status pillar on the left, B. The status pillar on the right, C. Both simultaneously","annotationPath":"curated/spatial-world-model/v7/vgenst-bench/annotations/scene_motion/vgenst_cm_f_exo_dyn_0_spaceship_bridge_command_console.json"},{"id":"vgenst_cm_f_exo_dyn_12_steampunk_airship_helm_console","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_cm_f_exo_dyn_12_steampunk_airship_helm_console.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_cm_f_exo_dyn_12_steampunk_airship_helm_console.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_cm_f_exo_dyn_12_steampunk_airship_helm_console.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Direction and Trajectory, Topology and Containment","perspective":"Exocentric","caption":"What happens to the Vacuum Tube on the left after the Copper Lever on the left is pulled?: A. It glows bright orange, B. It turns ON (glows green), C. It activates: green LEDs illuminate brightly and propellers begin to spin, D. It disappears from view","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_cm_f_exo_dyn_12_steampunk_airship_helm_console.json"},{"id":"vgenst_cm_f_exo_dyn_15_fortune_tellers_crystal_ball_table","videoPath":"curated/spatial-world-model/v7/vgenst-bench/videos/scene_motion/vgenst_cm_f_exo_dyn_15_fortune_tellers_crystal_ball_table.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/vgenst-bench/videos/scene_motion/vgenst_cm_f_exo_dyn_15_fortune_tellers_crystal_ball_table.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/vgenst-bench/initial_frames/scene_motion/vgenst_cm_f_exo_dyn_15_fortune_tellers_crystal_ball_table.png","sourceDataset":"VGenST-Bench","suggestedTrack":"scene_motion","scene":"object physics","spatialAbility":"Direction and Trajectory, Relative and Coupled Motion","perspective":"Exocentric","caption":"If the agent had activated the runestone on the right first instead of the one on the left, which crystal ball would activate first?: A. The crystal ball on the left, B. The crystal ball on the right, C. Both simultaneously","annotationPath":"curated/spatial-world-model/v7/vgenst-bench/annotations/scene_motion/vgenst_cm_f_exo_dyn_15_fortune_tellers_crystal_ball_table.json"},{"id":"vgenst_cm_f_exo_dyn_1_cyberpunk_hackers_neon_desk","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_cm_f_exo_dyn_1_cyberpunk_hackers_neon_desk.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_cm_f_exo_dyn_1_cyberpunk_hackers_neon_desk.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_cm_f_exo_dyn_1_cyberpunk_hackers_neon_desk.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Direction and Trajectory, Topology and Containment","perspective":"Exocentric","caption":"What action does the agent perform in the video?: A. Looks through a microscope, B. Flips the Dull Red Switches on the console, C. Presses the Scanner Pads on the console, D. Pulls the Red Levers on the console","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_cm_f_exo_dyn_1_cyberpunk_hackers_neon_desk.json"},{"id":"vgenst_cm_f_exo_dyn_24_mining_operations_control_desk","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_cm_f_exo_dyn_24_mining_operations_control_desk.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_cm_f_exo_dyn_24_mining_operations_control_desk.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_cm_f_exo_dyn_24_mining_operations_control_desk.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Direction and Trajectory, Topology and Containment","perspective":"Exocentric","caption":"What happens to the Warning Light on the right after the Warning Button on the right is pressed?: A. It activates — Right Warning Light activates (yellow spin), B. It begins moving belt segments, C. It activates — its LED headlights turn on brightly, D. It propellers immediately spin up rapidly","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_cm_f_exo_dyn_24_mining_operations_control_desk.json"},{"id":"vgenst_cm_f_exo_dyn_34_magicians_illusion_prop_table","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_cm_f_exo_dyn_34_magicians_illusion_prop_table.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_cm_f_exo_dyn_34_magicians_illusion_prop_table.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_cm_f_exo_dyn_34_magicians_illusion_prop_table.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Direction and Trajectory, Topology and Containment","perspective":"Exocentric","caption":"What happens to the Velvet Box on the right after the Brass Button on the right is pressed?: A. It needle immediately swings from zero to high pressure, B. It begins to glow with blue internal light and rotate slowly, C. It opens its lid synchronously with the press, D. It illuminates with red light and extends slightly upwards","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_cm_f_exo_dyn_34_magicians_illusion_prop_table.json"},{"id":"vgenst_cm_f_exo_dyn_45_movie_theater_ticket_booth","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_cm_f_exo_dyn_45_movie_theater_ticket_booth.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_cm_f_exo_dyn_45_movie_theater_ticket_booth.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_cm_f_exo_dyn_45_movie_theater_ticket_booth.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Direction and Trajectory, Topology and Containment","perspective":"Exocentric","caption":"What action does the agent perform in the video?: A. Presses the Red Activation Buttons on the console, B. Presses the Selection Buttons on the console, C. Presses the Combo Buttons on the console, D. Presses the Control Buttons on the console","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_cm_f_exo_dyn_45_movie_theater_ticket_booth.json"},{"id":"vgenst_cm_f_exo_dyn_56_deep_sea_submersible_control_panel","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_cm_f_exo_dyn_56_deep_sea_submersible_control_panel.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_cm_f_exo_dyn_56_deep_sea_submersible_control_panel.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_cm_f_exo_dyn_56_deep_sea_submersible_control_panel.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Direction and Trajectory, Topology and Containment","perspective":"Exocentric","caption":"What action does the agent perform in the video?: A. Flips the Toggle Switches on the console, B. Turns the Control Knobs on the console, C. Talks into a phone, D. Flips the DAC Mode Switches on the console","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_cm_f_exo_dyn_56_deep_sea_submersible_control_panel.json"},{"id":"vgenst_cm_f_exo_dyn_67_djs_bedroom_mixing_desk","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_cm_f_exo_dyn_67_djs_bedroom_mixing_desk.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_cm_f_exo_dyn_67_djs_bedroom_mixing_desk.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_cm_f_exo_dyn_67_djs_bedroom_mixing_desk.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Direction and Trajectory, Topology and Containment","perspective":"Exocentric","caption":"What happens to the Circular LED on the left after the Cue Button on the left is pressed?: A. It activates — Right Warning Light activates (yellow spin), B. It changes color repeatedly, C. It needle immediately swings from zero to high pressure, D. It remains completely still","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_cm_f_exo_dyn_67_djs_bedroom_mixing_desk.json"},{"id":"vgenst_cm_f_exo_dyn_77_emergency_911_dispatch_desk","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_cm_f_exo_dyn_77_emergency_911_dispatch_desk.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_cm_f_exo_dyn_77_emergency_911_dispatch_desk.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_cm_f_exo_dyn_77_emergency_911_dispatch_desk.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Direction and Trajectory, Topology and Containment","perspective":"Exocentric","caption":"What happens to the Red Alert Strobe on the left after the Red Emergency Button on the left is pressed?: A. It activates — Right Lantern lights up, B. It flashes ON, C. It clenches its fingers into a fist, D. It activates — Right Orb glows bright red","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_cm_f_exo_dyn_77_emergency_911_dispatch_desk.json"},{"id":"vgenst_cm_f_exo_dyn_88_naval_ship_bridge_telegraph_station","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_cm_f_exo_dyn_88_naval_ship_bridge_telegraph_station.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_cm_f_exo_dyn_88_naval_ship_bridge_telegraph_station.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_cm_f_exo_dyn_88_naval_ship_bridge_telegraph_station.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"daily activity","spatialAbility":"Relative Spatial Relations, Direction and Trajectory, Topology and Containment","perspective":"Exocentric","caption":"What happens to the Indicator Dial on the right after the Brass Telegraph Lever on the right is pulled?: A. It reacts immediately, B. It turns ON immediately, C. It turns ON (Yellow), D. It flips up into display position","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_cm_f_exo_dyn_88_naval_ship_bridge_telegraph_station.json"},{"id":"vgenst_cm_f_exo_dyn_99_vr_arcade_setup_desk","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_cm_f_exo_dyn_99_vr_arcade_setup_desk.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_cm_f_exo_dyn_99_vr_arcade_setup_desk.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_cm_f_exo_dyn_99_vr_arcade_setup_desk.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Direction and Trajectory, Topology and Containment","perspective":"Exocentric","caption":"What action does the agent perform in the video?: A. Activates the Runestones on the console, B. Pulls the Brass Levers on the console, C. Presses the Red Control Buttons on the console, D. Presses the Activation Buttons on the console","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_cm_f_exo_dyn_99_vr_arcade_setup_desk.json"},{"id":"vgenst_de_v_ego_sta_0_contemporary_art_gallery_corner","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_de_v_ego_sta_0_contemporary_art_gallery_corner.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_de_v_ego_sta_0_contemporary_art_gallery_corner.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/View_motion/vgenst_de_v_ego_sta_0_contemporary_art_gallery_corner.png","sourceDataset":"VGenST-Bench","suggestedTrack":"View motion","scene":"urban","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"How does the camera move throughout the video?: A. It stays fixed at the starting position, B. It walks straight forward without turning, C. It walks forward, makes a turn, D. It rotates in place without moving","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/View_motion/vgenst_de_v_ego_sta_0_contemporary_art_gallery_corner.json"},{"id":"vgenst_de_v_ego_sta_12_optics_technology_showcase_l-corridor","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_de_v_ego_sta_12_optics_technology_showcase_l-corridor.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_de_v_ego_sta_12_optics_technology_showcase_l-corridor.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/View_motion/vgenst_de_v_ego_sta_12_optics_technology_showcase_l-corridor.png","sourceDataset":"VGenST-Bench","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"How does the camera move throughout the video?: A. It stays fixed at the starting position, B. It walks straight forward without turning, C. It walks forward, makes a turn, D. It rotates in place without moving","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/View_motion/vgenst_de_v_ego_sta_12_optics_technology_showcase_l-corridor.json"},{"id":"vgenst_de_v_ego_sta_1_school_of_visual_arts_corridor_gallery","videoPath":"curated/spatial-world-model/v7/vgenst-bench/videos/viewpoint_motion/vgenst_de_v_ego_sta_1_school_of_visual_arts_corridor_gallery.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/vgenst-bench/videos/viewpoint_motion/vgenst_de_v_ego_sta_1_school_of_visual_arts_corridor_gallery.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/vgenst-bench/initial_frames/viewpoint_motion/vgenst_de_v_ego_sta_1_school_of_visual_arts_corridor_gallery.png","sourceDataset":"VGenST-Bench","suggestedTrack":"viewpoint_motion","scene":"urban","spatialAbility":"Direction and Trajectory, Viewpoint Geometry","perspective":"Egocentric","caption":"At the final position, in which direction (using clock positions where 12 o'clock is straight ahead) is the starting point located?: A. 12 o'clock (directly ahead), B. 4-5 o'clock (back-right), C. 7-8 o'clock (back-left), D. 6 o'clock (directly behind)","annotationPath":"curated/spatial-world-model/v7/vgenst-bench/annotations/viewpoint_motion/vgenst_de_v_ego_sta_1_school_of_visual_arts_corridor_gallery.json"},{"id":"vgenst_de_v_ego_sta_23_geological_exhibit_wing_hallway","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_de_v_ego_sta_23_geological_exhibit_wing_hallway.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_de_v_ego_sta_23_geological_exhibit_wing_hallway.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/View_motion/vgenst_de_v_ego_sta_23_geological_exhibit_wing_hallway.png","sourceDataset":"VGenST-Bench","suggestedTrack":"View motion","scene":"daily activity","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"In which direction does the camera turn at the corner?: A. Left, B. Right, C. It does not turn, D. It makes a U-turn (180 degrees)","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/View_motion/vgenst_de_v_ego_sta_23_geological_exhibit_wing_hallway.json"},{"id":"vgenst_de_v_ego_sta_34_lounge_bar_l-shaped_corridor","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_de_v_ego_sta_34_lounge_bar_l-shaped_corridor.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_de_v_ego_sta_34_lounge_bar_l-shaped_corridor.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/View_motion/vgenst_de_v_ego_sta_34_lounge_bar_l-shaped_corridor.png","sourceDataset":"VGenST-Bench","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"In which direction does the camera turn at the corner?: A. Left, B. Right, C. It does not turn, D. It makes a U-turn (180 degrees)","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/View_motion/vgenst_de_v_ego_sta_34_lounge_bar_l-shaped_corridor.json"},{"id":"vgenst_de_v_ego_sta_45_data_center_l-aisle","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_de_v_ego_sta_45_data_center_l-aisle.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_de_v_ego_sta_45_data_center_l-aisle.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/View_motion/vgenst_de_v_ego_sta_45_data_center_l-aisle.png","sourceDataset":"VGenST-Bench","suggestedTrack":"View motion","scene":"daily activity","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"How does the camera move throughout the video?: A. It stays fixed at the starting position, B. It walks straight forward without turning, C. It walks forward, makes a turn, D. It rotates in place without moving","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/View_motion/vgenst_de_v_ego_sta_45_data_center_l-aisle.json"},{"id":"vgenst_de_v_ego_sta_55_modern_loft_apartment_corner","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_de_v_ego_sta_55_modern_loft_apartment_corner.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_de_v_ego_sta_55_modern_loft_apartment_corner.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/View_motion/vgenst_de_v_ego_sta_55_modern_loft_apartment_corner.png","sourceDataset":"VGenST-Bench","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"In which direction does the camera turn at the corner?: A. Left, B. Right, C. It does not turn, D. It makes a U-turn (180 degrees)","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/View_motion/vgenst_de_v_ego_sta_55_modern_loft_apartment_corner.json"},{"id":"vgenst_de_v_ego_sta_66_sporting_goods_camping_l-aisle_corner","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_de_v_ego_sta_66_sporting_goods_camping_l-aisle_corner.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_de_v_ego_sta_66_sporting_goods_camping_l-aisle_corner.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/View_motion/vgenst_de_v_ego_sta_66_sporting_goods_camping_l-aisle_corner.png","sourceDataset":"VGenST-Bench","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"In which direction does the camera turn at the corner?: A. Left, B. Right, C. It does not turn, D. It makes a U-turn (180 degrees)","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/View_motion/vgenst_de_v_ego_sta_66_sporting_goods_camping_l-aisle_corner.json"},{"id":"vgenst_de_v_ego_sta_77_textile_factory_loom_l-aisle","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_de_v_ego_sta_77_textile_factory_loom_l-aisle.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_de_v_ego_sta_77_textile_factory_loom_l-aisle.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/View_motion/vgenst_de_v_ego_sta_77_textile_factory_loom_l-aisle.png","sourceDataset":"VGenST-Bench","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"How does the camera move throughout the video?: A. It stays fixed at the starting position, B. It walks straight forward without turning, C. It walks forward, makes a turn, D. It rotates in place without moving","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/View_motion/vgenst_de_v_ego_sta_77_textile_factory_loom_l-aisle.json"},{"id":"vgenst_de_v_ego_sta_88_intergalactic_zoo_l-shaped_enclosure_corridor","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_de_v_ego_sta_88_intergalactic_zoo_l-shaped_enclosure_corridor.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_de_v_ego_sta_88_intergalactic_zoo_l-shaped_enclosure_corridor.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/View_motion/vgenst_de_v_ego_sta_88_intergalactic_zoo_l-shaped_enclosure_corridor.png","sourceDataset":"VGenST-Bench","suggestedTrack":"View motion","scene":"daily activity","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"How does the camera move throughout the video?: A. It stays fixed at the starting position, B. It walks straight forward without turning, C. It walks forward, makes a turn, D. It rotates in place without moving","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/View_motion/vgenst_de_v_ego_sta_88_intergalactic_zoo_l-shaped_enclosure_corridor.json"},{"id":"vgenst_de_v_ego_sta_99_old_west_saloon_l-shaped_back_hallway","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_de_v_ego_sta_99_old_west_saloon_l-shaped_back_hallway.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_de_v_ego_sta_99_old_west_saloon_l-shaped_back_hallway.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/View_motion/vgenst_de_v_ego_sta_99_old_west_saloon_l-shaped_back_hallway.png","sourceDataset":"VGenST-Bench","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"In which direction does the camera turn at the corner?: A. Left, B. Right, C. It does not turn, D. It makes a U-turn (180 degrees)","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/View_motion/vgenst_de_v_ego_sta_99_old_west_saloon_l-shaped_back_hallway.json"},{"id":"vgenst_ds_e_ego_sta_0_international_airport_main_concourse","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_ds_e_ego_sta_0_international_airport_main_concourse.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_ds_e_ego_sta_0_international_airport_main_concourse.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/View_motion/vgenst_ds_e_ego_sta_0_international_airport_main_concourse.png","sourceDataset":"VGenST-Bench","suggestedTrack":"View motion","scene":"daily activity","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"How does the camera move throughout the video?: A. It walks straight forward, B. It walks forward then turns left, C. It walks forward then turns right, D. It stays fixed in place","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/View_motion/vgenst_ds_e_ego_sta_0_international_airport_main_concourse.json"},{"id":"vgenst_ds_e_ego_sta_11_veterinary_teaching_hospital_main_hall","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_ds_e_ego_sta_11_veterinary_teaching_hospital_main_hall.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_ds_e_ego_sta_11_veterinary_teaching_hospital_main_hall.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/View_motion/vgenst_ds_e_ego_sta_11_veterinary_teaching_hospital_main_hall.png","sourceDataset":"VGenST-Bench","suggestedTrack":"View motion","scene":"daily activity","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"How does the camera move throughout the video?: A. It walks straight forward, B. It walks forward then turns left, C. It walks forward then turns right, D. It stays fixed in place","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/View_motion/vgenst_ds_e_ego_sta_11_veterinary_teaching_hospital_main_hall.json"},{"id":"vgenst_ds_e_ego_sta_22_particle_accelerator_circular_tunnel","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_ds_e_ego_sta_22_particle_accelerator_circular_tunnel.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_ds_e_ego_sta_22_particle_accelerator_circular_tunnel.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/View_motion/vgenst_ds_e_ego_sta_22_particle_accelerator_circular_tunnel.png","sourceDataset":"VGenST-Bench","suggestedTrack":"View motion","scene":"daily activity","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"How does the camera move throughout the video?: A. It walks straight forward, B. It walks forward then turns left, C. It walks forward then turns right, D. It stays fixed in place","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/View_motion/vgenst_ds_e_ego_sta_22_particle_accelerator_circular_tunnel.json"},{"id":"vgenst_ds_e_ego_sta_33_luxury_outlet_village_outdoor_promenade","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_ds_e_ego_sta_33_luxury_outlet_village_outdoor_promenade.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_ds_e_ego_sta_33_luxury_outlet_village_outdoor_promenade.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/View_motion/vgenst_ds_e_ego_sta_33_luxury_outlet_village_outdoor_promenade.png","sourceDataset":"VGenST-Bench","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"How does the camera move throughout the video?: A. It walks straight forward, B. It walks forward then turns left, C. It walks forward then turns right, D. It stays fixed in place","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/View_motion/vgenst_ds_e_ego_sta_33_luxury_outlet_village_outdoor_promenade.json"},{"id":"vgenst_ds_e_ego_sta_44_grand_opera_house_cloakroom_corridor","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_ds_e_ego_sta_44_grand_opera_house_cloakroom_corridor.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_ds_e_ego_sta_44_grand_opera_house_cloakroom_corridor.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/View_motion/vgenst_ds_e_ego_sta_44_grand_opera_house_cloakroom_corridor.png","sourceDataset":"VGenST-Bench","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"How does the camera move throughout the video?: A. It walks straight forward, B. It walks forward then turns left, C. It walks forward then turns right, D. It stays fixed in place","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/View_motion/vgenst_ds_e_ego_sta_44_grand_opera_house_cloakroom_corridor.json"},{"id":"vgenst_ds_e_ego_sta_55_semiconductor_cleanroom_facility_corridor","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_ds_e_ego_sta_55_semiconductor_cleanroom_facility_corridor.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_ds_e_ego_sta_55_semiconductor_cleanroom_facility_corridor.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/View_motion/vgenst_ds_e_ego_sta_55_semiconductor_cleanroom_facility_corridor.png","sourceDataset":"VGenST-Bench","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"How does the camera move throughout the video?: A. It walks straight forward, B. It walks forward then turns left, C. It walks forward then turns right, D. It stays fixed in place","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/View_motion/vgenst_ds_e_ego_sta_55_semiconductor_cleanroom_facility_corridor.json"},{"id":"vgenst_ds_e_ego_sta_66_tax_bureau_public_service_hallway","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_ds_e_ego_sta_66_tax_bureau_public_service_hallway.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_ds_e_ego_sta_66_tax_bureau_public_service_hallway.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/View_motion/vgenst_ds_e_ego_sta_66_tax_bureau_public_service_hallway.png","sourceDataset":"VGenST-Bench","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"How does the camera move throughout the video?: A. It walks straight forward, B. It walks forward then turns left, C. It walks forward then turns right, D. It stays fixed in place","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/View_motion/vgenst_ds_e_ego_sta_66_tax_bureau_public_service_hallway.json"},{"id":"vgenst_ds_e_ego_sta_77_capsule_hotel_network_corridor","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_ds_e_ego_sta_77_capsule_hotel_network_corridor.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_ds_e_ego_sta_77_capsule_hotel_network_corridor.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/View_motion/vgenst_ds_e_ego_sta_77_capsule_hotel_network_corridor.png","sourceDataset":"VGenST-Bench","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"How does the camera move throughout the video?: A. It walks straight forward, B. It walks forward then turns left, C. It walks forward then turns right, D. It stays fixed in place","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/View_motion/vgenst_ds_e_ego_sta_77_capsule_hotel_network_corridor.json"},{"id":"vgenst_ds_e_ego_sta_88_holographic_archive_information_aisle","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_ds_e_ego_sta_88_holographic_archive_information_aisle.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_ds_e_ego_sta_88_holographic_archive_information_aisle.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/View_motion/vgenst_ds_e_ego_sta_88_holographic_archive_information_aisle.png","sourceDataset":"VGenST-Bench","suggestedTrack":"View motion","scene":"daily activity","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"How does the camera move throughout the video?: A. It walks straight forward, B. It walks forward then turns left, C. It walks forward then turns right, D. It stays fixed in place","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/View_motion/vgenst_ds_e_ego_sta_88_holographic_archive_information_aisle.json"},{"id":"vgenst_ds_e_ego_sta_99_magical_creature_zoo","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_ds_e_ego_sta_99_magical_creature_zoo.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_ds_e_ego_sta_99_magical_creature_zoo.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/View_motion/vgenst_ds_e_ego_sta_99_magical_creature_zoo.png","sourceDataset":"VGenST-Bench","suggestedTrack":"View motion","scene":"daily activity","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Egocentric","caption":"How does the camera move throughout the video?: A. It walks straight forward, B. It walks forward then turns left, C. It walks forward then turns right, D. It stays fixed in place","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/View_motion/vgenst_ds_e_ego_sta_99_magical_creature_zoo.json"},{"id":"vgenst_ho_v_exo_sta_0_minimalist_living_room","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_ho_v_exo_sta_0_minimalist_living_room.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_ho_v_exo_sta_0_minimalist_living_room.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_ho_v_exo_sta_0_minimalist_living_room.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Viewpoint Geometry, Relative Spatial Relations, Topology and Containment","perspective":"Exocentric","caption":"How does the camera move throughout the video?: A. It pans horizontally from left to right, B. It tilts vertically from bottom to top, C. It zooms in and out, D. It rotates around the room","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_ho_v_exo_sta_0_minimalist_living_room.json"},{"id":"vgenst_ho_v_exo_sta_11_childrens_bedroom","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_ho_v_exo_sta_11_childrens_bedroom.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_ho_v_exo_sta_11_childrens_bedroom.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_ho_v_exo_sta_11_childrens_bedroom.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Viewpoint Geometry, Relative Spatial Relations, Topology and Containment","perspective":"Exocentric","caption":"In which direction does the camera tilt?: A. From bottom to top, B. From top to bottom, C. From left to right, D. From right to left","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_ho_v_exo_sta_11_childrens_bedroom.json"},{"id":"vgenst_ho_v_exo_sta_22_architects_studio","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_ho_v_exo_sta_22_architects_studio.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_ho_v_exo_sta_22_architects_studio.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_ho_v_exo_sta_22_architects_studio.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"driving","spatialAbility":"Viewpoint Geometry, Relative Spatial Relations, Topology and Containment","perspective":"Exocentric","caption":"How does the camera move throughout the video?: A. It pans horizontally from left to right, B. It tilts vertically from top to bottom, C. It zooms in and out, D. It rotates around the room","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_ho_v_exo_sta_22_architects_studio.json"},{"id":"vgenst_ho_v_exo_sta_33_restaurant_kitchen_pass","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_ho_v_exo_sta_33_restaurant_kitchen_pass.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_ho_v_exo_sta_33_restaurant_kitchen_pass.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_ho_v_exo_sta_33_restaurant_kitchen_pass.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Viewpoint Geometry, Relative Spatial Relations, Topology and Containment","perspective":"Exocentric","caption":"In which direction does the camera tilt?: A. From bottom to top, B. From top to bottom, C. From left to right, D. From right to left","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_ho_v_exo_sta_33_restaurant_kitchen_pass.json"},{"id":"vgenst_ho_v_exo_sta_44_pottery_studio","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_ho_v_exo_sta_44_pottery_studio.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_ho_v_exo_sta_44_pottery_studio.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_ho_v_exo_sta_44_pottery_studio.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"daily activity","spatialAbility":"Viewpoint Geometry, Relative Spatial Relations, Topology and Containment","perspective":"Exocentric","caption":"How does the camera move throughout the video?: A. It pans horizontally from left to right, B. It tilts vertically from bottom to top, C. It zooms in and out, D. It rotates around the room","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_ho_v_exo_sta_44_pottery_studio.json"},{"id":"vgenst_ho_v_exo_sta_55_sporting_goods_store","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_ho_v_exo_sta_55_sporting_goods_store.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_ho_v_exo_sta_55_sporting_goods_store.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_ho_v_exo_sta_55_sporting_goods_store.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Viewpoint Geometry, Relative Spatial Relations, Topology and Containment","perspective":"Exocentric","caption":"In which direction does the camera tilt?: A. From bottom to top, B. From top to bottom, C. From left to right, D. From right to left","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_ho_v_exo_sta_55_sporting_goods_store.json"},{"id":"vgenst_ho_v_exo_sta_66_dance_studio","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_ho_v_exo_sta_66_dance_studio.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_ho_v_exo_sta_66_dance_studio.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_ho_v_exo_sta_66_dance_studio.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Viewpoint Geometry, Relative Spatial Relations, Topology and Containment","perspective":"Exocentric","caption":"How does the camera move throughout the video?: A. It pans horizontally from left to right, B. It tilts vertically from top to bottom, C. It zooms in and out, D. It rotates around the room","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_ho_v_exo_sta_66_dance_studio.json"},{"id":"vgenst_ho_v_exo_sta_77_science_classroom","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_ho_v_exo_sta_77_science_classroom.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_ho_v_exo_sta_77_science_classroom.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_ho_v_exo_sta_77_science_classroom.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Viewpoint Geometry, Relative Spatial Relations, Topology and Containment","perspective":"Exocentric","caption":"In which direction does the camera tilt?: A. From bottom to top, B. From top to bottom, C. From left to right, D. From right to left","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_ho_v_exo_sta_77_science_classroom.json"},{"id":"vgenst_ho_v_exo_sta_88_arcade_corner","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_ho_v_exo_sta_88_arcade_corner.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_ho_v_exo_sta_88_arcade_corner.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_ho_v_exo_sta_88_arcade_corner.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"daily activity","spatialAbility":"Viewpoint Geometry, Relative Spatial Relations, Topology and Containment","perspective":"Exocentric","caption":"How does the camera move throughout the video?: A. It pans horizontally from left to right, B. It tilts vertically from bottom to top, C. It zooms in and out, D. It rotates around the room","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_ho_v_exo_sta_88_arcade_corner.json"},{"id":"vgenst_ho_v_exo_sta_99_dwarven_armory","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_ho_v_exo_sta_99_dwarven_armory.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_ho_v_exo_sta_99_dwarven_armory.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_ho_v_exo_sta_99_dwarven_armory.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Viewpoint Geometry, Relative Spatial Relations, Topology and Containment","perspective":"Exocentric","caption":"In which direction does the camera tilt?: A. From bottom to top, B. From top to bottom, C. From left to right, D. From right to left","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_ho_v_exo_sta_99_dwarven_armory.json"},{"id":"vgenst_io_v_ego_dyn_0_living_room_with_coffee_table_and_side_shelf","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_io_v_ego_dyn_0_living_room_with_coffee_table_and_side_shelf.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_io_v_ego_dyn_0_living_room_with_coffee_table_and_side_shelf.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_io_v_ego_dyn_0_living_room_with_coffee_table_and_side_shelf.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory, Topology and Containment","perspective":"Egocentric","caption":"What action does the agent perform on one of the objects?: A. Picks it up and places it on another surface, B. Pushes it off the table, C. Rearranges its position on the same surface, D. Breaks it into pieces","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_io_v_ego_dyn_0_living_room_with_coffee_table_and_side_shelf.json"},{"id":"vgenst_io_v_ego_dyn_12_hotel_room_with_writing_desk_and_white_marble_side_table","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_io_v_ego_dyn_12_hotel_room_with_writing_desk_and_white_marble_side_table.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_io_v_ego_dyn_12_hotel_room_with_writing_desk_and_white_marble_side_table.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_io_v_ego_dyn_12_hotel_room_with_writing_desk_and_white_marble_side_table.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory, Topology and Containment","perspective":"Egocentric","caption":"Which object does the agent pick up?: A. Brown Leather Passport Holder, B. Silver Pen, C. White Hotel Keycard","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_io_v_ego_dyn_12_hotel_room_with_writing_desk_and_white_marble_side_table.json"},{"id":"vgenst_io_v_ego_dyn_23_architects_studio_with_drafting_table_and_supply_shelf","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_io_v_ego_dyn_23_architects_studio_with_drafting_table_and_supply_shelf.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_io_v_ego_dyn_23_architects_studio_with_drafting_table_and_supply_shelf.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_io_v_ego_dyn_23_architects_studio_with_drafting_table_and_supply_shelf.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory, Topology and Containment","perspective":"Egocentric","caption":"Which object does the agent pick up?: A. Yellow Mechanical Pencil, B. Silver Drafting Compass, C. Red Eraser Block","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_io_v_ego_dyn_23_architects_studio_with_drafting_table_and_supply_shelf.json"},{"id":"vgenst_io_v_ego_dyn_33_restaurant_kitchen_with_pass_counter_and_plating_station","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_io_v_ego_dyn_33_restaurant_kitchen_with_pass_counter_and_plating_station.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_io_v_ego_dyn_33_restaurant_kitchen_with_pass_counter_and_plating_station.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_io_v_ego_dyn_33_restaurant_kitchen_with_pass_counter_and_plating_station.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory, Topology and Containment","perspective":"Egocentric","caption":"From which position on the Pass Counter does the agent pick up the object?: A. Left, B. Center, C. Right","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_io_v_ego_dyn_33_restaurant_kitchen_with_pass_counter_and_plating_station.json"},{"id":"vgenst_io_v_ego_dyn_3_cozy_den_with_ottoman_tray_and_fireplace_mantel","videoPath":"curated/spatial-world-model/v7/vgenst-bench/videos/scene_motion/vgenst_io_v_ego_dyn_3_cozy_den_with_ottoman_tray_and_fireplace_mantel.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/vgenst-bench/videos/scene_motion/vgenst_io_v_ego_dyn_3_cozy_den_with_ottoman_tray_and_fireplace_mantel.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/vgenst-bench/initial_frames/scene_motion/vgenst_io_v_ego_dyn_3_cozy_den_with_ottoman_tray_and_fireplace_mantel.png","sourceDataset":"VGenST-Bench","suggestedTrack":"scene_motion","scene":"living space","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"From the camera's perspective, what is the left-to-right order of objects on the Ottoman Tray?: A. Brown Leather Notebook, Red Stoneware Mug, Beige Knit Coaster Set, B. Red Stoneware Mug, Brown Leather Notebook, Beige Knit Coaster Set, C. Beige Knit Coaster Set, Red Stoneware Mug, Brown Leather Notebook, D. Brown Leather Notebook, Beige Knit Coaster Set, Red Stoneware Mug","annotationPath":"curated/spatial-world-model/v7/vgenst-bench/annotations/scene_motion/vgenst_io_v_ego_dyn_3_cozy_den_with_ottoman_tray_and_fireplace_mantel.json"},{"id":"vgenst_io_v_ego_dyn_44_jewelers_studio_with_workbench_and_display_case_top","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_io_v_ego_dyn_44_jewelers_studio_with_workbench_and_display_case_top.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_io_v_ego_dyn_44_jewelers_studio_with_workbench_and_display_case_top.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_io_v_ego_dyn_44_jewelers_studio_with_workbench_and_display_case_top.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory, Topology and Containment","perspective":"Egocentric","caption":"From which position on the Wide Jeweler's Workbench does the agent pick up the object?: A. Left, B. Center, C. Right","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_io_v_ego_dyn_44_jewelers_studio_with_workbench_and_display_case_top.json"},{"id":"vgenst_io_v_ego_dyn_55_pharmacy_with_dispensing_counter_and_product_shelf","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_io_v_ego_dyn_55_pharmacy_with_dispensing_counter_and_product_shelf.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_io_v_ego_dyn_55_pharmacy_with_dispensing_counter_and_product_shelf.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_io_v_ego_dyn_55_pharmacy_with_dispensing_counter_and_product_shelf.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory, Topology and Containment","perspective":"Egocentric","caption":"What action does the agent perform on one of the objects?: A. Picks it up and places it on another surface, B. Pushes it off the table, C. Rearranges its position on the same surface, D. Breaks it into pieces","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_io_v_ego_dyn_55_pharmacy_with_dispensing_counter_and_product_shelf.json"},{"id":"vgenst_io_v_ego_dyn_66_physical_therapy_room_with_equipment_table_and_mat_stack","videoPath":"curated/spatial-world-model/v7/vgenst-bench/videos/scene_motion/vgenst_io_v_ego_dyn_66_physical_therapy_room_with_equipment_table_and_mat_stack.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/vgenst-bench/videos/scene_motion/vgenst_io_v_ego_dyn_66_physical_therapy_room_with_equipment_table_and_mat_stack.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/vgenst-bench/initial_frames/scene_motion/vgenst_io_v_ego_dyn_66_physical_therapy_room_with_equipment_table_and_mat_stack.png","sourceDataset":"VGenST-Bench","suggestedTrack":"scene_motion","scene":"daily activity","spatialAbility":"Direction and Trajectory, Relative Spatial Relations","perspective":"Exocentric","caption":"Which object does the agent pick up?: A. Red Resistance Band Coil, B. Blue Foam Roller Block, C. Yellow Stress Ball","annotationPath":"curated/spatial-world-model/v7/vgenst-bench/annotations/scene_motion/vgenst_io_v_ego_dyn_66_physical_therapy_room_with_equipment_table_and_mat_stack.json"},{"id":"vgenst_io_v_ego_dyn_67_beauty_salon_with_styling_station_and_product_shelf","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_io_v_ego_dyn_67_beauty_salon_with_styling_station_and_product_shelf.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_io_v_ego_dyn_67_beauty_salon_with_styling_station_and_product_shelf.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_io_v_ego_dyn_67_beauty_salon_with_styling_station_and_product_shelf.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory, Topology and Containment","perspective":"Egocentric","caption":"Which object does the agent pick up?: A. Black Hair Dryer, B. Pink Hair Comb, C. Silver Scissors","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_io_v_ego_dyn_67_beauty_salon_with_styling_station_and_product_shelf.json"},{"id":"vgenst_io_v_ego_dyn_77_game_room_with_board_game_table_and_trophy_shelf","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_io_v_ego_dyn_77_game_room_with_board_game_table_and_trophy_shelf.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_io_v_ego_dyn_77_game_room_with_board_game_table_and_trophy_shelf.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_io_v_ego_dyn_77_game_room_with_board_game_table_and_trophy_shelf.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory, Topology and Containment","perspective":"Egocentric","caption":"Which object does the agent pick up?: A. Red Game Dice, B. Black Chess Pawn, C. Gold Trophy Token","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_io_v_ego_dyn_77_game_room_with_board_game_table_and_trophy_shelf.json"},{"id":"vgenst_io_v_ego_dyn_88_beekeepers_prep_room_with_extraction_table_and_jar_shelf","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_io_v_ego_dyn_88_beekeepers_prep_room_with_extraction_table_and_jar_shelf.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_io_v_ego_dyn_88_beekeepers_prep_room_with_extraction_table_and_jar_shelf.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_io_v_ego_dyn_88_beekeepers_prep_room_with_extraction_table_and_jar_shelf.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory, Topology and Containment","perspective":"Egocentric","caption":"From which position on the Extraction Table does the agent pick up the object?: A. Left, B. Center, C. Right","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_io_v_ego_dyn_88_beekeepers_prep_room_with_extraction_table_and_jar_shelf.json"},{"id":"vgenst_io_v_ego_dyn_99_dwarven_armory_with_forge_table_and_weapon_rack_bench","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_io_v_ego_dyn_99_dwarven_armory_with_forge_table_and_weapon_rack_bench.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_io_v_ego_dyn_99_dwarven_armory_with_forge_table_and_weapon_rack_bench.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_io_v_ego_dyn_99_dwarven_armory_with_forge_table_and_weapon_rack_bench.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"sports","spatialAbility":"Relative Spatial Relations, Direction and Trajectory, Topology and Containment","perspective":"Egocentric","caption":"What action does the agent perform on one of the objects?: A. Picks it up and places it on another surface, B. Pushes it off the table, C. Rearranges its position on the same surface, D. Breaks it into pieces","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_io_v_ego_dyn_99_dwarven_armory_with_forge_table_and_weapon_rack_bench.json"},{"id":"vgenst_ls_e_exo_sta_0_downtown_skyline","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_ls_e_exo_sta_0_downtown_skyline.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_ls_e_exo_sta_0_downtown_skyline.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/View_motion/vgenst_ls_e_exo_sta_0_downtown_skyline.png","sourceDataset":"VGenST-Bench","suggestedTrack":"View motion","scene":"driving","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Exocentric","caption":"In which compass direction does the camera fly horizontally?: A. North, B. East, C. South, D. West","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/View_motion/vgenst_ls_e_exo_sta_0_downtown_skyline.json"},{"id":"vgenst_ls_e_exo_sta_11_naval_base_harbor","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_ls_e_exo_sta_11_naval_base_harbor.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_ls_e_exo_sta_11_naval_base_harbor.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/View_motion/vgenst_ls_e_exo_sta_11_naval_base_harbor.png","sourceDataset":"VGenST-Bench","suggestedTrack":"View motion","scene":"daily activity","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Exocentric","caption":"In which compass direction does the camera fly horizontally?: A. North, B. East, C. South, D. West","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/View_motion/vgenst_ls_e_exo_sta_11_naval_base_harbor.json"},{"id":"vgenst_ls_e_exo_sta_22_railway_junction_hub","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_ls_e_exo_sta_22_railway_junction_hub.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_ls_e_exo_sta_22_railway_junction_hub.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/View_motion/vgenst_ls_e_exo_sta_22_railway_junction_hub.png","sourceDataset":"VGenST-Bench","suggestedTrack":"View motion","scene":"driving","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Exocentric","caption":"In which compass direction does the camera fly horizontally?: A. North, B. East, C. South, D. West","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/View_motion/vgenst_ls_e_exo_sta_22_railway_junction_hub.json"},{"id":"vgenst_ls_e_exo_sta_33_vineyard_estate","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_ls_e_exo_sta_33_vineyard_estate.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_ls_e_exo_sta_33_vineyard_estate.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/View_motion/vgenst_ls_e_exo_sta_33_vineyard_estate.png","sourceDataset":"VGenST-Bench","suggestedTrack":"View motion","scene":"daily activity","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Exocentric","caption":"In which compass direction does the camera fly horizontally?: A. North, B. East, C. South, D. West","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/View_motion/vgenst_ls_e_exo_sta_33_vineyard_estate.json"},{"id":"vgenst_ls_e_exo_sta_44_mesa_archaeological_site","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_ls_e_exo_sta_44_mesa_archaeological_site.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_ls_e_exo_sta_44_mesa_archaeological_site.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/View_motion/vgenst_ls_e_exo_sta_44_mesa_archaeological_site.png","sourceDataset":"VGenST-Bench","suggestedTrack":"View motion","scene":"daily activity","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Exocentric","caption":"How does the camera move throughout the video?: A. Cranes up first, then flies horizontally to a new location, B. Stays fixed at the starting position, C. Rotates 360 degrees in place, D. Zooms in on a specific structure","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/View_motion/vgenst_ls_e_exo_sta_44_mesa_archaeological_site.json"},{"id":"vgenst_ls_e_exo_sta_55_gothic_cathedral_quarter","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_ls_e_exo_sta_55_gothic_cathedral_quarter.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_ls_e_exo_sta_55_gothic_cathedral_quarter.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/View_motion/vgenst_ls_e_exo_sta_55_gothic_cathedral_quarter.png","sourceDataset":"VGenST-Bench","suggestedTrack":"View motion","scene":"driving","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Exocentric","caption":"In which compass direction does the camera fly horizontally?: A. North, B. East, C. South, D. West","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/View_motion/vgenst_ls_e_exo_sta_55_gothic_cathedral_quarter.json"},{"id":"vgenst_ls_e_exo_sta_66_army_training_camp","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_ls_e_exo_sta_66_army_training_camp.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_ls_e_exo_sta_66_army_training_camp.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/View_motion/vgenst_ls_e_exo_sta_66_army_training_camp.png","sourceDataset":"VGenST-Bench","suggestedTrack":"View motion","scene":"daily activity","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Exocentric","caption":"In which compass direction does the camera fly horizontally?: A. North, B. East, C. South, D. West","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/View_motion/vgenst_ls_e_exo_sta_66_army_training_camp.json"},{"id":"vgenst_ls_e_exo_sta_77_waterfall_gorge_settlement","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_ls_e_exo_sta_77_waterfall_gorge_settlement.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_ls_e_exo_sta_77_waterfall_gorge_settlement.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/View_motion/vgenst_ls_e_exo_sta_77_waterfall_gorge_settlement.png","sourceDataset":"VGenST-Bench","suggestedTrack":"View motion","scene":"daily activity","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Exocentric","caption":"In which compass direction does the camera fly horizontally?: A. North, B. East, C. South, D. West","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/View_motion/vgenst_ls_e_exo_sta_77_waterfall_gorge_settlement.json"},{"id":"vgenst_ls_e_exo_sta_88_snow-covered_mountain_town","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_ls_e_exo_sta_88_snow-covered_mountain_town.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_ls_e_exo_sta_88_snow-covered_mountain_town.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/View_motion/vgenst_ls_e_exo_sta_88_snow-covered_mountain_town.png","sourceDataset":"VGenST-Bench","suggestedTrack":"View motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Exocentric","caption":"In which compass direction does the camera fly horizontally?: A. North, B. East, C. South, D. West","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/View_motion/vgenst_ls_e_exo_sta_88_snow-covered_mountain_town.json"},{"id":"vgenst_ls_e_exo_sta_99_post-apocalyptic_outpost","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_ls_e_exo_sta_99_post-apocalyptic_outpost.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_ls_e_exo_sta_99_post-apocalyptic_outpost.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/View_motion/vgenst_ls_e_exo_sta_99_post-apocalyptic_outpost.png","sourceDataset":"VGenST-Bench","suggestedTrack":"View motion","scene":"driving","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Viewpoint Geometry","perspective":"Exocentric","caption":"In which compass direction does the camera fly horizontally?: A. North, B. East, C. South, D. West","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/View_motion/vgenst_ls_e_exo_sta_99_post-apocalyptic_outpost.json"},{"id":"vgenst_mc_f_ego_sta_0_living_room_table","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_mc_f_ego_sta_0_living_room_table.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_mc_f_ego_sta_0_living_room_table.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/View_motion/vgenst_mc_f_ego_sta_0_living_room_table.png","sourceDataset":"VGenST-Bench","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Viewpoint Geometry, Relative Spatial Relations, Topology and Containment","perspective":"Egocentric","caption":"How does the camera move throughout the video?: A. Boom Up (rising vertically), B. Boom Down (descending vertically), C. Pan Left (rotating horizontally), D. Zoom In (moving closer)","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/View_motion/vgenst_mc_f_ego_sta_0_living_room_table.json"},{"id":"vgenst_mc_f_ego_sta_11_restaurant_booth_table","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_mc_f_ego_sta_11_restaurant_booth_table.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_mc_f_ego_sta_11_restaurant_booth_table.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/View_motion/vgenst_mc_f_ego_sta_11_restaurant_booth_table.png","sourceDataset":"VGenST-Bench","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Viewpoint Geometry, Relative Spatial Relations, Topology and Containment","perspective":"Egocentric","caption":"How does the camera move throughout the video?: A. Boom Up (rising vertically), B. Boom Down (descending vertically), C. Pan Left (rotating horizontally), D. Zoom In (moving closer)","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/View_motion/vgenst_mc_f_ego_sta_11_restaurant_booth_table.json"},{"id":"vgenst_mc_f_ego_sta_19_museum_information_desk","videoPath":"curated/spatial-world-model/v7/vgenst-bench/videos/viewpoint_motion/vgenst_mc_f_ego_sta_19_museum_information_desk.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/vgenst-bench/videos/viewpoint_motion/vgenst_mc_f_ego_sta_19_museum_information_desk.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/vgenst-bench/initial_frames/viewpoint_motion/vgenst_mc_f_ego_sta_19_museum_information_desk.png","sourceDataset":"VGenST-Bench","suggestedTrack":"viewpoint_motion","scene":"living space","spatialAbility":"Viewpoint Geometry, Topology and Containment","perspective":"Egocentric","caption":"What is the content inside the Emerald Metal Donation Tin?: A. White Folded Maps, B. Yellow Pencils, C. Silver Coins, D. Empty","annotationPath":"curated/spatial-world-model/v7/vgenst-bench/annotations/viewpoint_motion/vgenst_mc_f_ego_sta_19_museum_information_desk.json"},{"id":"vgenst_mc_f_ego_sta_23_auto_mechanic_shop_table","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_mc_f_ego_sta_23_auto_mechanic_shop_table.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_mc_f_ego_sta_23_auto_mechanic_shop_table.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/View_motion/vgenst_mc_f_ego_sta_23_auto_mechanic_shop_table.png","sourceDataset":"VGenST-Bench","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Viewpoint Geometry, Relative Spatial Relations, Topology and Containment","perspective":"Egocentric","caption":"How does the camera move throughout the video?: A. Boom Up (rising vertically), B. Boom Down (descending vertically), C. Pan Left (rotating horizontally), D. Zoom In (moving closer)","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/View_motion/vgenst_mc_f_ego_sta_23_auto_mechanic_shop_table.json"},{"id":"vgenst_mc_f_ego_sta_33_sci-fi_cantina_bar_counter","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_mc_f_ego_sta_33_sci-fi_cantina_bar_counter.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_mc_f_ego_sta_33_sci-fi_cantina_bar_counter.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/View_motion/vgenst_mc_f_ego_sta_33_sci-fi_cantina_bar_counter.png","sourceDataset":"VGenST-Bench","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Viewpoint Geometry, Relative Spatial Relations, Topology and Containment","perspective":"Egocentric","caption":"How does the camera move throughout the video?: A. Boom Up (rising vertically), B. Boom Down (descending vertically), C. Pan Left (rotating horizontally), D. Zoom In (moving closer)","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/View_motion/vgenst_mc_f_ego_sta_33_sci-fi_cantina_bar_counter.json"},{"id":"vgenst_mc_f_ego_sta_42_pirate_ship_captains_map_desk","videoPath":"curated/spatial-world-model/v7/vgenst-bench/videos/viewpoint_motion/vgenst_mc_f_ego_sta_42_pirate_ship_captains_map_desk.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/vgenst-bench/videos/viewpoint_motion/vgenst_mc_f_ego_sta_42_pirate_ship_captains_map_desk.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/vgenst-bench/initial_frames/viewpoint_motion/vgenst_mc_f_ego_sta_42_pirate_ship_captains_map_desk.png","sourceDataset":"VGenST-Bench","suggestedTrack":"viewpoint_motion","scene":"living space","spatialAbility":"Viewpoint Geometry, Topology and Containment","perspective":"Egocentric","caption":"What is the content inside the Green Wooden Box?: A. Black Ink, B. Gold Coins, C. Rolled Parchment, D. Empty","annotationPath":"curated/spatial-world-model/v7/vgenst-bench/annotations/viewpoint_motion/vgenst_mc_f_ego_sta_42_pirate_ship_captains_map_desk.json"},{"id":"vgenst_mc_f_ego_sta_45_gothic_vampire_castle_dining_table","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_mc_f_ego_sta_45_gothic_vampire_castle_dining_table.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_mc_f_ego_sta_45_gothic_vampire_castle_dining_table.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/View_motion/vgenst_mc_f_ego_sta_45_gothic_vampire_castle_dining_table.png","sourceDataset":"VGenST-Bench","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Viewpoint Geometry, Relative Spatial Relations, Topology and Containment","perspective":"Egocentric","caption":"How does the camera move throughout the video?: A. Boom Up (rising vertically), B. Boom Down (descending vertically), C. Pan Left (rotating horizontally), D. Zoom In (moving closer)","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/View_motion/vgenst_mc_f_ego_sta_45_gothic_vampire_castle_dining_table.json"},{"id":"vgenst_mc_f_ego_sta_56_ferry_boat_snack_bar_counter","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_mc_f_ego_sta_56_ferry_boat_snack_bar_counter.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_mc_f_ego_sta_56_ferry_boat_snack_bar_counter.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/View_motion/vgenst_mc_f_ego_sta_56_ferry_boat_snack_bar_counter.png","sourceDataset":"VGenST-Bench","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Viewpoint Geometry, Relative Spatial Relations, Topology and Containment","perspective":"Egocentric","caption":"How does the camera move throughout the video?: A. Boom Up (rising vertically), B. Boom Down (descending vertically), C. Pan Left (rotating horizontally), D. Zoom In (moving closer)","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/View_motion/vgenst_mc_f_ego_sta_56_ferry_boat_snack_bar_counter.json"},{"id":"vgenst_mc_f_ego_sta_67_cave_explorers_rock_ledge","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_mc_f_ego_sta_67_cave_explorers_rock_ledge.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_mc_f_ego_sta_67_cave_explorers_rock_ledge.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/View_motion/vgenst_mc_f_ego_sta_67_cave_explorers_rock_ledge.png","sourceDataset":"VGenST-Bench","suggestedTrack":"View motion","scene":"daily activity","spatialAbility":"Viewpoint Geometry, Relative Spatial Relations, Topology and Containment","perspective":"Egocentric","caption":"How does the camera move throughout the video?: A. Boom Up (rising vertically), B. Boom Down (descending vertically), C. Pan Left (rotating horizontally), D. Zoom In (moving closer)","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/View_motion/vgenst_mc_f_ego_sta_67_cave_explorers_rock_ledge.json"},{"id":"vgenst_mc_f_ego_sta_77_makeup_artists_vanity_station","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_mc_f_ego_sta_77_makeup_artists_vanity_station.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_mc_f_ego_sta_77_makeup_artists_vanity_station.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/View_motion/vgenst_mc_f_ego_sta_77_makeup_artists_vanity_station.png","sourceDataset":"VGenST-Bench","suggestedTrack":"View motion","scene":"living space","spatialAbility":"Viewpoint Geometry, Relative Spatial Relations, Topology and Containment","perspective":"Egocentric","caption":"How does the camera move throughout the video?: A. Boom Up (rising vertically), B. Boom Down (descending vertically), C. Pan Left (rotating horizontally), D. Zoom In (moving closer)","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/View_motion/vgenst_mc_f_ego_sta_77_makeup_artists_vanity_station.json"},{"id":"vgenst_mc_f_ego_sta_88_boxing_gym_equipment_desk","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_mc_f_ego_sta_88_boxing_gym_equipment_desk.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_mc_f_ego_sta_88_boxing_gym_equipment_desk.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/View_motion/vgenst_mc_f_ego_sta_88_boxing_gym_equipment_desk.png","sourceDataset":"VGenST-Bench","suggestedTrack":"View motion","scene":"sports","spatialAbility":"Viewpoint Geometry, Relative Spatial Relations, Topology and Containment","perspective":"Egocentric","caption":"How does the camera move throughout the video?: A. Boom Up (rising vertically), B. Boom Down (descending vertically), C. Pan Left (rotating horizontally), D. Zoom In (moving closer)","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/View_motion/vgenst_mc_f_ego_sta_88_boxing_gym_equipment_desk.json"},{"id":"vgenst_mc_f_ego_sta_99_magicians_stage_prop_table","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_mc_f_ego_sta_99_magicians_stage_prop_table.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/View_motion/vgenst_mc_f_ego_sta_99_magicians_stage_prop_table.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/View_motion/vgenst_mc_f_ego_sta_99_magicians_stage_prop_table.png","sourceDataset":"VGenST-Bench","suggestedTrack":"View motion","scene":"driving","spatialAbility":"Viewpoint Geometry, Relative Spatial Relations, Topology and Containment","perspective":"Egocentric","caption":"How does the camera move throughout the video?: A. Boom Up (rising vertically), B. Boom Down (descending vertically), C. Pan Left (rotating horizontally), D. Zoom In (moving closer)","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/View_motion/vgenst_mc_f_ego_sta_99_magicians_stage_prop_table.json"},{"id":"vgenst_qc_f_ego_dyn_0_living_room_table","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_qc_f_ego_dyn_0_living_room_table.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_qc_f_ego_dyn_0_living_room_table.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_qc_f_ego_dyn_0_living_room_table.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Direction and Trajectory, Topology and Containment","perspective":"Egocentric","caption":"How many times does the hand place an item into the container?: A. 0, B. 1, C. 2, D. 3","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_qc_f_ego_dyn_0_living_room_table.json"},{"id":"vgenst_qc_f_ego_dyn_11_restaurant_booth_table","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_qc_f_ego_dyn_11_restaurant_booth_table.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_qc_f_ego_dyn_11_restaurant_booth_table.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_qc_f_ego_dyn_11_restaurant_booth_table.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Direction and Trajectory, Topology and Containment","perspective":"Egocentric","caption":"What action does the hand perform in the second step?: A. Places an item into the container, B. Takes an item out of the container, C. Moves an item on the surface to the other location of the surface","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_qc_f_ego_dyn_11_restaurant_booth_table.json"},{"id":"vgenst_qc_f_ego_dyn_18_park_picnic_table","videoPath":"curated/spatial-world-model/v7/vgenst-bench/videos/scene_motion/vgenst_qc_f_ego_dyn_18_park_picnic_table.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/vgenst-bench/videos/scene_motion/vgenst_qc_f_ego_dyn_18_park_picnic_table.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/vgenst-bench/initial_frames/scene_motion/vgenst_qc_f_ego_dyn_18_park_picnic_table.png","sourceDataset":"VGenST-Bench","suggestedTrack":"scene_motion","scene":"daily activity","spatialAbility":"Topology and Containment, Relative Spatial Relations","perspective":"Egocentric","caption":"From the camera's perspective, where are the items placed relative to the container?: A. Inside the container, B. Beside the container on the surface, C. On top of the container, D. Underneath the container","annotationPath":"curated/spatial-world-model/v7/vgenst-bench/annotations/scene_motion/vgenst_qc_f_ego_dyn_18_park_picnic_table.json"},{"id":"vgenst_qc_f_ego_dyn_23_auto_mechanic_shop_table","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_qc_f_ego_dyn_23_auto_mechanic_shop_table.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_qc_f_ego_dyn_23_auto_mechanic_shop_table.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_qc_f_ego_dyn_23_auto_mechanic_shop_table.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Direction and Trajectory, Topology and Containment","perspective":"Egocentric","caption":"What action does the hand perform in the second step?: A. Places an item into the container, B. Takes an item out of the container, C. Moves an item on the surface to the other location of the surface","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_qc_f_ego_dyn_23_auto_mechanic_shop_table.json"},{"id":"vgenst_qc_f_ego_dyn_33_sci-fi_cantina_bar_counter","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_qc_f_ego_dyn_33_sci-fi_cantina_bar_counter.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_qc_f_ego_dyn_33_sci-fi_cantina_bar_counter.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_qc_f_ego_dyn_33_sci-fi_cantina_bar_counter.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Direction and Trajectory, Topology and Containment","perspective":"Egocentric","caption":"How many times does the hand place an item into the container?: A. 0, B. 1, C. 2, D. 3","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_qc_f_ego_dyn_33_sci-fi_cantina_bar_counter.json"},{"id":"vgenst_qc_f_ego_dyn_44_enchanted_forest_flat_tree_table","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_qc_f_ego_dyn_44_enchanted_forest_flat_tree_table.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_qc_f_ego_dyn_44_enchanted_forest_flat_tree_table.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_qc_f_ego_dyn_44_enchanted_forest_flat_tree_table.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"natural scenery","spatialAbility":"Relative Spatial Relations, Direction and Trajectory, Topology and Containment","perspective":"Egocentric","caption":"How many times does the hand place an item into the container?: A. 0, B. 1, C. 2, D. 3","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_qc_f_ego_dyn_44_enchanted_forest_flat_tree_table.json"},{"id":"vgenst_qc_f_ego_dyn_55_vintage_train_cabin_table","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_qc_f_ego_dyn_55_vintage_train_cabin_table.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_qc_f_ego_dyn_55_vintage_train_cabin_table.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_qc_f_ego_dyn_55_vintage_train_cabin_table.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Direction and Trajectory, Topology and Containment","perspective":"Egocentric","caption":"What action does the hand perform in the second step?: A. Places an item into the container, B. Takes an item out of the container, C. Moves an item on the surface to the other location of the surface","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_qc_f_ego_dyn_55_vintage_train_cabin_table.json"},{"id":"vgenst_qc_f_ego_dyn_66_safari_table","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_qc_f_ego_dyn_66_safari_table.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_qc_f_ego_dyn_66_safari_table.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_qc_f_ego_dyn_66_safari_table.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Direction and Trajectory, Topology and Containment","perspective":"Egocentric","caption":"What action does the hand perform in the second step?: A. Places an item into the container, B. Takes an item out of the container, C. Moves an item on the surface to the other location of the surface","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_qc_f_ego_dyn_66_safari_table.json"},{"id":"vgenst_qc_f_ego_dyn_76_coin_collectors_velvet_table","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_qc_f_ego_dyn_76_coin_collectors_velvet_table.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_qc_f_ego_dyn_76_coin_collectors_velvet_table.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_qc_f_ego_dyn_76_coin_collectors_velvet_table.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Direction and Trajectory, Topology and Containment","perspective":"Egocentric","caption":"How many times does the hand place an item into the container?: A. 0, B. 1, C. 2, D. 3","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_qc_f_ego_dyn_76_coin_collectors_velvet_table.json"},{"id":"vgenst_qc_f_ego_dyn_82_golf_clubhouse_bar_counter","videoPath":"curated/spatial-world-model/v7/vgenst-bench/videos/scene_motion/vgenst_qc_f_ego_dyn_82_golf_clubhouse_bar_counter.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/vgenst-bench/videos/scene_motion/vgenst_qc_f_ego_dyn_82_golf_clubhouse_bar_counter.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/vgenst-bench/initial_frames/scene_motion/vgenst_qc_f_ego_dyn_82_golf_clubhouse_bar_counter.png","sourceDataset":"VGenST-Bench","suggestedTrack":"scene_motion","scene":"sports","spatialAbility":"Topology and Containment, Relative Spatial Relations","perspective":"Egocentric","caption":"Suppose the container was empty at the start of the video - How many identical items are in container at the end of the video?: A. 0, B. 1, C. 2, D. 3","annotationPath":"curated/spatial-world-model/v7/vgenst-bench/annotations/scene_motion/vgenst_qc_f_ego_dyn_82_golf_clubhouse_bar_counter.json"},{"id":"vgenst_qc_f_ego_dyn_88_boxing_gym_equipment_desk","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_qc_f_ego_dyn_88_boxing_gym_equipment_desk.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_qc_f_ego_dyn_88_boxing_gym_equipment_desk.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_qc_f_ego_dyn_88_boxing_gym_equipment_desk.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Direction and Trajectory, Topology and Containment","perspective":"Egocentric","caption":"How many times does the hand place an item into the container?: A. 0, B. 1, C. 2, D. 3","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_qc_f_ego_dyn_88_boxing_gym_equipment_desk.json"},{"id":"vgenst_qc_f_ego_dyn_99_magicians_stage_prop_table","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_qc_f_ego_dyn_99_magicians_stage_prop_table.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_qc_f_ego_dyn_99_magicians_stage_prop_table.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_qc_f_ego_dyn_99_magicians_stage_prop_table.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Relative Spatial Relations, Direction and Trajectory, Topology and Containment","perspective":"Egocentric","caption":"What action does the hand perform in the second step?: A. Places an item into the container, B. Takes an item out of the container, C. Moves an item on the surface to the other location of the surface","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_qc_f_ego_dyn_99_magicians_stage_prop_table.json"},{"id":"vgenst_rv_e_ego_dyn_0_desert_highway","videoPath":"curated/spatial-world-model/v7/vgenst-bench/videos/coupled_motion/vgenst_rv_e_ego_dyn_0_desert_highway.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/vgenst-bench/videos/coupled_motion/vgenst_rv_e_ego_dyn_0_desert_highway.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/vgenst-bench/initial_frames/coupled_motion/vgenst_rv_e_ego_dyn_0_desert_highway.png","sourceDataset":"VGenST-Bench","suggestedTrack":"coupled_motion","scene":"driving","spatialAbility":"Direction and Trajectory, Relative and Coupled Motion","perspective":"Egocentric","caption":"How does the Construction Truck appear to move relative to the camera?: A. Drifts backward, B. Streaks forward, C. Stays stationary at the same distance, D. Moves to the side and disappears","annotationPath":"curated/spatial-world-model/v7/vgenst-bench/annotations/coupled_motion/vgenst_rv_e_ego_dyn_0_desert_highway.json"},{"id":"vgenst_rv_e_ego_dyn_12_desert_rally","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/coupled_motion/vgenst_rv_e_ego_dyn_12_desert_rally.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/coupled_motion/vgenst_rv_e_ego_dyn_12_desert_rally.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/coupled_motion/vgenst_rv_e_ego_dyn_12_desert_rally.png","sourceDataset":"VGenST-Bench","suggestedTrack":"coupled motion","scene":"driving","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Relative and Coupled Motion","perspective":"Egocentric","caption":"How does the Support Vehicle appear to move relative to the camera?: A. Drifts backward, B. Streaks forward, C. Stays stationary at the same distance, D. Moves to the side and disappears","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/coupled_motion/vgenst_rv_e_ego_dyn_12_desert_rally.json"},{"id":"vgenst_rv_e_ego_dyn_1_coastal_freeway","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/coupled_motion/vgenst_rv_e_ego_dyn_1_coastal_freeway.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/coupled_motion/vgenst_rv_e_ego_dyn_1_coastal_freeway.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/coupled_motion/vgenst_rv_e_ego_dyn_1_coastal_freeway.png","sourceDataset":"VGenST-Bench","suggestedTrack":"coupled motion","scene":"driving","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Relative and Coupled Motion","perspective":"Egocentric","caption":"How does the Motorcycle appear to move relative to the camera?: A. Drifts backward, B. Streaks forward, C. Stays stationary at the same distance, D. Moves to the side and disappears","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/coupled_motion/vgenst_rv_e_ego_dyn_1_coastal_freeway.json"},{"id":"vgenst_rv_e_ego_dyn_23_tropical_lagoon","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/coupled_motion/vgenst_rv_e_ego_dyn_23_tropical_lagoon.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/coupled_motion/vgenst_rv_e_ego_dyn_23_tropical_lagoon.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/coupled_motion/vgenst_rv_e_ego_dyn_23_tropical_lagoon.png","sourceDataset":"VGenST-Bench","suggestedTrack":"coupled motion","scene":"driving","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Relative and Coupled Motion","perspective":"Egocentric","caption":"Which object is moving slower than the camera?: A. Brown Log Raft, B. White Hydrofoil, C. Both move slower","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/coupled_motion/vgenst_rv_e_ego_dyn_23_tropical_lagoon.json"},{"id":"vgenst_rv_e_ego_dyn_33_stratosphere","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/coupled_motion/vgenst_rv_e_ego_dyn_33_stratosphere.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/coupled_motion/vgenst_rv_e_ego_dyn_33_stratosphere.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/coupled_motion/vgenst_rv_e_ego_dyn_33_stratosphere.png","sourceDataset":"VGenST-Bench","suggestedTrack":"coupled motion","scene":"driving","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Relative and Coupled Motion","perspective":"Egocentric","caption":"How does the Zeppelin appear to move relative to the camera?: A. Drifts backward, B. Streaks forward, C. Stays stationary at the same distance, D. Moves to the side and disappears","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/coupled_motion/vgenst_rv_e_ego_dyn_33_stratosphere.json"},{"id":"vgenst_rv_e_ego_dyn_44_asteroid_field","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/coupled_motion/vgenst_rv_e_ego_dyn_44_asteroid_field.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/coupled_motion/vgenst_rv_e_ego_dyn_44_asteroid_field.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/coupled_motion/vgenst_rv_e_ego_dyn_44_asteroid_field.png","sourceDataset":"VGenST-Bench","suggestedTrack":"coupled motion","scene":"driving","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Relative and Coupled Motion","perspective":"Egocentric","caption":"Which object is moving slower than the camera?: A. Brown Rock Hauler, B. Hovering Jet Drone, C. Both move slower","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/coupled_motion/vgenst_rv_e_ego_dyn_44_asteroid_field.json"},{"id":"vgenst_rv_e_ego_dyn_55_arctic_ice_road","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/coupled_motion/vgenst_rv_e_ego_dyn_55_arctic_ice_road.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/coupled_motion/vgenst_rv_e_ego_dyn_55_arctic_ice_road.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/coupled_motion/vgenst_rv_e_ego_dyn_55_arctic_ice_road.png","sourceDataset":"VGenST-Bench","suggestedTrack":"coupled motion","scene":"driving","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Relative and Coupled Motion","perspective":"Egocentric","caption":"How does the Ice Racing Car appear to move relative to the camera?: A. Drifts backward, B. Streaks forward, C. Stays stationary at the same distance, D. Moves to the side and disappears","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/coupled_motion/vgenst_rv_e_ego_dyn_55_arctic_ice_road.json"},{"id":"vgenst_rv_e_ego_dyn_66_beach_shoreline","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/coupled_motion/vgenst_rv_e_ego_dyn_66_beach_shoreline.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/coupled_motion/vgenst_rv_e_ego_dyn_66_beach_shoreline.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/coupled_motion/vgenst_rv_e_ego_dyn_66_beach_shoreline.png","sourceDataset":"VGenST-Bench","suggestedTrack":"coupled motion","scene":"driving","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Relative and Coupled Motion","perspective":"Egocentric","caption":"How does the Draft Horse appear to move relative to the camera?: A. Drifts backward, B. Streaks forward, C. Stays stationary at the same distance, D. Moves to the side and disappears","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/coupled_motion/vgenst_rv_e_ego_dyn_66_beach_shoreline.json"},{"id":"vgenst_rv_e_ego_dyn_76_bmx_dirt_track","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/coupled_motion/vgenst_rv_e_ego_dyn_76_bmx_dirt_track.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/coupled_motion/vgenst_rv_e_ego_dyn_76_bmx_dirt_track.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/coupled_motion/vgenst_rv_e_ego_dyn_76_bmx_dirt_track.png","sourceDataset":"VGenST-Bench","suggestedTrack":"coupled motion","scene":"driving","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Relative and Coupled Motion","perspective":"Egocentric","caption":"How does the Downhill Racer appear to move relative to the camera?: A. Drifts backward, B. Streaks forward, C. Stays stationary at the same distance, D. Moves to the side and disappears","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/coupled_motion/vgenst_rv_e_ego_dyn_76_bmx_dirt_track.json"},{"id":"vgenst_rv_e_ego_dyn_86_crystal_gorge","videoPath":"curated/spatial-world-model/v7/vgenst-bench/videos/coupled_motion/vgenst_rv_e_ego_dyn_86_crystal_gorge.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/vgenst-bench/videos/coupled_motion/vgenst_rv_e_ego_dyn_86_crystal_gorge.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/vgenst-bench/initial_frames/coupled_motion/vgenst_rv_e_ego_dyn_86_crystal_gorge.png","sourceDataset":"VGenST-Bench","suggestedTrack":"coupled_motion","scene":"natural scenery","spatialAbility":"Direction and Trajectory, Relative and Coupled Motion","perspective":"Egocentric","caption":"If all objects continue at their current speeds after the video ends, where will the Ruby Fire Chariot be relative to the camera?: A. Far ahead and out of sight, B. Right next to the camera, C. Far behind the camera, D. Stopped at the side","annotationPath":"curated/spatial-world-model/v7/vgenst-bench/annotations/coupled_motion/vgenst_rv_e_ego_dyn_86_crystal_gorge.json"},{"id":"vgenst_rv_e_ego_dyn_88_steampunk_skyway","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/coupled_motion/vgenst_rv_e_ego_dyn_88_steampunk_skyway.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/coupled_motion/vgenst_rv_e_ego_dyn_88_steampunk_skyway.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/coupled_motion/vgenst_rv_e_ego_dyn_88_steampunk_skyway.png","sourceDataset":"VGenST-Bench","suggestedTrack":"coupled motion","scene":"driving","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Relative and Coupled Motion","perspective":"Egocentric","caption":"How does the Aether Glider appear to move relative to the camera?: A. Drifts backward, B. Streaks forward, C. Stays stationary at the same distance, D. Moves to the side and disappears","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/coupled_motion/vgenst_rv_e_ego_dyn_88_steampunk_skyway.json"},{"id":"vgenst_rv_e_ego_dyn_99_pipeline_route","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/coupled_motion/vgenst_rv_e_ego_dyn_99_pipeline_route.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/coupled_motion/vgenst_rv_e_ego_dyn_99_pipeline_route.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/coupled_motion/vgenst_rv_e_ego_dyn_99_pipeline_route.png","sourceDataset":"VGenST-Bench","suggestedTrack":"coupled motion","scene":"driving","spatialAbility":"Direction and Trajectory, Relative Spatial Relations, Relative and Coupled Motion","perspective":"Egocentric","caption":"How does the Utility ATV appear to move relative to the camera?: A. Drifts backward, B. Streaks forward, C. Stays stationary at the same distance, D. Moves to the side and disappears","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/coupled_motion/vgenst_rv_e_ego_dyn_99_pipeline_route.json"},{"id":"vgenst_vi_v_exo_dyn_0_bank_vault_room_with_large_safety_deposit_cabinet","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_vi_v_exo_dyn_0_bank_vault_room_with_large_safety_deposit_cabinet.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_vi_v_exo_dyn_0_bank_vault_room_with_large_safety_deposit_cabinet.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_vi_v_exo_dyn_0_bank_vault_room_with_large_safety_deposit_cabinet.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Visibility and Occlusion, Relative Spatial Relations","perspective":"Exocentric","caption":"What action does the agent located in top perform in the video?: A. Walks from one position to another, B. Stands completely still, C. Picks up an item, D. Exits the frame","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_vi_v_exo_dyn_0_bank_vault_room_with_large_safety_deposit_cabinet.json"},{"id":"vgenst_vi_v_exo_dyn_11_backyard_garden_with_wide_oak_tree","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_vi_v_exo_dyn_11_backyard_garden_with_wide_oak_tree.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_vi_v_exo_dyn_11_backyard_garden_with_wide_oak_tree.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_vi_v_exo_dyn_11_backyard_garden_with_wide_oak_tree.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"driving","spatialAbility":"Visibility and Occlusion, Relative Spatial Relations","perspective":"Exocentric","caption":"What action does the agent located in bottom perform in the video?: A. Walks from one position to another, B. Stands completely still, C. Picks up an item, D. Exits the frame","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_vi_v_exo_dyn_11_backyard_garden_with_wide_oak_tree.json"},{"id":"vgenst_vi_v_exo_dyn_16_indoor_playground_with_large_ball_pit_wall","videoPath":"curated/spatial-world-model/v7/vgenst-bench/videos/scene_motion/vgenst_vi_v_exo_dyn_16_indoor_playground_with_large_ball_pit_wall.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/vgenst-bench/videos/scene_motion/vgenst_vi_v_exo_dyn_16_indoor_playground_with_large_ball_pit_wall.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/vgenst-bench/initial_frames/scene_motion/vgenst_vi_v_exo_dyn_16_indoor_playground_with_large_ball_pit_wall.png","sourceDataset":"VGenST-Bench","suggestedTrack":"scene_motion","scene":"human interaction","spatialAbility":"Visibility and Occlusion, Relative Spatial Relations","perspective":"Exocentric","caption":"How did the visibility of the Child from the Parent's perspective change between the initial and final views?: A. Occluded to Visible, B. Visible to Occluded, C. Always visible, D. Always occluded","annotationPath":"curated/spatial-world-model/v7/vgenst-bench/annotations/scene_motion/vgenst_vi_v_exo_dyn_16_indoor_playground_with_large_ball_pit_wall.json"},{"id":"vgenst_vi_v_exo_dyn_18_basement_recreation_room_with_billiard_table","videoPath":"curated/spatial-world-model/v7/vgenst-bench/videos/scene_motion/vgenst_vi_v_exo_dyn_18_basement_recreation_room_with_billiard_table.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/vgenst-bench/videos/scene_motion/vgenst_vi_v_exo_dyn_18_basement_recreation_room_with_billiard_table.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/vgenst-bench/initial_frames/scene_motion/vgenst_vi_v_exo_dyn_18_basement_recreation_room_with_billiard_table.png","sourceDataset":"VGenST-Bench","suggestedTrack":"scene_motion","scene":"living space","spatialAbility":"Visibility and Occlusion, Relative Spatial Relations","perspective":"Exocentric","caption":"In the final view, what is the spatial arrangement of the three entities?: A. The Billiard Table is between the Golden Retriever and the Orange Cat on a diagonal, B. The Billiard Table is directly between the Golden Retriever and the Orange Cat on the same horizontal line, C. All three are clustered together at one corner, D. The Golden Retriever is between the Billiard Table and the Orange Cat","annotationPath":"curated/spatial-world-model/v7/vgenst-bench/annotations/scene_motion/vgenst_vi_v_exo_dyn_18_basement_recreation_room_with_billiard_table.json"},{"id":"vgenst_vi_v_exo_dyn_23_hardware_store_with_towering_lumber_stacks","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_vi_v_exo_dyn_23_hardware_store_with_towering_lumber_stacks.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_vi_v_exo_dyn_23_hardware_store_with_towering_lumber_stacks.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_vi_v_exo_dyn_23_hardware_store_with_towering_lumber_stacks.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"driving","spatialAbility":"Visibility and Occlusion, Relative Spatial Relations","perspective":"Exocentric","caption":"What action does the agent located in top perform in the video?: A. Walks from one position to another, B. Stands completely still, C. Picks up an item, D. Exits the frame","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_vi_v_exo_dyn_23_hardware_store_with_towering_lumber_stacks.json"},{"id":"vgenst_vi_v_exo_dyn_34_boardroom_with_massive_conference_table","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_vi_v_exo_dyn_34_boardroom_with_massive_conference_table.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_vi_v_exo_dyn_34_boardroom_with_massive_conference_table.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_vi_v_exo_dyn_34_boardroom_with_massive_conference_table.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Visibility and Occlusion, Relative Spatial Relations","perspective":"Exocentric","caption":"What action does the agent located in top perform in the video?: A. Walks from one position to another, B. Stands completely still, C. Picks up an item, D. Exits the frame","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_vi_v_exo_dyn_34_boardroom_with_massive_conference_table.json"},{"id":"vgenst_vi_v_exo_dyn_39_coworking_space_with_large_whiteboard_partition","videoPath":"curated/spatial-world-model/v7/vgenst-bench/videos/scene_motion/vgenst_vi_v_exo_dyn_39_coworking_space_with_large_whiteboard_partition.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/vgenst-bench/videos/scene_motion/vgenst_vi_v_exo_dyn_39_coworking_space_with_large_whiteboard_partition.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v7/vgenst-bench/initial_frames/scene_motion/vgenst_vi_v_exo_dyn_39_coworking_space_with_large_whiteboard_partition.png","sourceDataset":"VGenST-Bench","suggestedTrack":"scene_motion","scene":"human interaction","spatialAbility":"Visibility and Occlusion, Relative Spatial Relations","perspective":"Exocentric","caption":"How did the visibility of the Startup Founder from the Freelancer's perspective change between the initial and final views?: A. Occluded to Visible, B. Visible to Occluded, C. Always visible, D. Always occluded","annotationPath":"curated/spatial-world-model/v7/vgenst-bench/annotations/scene_motion/vgenst_vi_v_exo_dyn_39_coworking_space_with_large_whiteboard_partition.json"},{"id":"vgenst_vi_v_exo_dyn_46_veterinary_clinic_with_solid-walled_kennel_enclosure","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_vi_v_exo_dyn_46_veterinary_clinic_with_solid-walled_kennel_enclosure.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_vi_v_exo_dyn_46_veterinary_clinic_with_solid-walled_kennel_enclosure.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_vi_v_exo_dyn_46_veterinary_clinic_with_solid-walled_kennel_enclosure.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"daily activity","spatialAbility":"Visibility and Occlusion, Relative Spatial Relations","perspective":"Exocentric","caption":"What action does the agent located in top perform in the video?: A. Walks from one position to another, B. Stands completely still, C. Picks up an item, D. Exits the frame","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_vi_v_exo_dyn_46_veterinary_clinic_with_solid-walled_kennel_enclosure.json"},{"id":"vgenst_vi_v_exo_dyn_56_ferry_deck_with_funnel_stack","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_vi_v_exo_dyn_56_ferry_deck_with_funnel_stack.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_vi_v_exo_dyn_56_ferry_deck_with_funnel_stack.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_vi_v_exo_dyn_56_ferry_deck_with_funnel_stack.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"daily activity","spatialAbility":"Visibility and Occlusion, Relative Spatial Relations","perspective":"Exocentric","caption":"What action does the agent located in top perform in the video?: A. Walks from one position to another, B. Stands completely still, C. Picks up an item, D. Exits the frame","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_vi_v_exo_dyn_56_ferry_deck_with_funnel_stack.json"},{"id":"vgenst_vi_v_exo_dyn_67_nightclub_with_vip_lounge_divider","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_vi_v_exo_dyn_67_nightclub_with_vip_lounge_divider.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_vi_v_exo_dyn_67_nightclub_with_vip_lounge_divider.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_vi_v_exo_dyn_67_nightclub_with_vip_lounge_divider.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Visibility and Occlusion, Relative Spatial Relations","perspective":"Exocentric","caption":"What action does the agent located in top perform in the video?: A. Walks from one position to another, B. Stands completely still, C. Picks up an item, D. Exits the frame","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_vi_v_exo_dyn_67_nightclub_with_vip_lounge_divider.json"},{"id":"vgenst_vi_v_exo_dyn_78_safari_plains_with_giant_termite_mound","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_vi_v_exo_dyn_78_safari_plains_with_giant_termite_mound.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_vi_v_exo_dyn_78_safari_plains_with_giant_termite_mound.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_vi_v_exo_dyn_78_safari_plains_with_giant_termite_mound.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"daily activity","spatialAbility":"Visibility and Occlusion, Relative Spatial Relations","perspective":"Exocentric","caption":"What action does the agent located in top perform in the video?: A. Walks from one position to another, B. Stands completely still, C. Picks up an item, D. Exits the frame","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_vi_v_exo_dyn_78_safari_plains_with_giant_termite_mound.json"},{"id":"vgenst_vi_v_exo_dyn_88_space_station_bay_with_cargo_containers","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_vi_v_exo_dyn_88_space_station_bay_with_cargo_containers.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_vi_v_exo_dyn_88_space_station_bay_with_cargo_containers.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_vi_v_exo_dyn_88_space_station_bay_with_cargo_containers.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"driving","spatialAbility":"Visibility and Occlusion, Relative Spatial Relations","perspective":"Exocentric","caption":"What action does the agent located in top perform in the video?: A. Walks from one position to another, B. Stands completely still, C. Picks up an item, D. Exits the frame","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_vi_v_exo_dyn_88_space_station_bay_with_cargo_containers.json"},{"id":"vgenst_vi_v_exo_dyn_99_old_west_saloon_with_large_wooden_bar_counter","videoPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_vi_v_exo_dyn_99_old_west_saloon_with_large_wooden_bar_counter.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/videos/Scene_motion/vgenst_vi_v_exo_dyn_99_old_west_saloon_with_large_wooden_bar_counter.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v8/vgenst-bench-expansion/initial_frames/Scene_motion/vgenst_vi_v_exo_dyn_99_old_west_saloon_with_large_wooden_bar_counter.png","sourceDataset":"VGenST-Bench","suggestedTrack":"Scene motion","scene":"living space","spatialAbility":"Visibility and Occlusion, Relative Spatial Relations","perspective":"Exocentric","caption":"What action does the agent located in bottom perform in the video?: A. Walks from one position to another, B. Stands completely still, C. Picks up an item, D. Exits the frame","annotationPath":"curated/spatial-world-model/v8/vgenst-bench-expansion/annotations/Scene_motion/vgenst_vi_v_exo_dyn_99_old_west_saloon_with_large_wooden_bar_counter.json"},{"id":"003188da7fc95f302c89beaf04bff082a2be08d43c24a5c949648db5fbfe43e3","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/003188da7fc95f302c89beaf04bff082a2be08d43c24a5c949648db5fbfe43e3.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/003188da7fc95f302c89beaf04bff082a2be08d43c24a5c949648db5fbfe43e3.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/003188da7fc95f302c89beaf04bff082a2be08d43c24a5c949648db5fbfe43e3.json"},{"id":"005247195cbd2c3ed8f38f567a76b7ae0458074013a29be03002c48c95381074","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/005247195cbd2c3ed8f38f567a76b7ae0458074013a29be03002c48c95381074.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/005247195cbd2c3ed8f38f567a76b7ae0458074013a29be03002c48c95381074.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/005247195cbd2c3ed8f38f567a76b7ae0458074013a29be03002c48c95381074.json"},{"id":"007354fa60f225dc1af19c1b187a14b0b11e6cf84d063242e30a12de6bd8b39c","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/007354fa60f225dc1af19c1b187a14b0b11e6cf84d063242e30a12de6bd8b39c.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/007354fa60f225dc1af19c1b187a14b0b11e6cf84d063242e30a12de6bd8b39c.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/007354fa60f225dc1af19c1b187a14b0b11e6cf84d063242e30a12de6bd8b39c.json"},{"id":"0083f8939580f9b7d41e6134fcc2202520c9e1688accfd516227c7850690a9ac","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/0083f8939580f9b7d41e6134fcc2202520c9e1688accfd516227c7850690a9ac.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/0083f8939580f9b7d41e6134fcc2202520c9e1688accfd516227c7850690a9ac.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/0083f8939580f9b7d41e6134fcc2202520c9e1688accfd516227c7850690a9ac.json"},{"id":"0109ed7d87b6f4576a277ae350786d9ffd0afa77144ce597186dce95c4637841","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/0109ed7d87b6f4576a277ae350786d9ffd0afa77144ce597186dce95c4637841.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/0109ed7d87b6f4576a277ae350786d9ffd0afa77144ce597186dce95c4637841.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/0109ed7d87b6f4576a277ae350786d9ffd0afa77144ce597186dce95c4637841.json"},{"id":"012bd3843bf7c038d76d08208e6cd478de9b25ebb54551b29dc51c0c4272622d","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/012bd3843bf7c038d76d08208e6cd478de9b25ebb54551b29dc51c0c4272622d.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/012bd3843bf7c038d76d08208e6cd478de9b25ebb54551b29dc51c0c4272622d.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/012bd3843bf7c038d76d08208e6cd478de9b25ebb54551b29dc51c0c4272622d.json"},{"id":"016559e35c370a60eb189d2f76eaaf9f17c6100441e639afd5fabc388692e43a","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/016559e35c370a60eb189d2f76eaaf9f17c6100441e639afd5fabc388692e43a.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/016559e35c370a60eb189d2f76eaaf9f17c6100441e639afd5fabc388692e43a.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/016559e35c370a60eb189d2f76eaaf9f17c6100441e639afd5fabc388692e43a.json"},{"id":"01895e888aeba716c67f884af44a784c82b5dc8fca949fbce2aa6fb20aaa95d5","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/01895e888aeba716c67f884af44a784c82b5dc8fca949fbce2aa6fb20aaa95d5.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/01895e888aeba716c67f884af44a784c82b5dc8fca949fbce2aa6fb20aaa95d5.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/01895e888aeba716c67f884af44a784c82b5dc8fca949fbce2aa6fb20aaa95d5.json"},{"id":"01c1e71da684cee8d58b1507758c39180f13766e6acb1204ce48014d9851a0ac","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/01c1e71da684cee8d58b1507758c39180f13766e6acb1204ce48014d9851a0ac.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/01c1e71da684cee8d58b1507758c39180f13766e6acb1204ce48014d9851a0ac.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/01c1e71da684cee8d58b1507758c39180f13766e6acb1204ce48014d9851a0ac.json"},{"id":"01eeb6b8dbf439f7c4f9fcbc0e63d13169e726efd5cae05f46d428abefac418c","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/01eeb6b8dbf439f7c4f9fcbc0e63d13169e726efd5cae05f46d428abefac418c.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/01eeb6b8dbf439f7c4f9fcbc0e63d13169e726efd5cae05f46d428abefac418c.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/01eeb6b8dbf439f7c4f9fcbc0e63d13169e726efd5cae05f46d428abefac418c.json"},{"id":"0210dbf266ee7510f728909a266a462b2915e047959224c705b00cabf1fc2057","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/0210dbf266ee7510f728909a266a462b2915e047959224c705b00cabf1fc2057.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/0210dbf266ee7510f728909a266a462b2915e047959224c705b00cabf1fc2057.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/0210dbf266ee7510f728909a266a462b2915e047959224c705b00cabf1fc2057.json"},{"id":"0251c471188388289cc46dfc9d6c6fdc10a4ab7c8faca2ceee012ab84e3ef0e2","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/0251c471188388289cc46dfc9d6c6fdc10a4ab7c8faca2ceee012ab84e3ef0e2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/0251c471188388289cc46dfc9d6c6fdc10a4ab7c8faca2ceee012ab84e3ef0e2.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/0251c471188388289cc46dfc9d6c6fdc10a4ab7c8faca2ceee012ab84e3ef0e2.json"},{"id":"028bd0d02119e9ab7ab6fe1bc15197c6566f79e93d6348e307a0c05bb610fff3","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/028bd0d02119e9ab7ab6fe1bc15197c6566f79e93d6348e307a0c05bb610fff3.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/028bd0d02119e9ab7ab6fe1bc15197c6566f79e93d6348e307a0c05bb610fff3.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/028bd0d02119e9ab7ab6fe1bc15197c6566f79e93d6348e307a0c05bb610fff3.json"},{"id":"02c00ff3a7bdff797e8691aa9e9b97253146ee487b32d13f74a332d6f1e70cb1","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/02c00ff3a7bdff797e8691aa9e9b97253146ee487b32d13f74a332d6f1e70cb1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/02c00ff3a7bdff797e8691aa9e9b97253146ee487b32d13f74a332d6f1e70cb1.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/02c00ff3a7bdff797e8691aa9e9b97253146ee487b32d13f74a332d6f1e70cb1.json"},{"id":"031adcbf87d77127761a98865759b5934bc2b303ab4655270e2f24e3b9bc3180","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/031adcbf87d77127761a98865759b5934bc2b303ab4655270e2f24e3b9bc3180.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/031adcbf87d77127761a98865759b5934bc2b303ab4655270e2f24e3b9bc3180.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/031adcbf87d77127761a98865759b5934bc2b303ab4655270e2f24e3b9bc3180.json"},{"id":"0326e292fcf34496fa2291405d9960c23776ebb9b5bca1dba3595031383800a8","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/0326e292fcf34496fa2291405d9960c23776ebb9b5bca1dba3595031383800a8.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/0326e292fcf34496fa2291405d9960c23776ebb9b5bca1dba3595031383800a8.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/0326e292fcf34496fa2291405d9960c23776ebb9b5bca1dba3595031383800a8.json"},{"id":"033e7a001fc093aa60ec88af72549319f7a2cbd4cc159fa7110d33399665a8ab","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/033e7a001fc093aa60ec88af72549319f7a2cbd4cc159fa7110d33399665a8ab.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/033e7a001fc093aa60ec88af72549319f7a2cbd4cc159fa7110d33399665a8ab.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/033e7a001fc093aa60ec88af72549319f7a2cbd4cc159fa7110d33399665a8ab.json"},{"id":"03ad1cf39ae4b69745a0cca24365ea05f25fb1b357d7e10508c26dafb0a961d1","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/03ad1cf39ae4b69745a0cca24365ea05f25fb1b357d7e10508c26dafb0a961d1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/03ad1cf39ae4b69745a0cca24365ea05f25fb1b357d7e10508c26dafb0a961d1.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/03ad1cf39ae4b69745a0cca24365ea05f25fb1b357d7e10508c26dafb0a961d1.json"},{"id":"03b7fbe0a14fa38d56abad12ae8ca9dc357d4a4f11309f69f3cac8e054103090","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/03b7fbe0a14fa38d56abad12ae8ca9dc357d4a4f11309f69f3cac8e054103090.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/03b7fbe0a14fa38d56abad12ae8ca9dc357d4a4f11309f69f3cac8e054103090.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/03b7fbe0a14fa38d56abad12ae8ca9dc357d4a4f11309f69f3cac8e054103090.json"},{"id":"03fc001dcc650c843e9f76a3740ee67f525e472dbd6761327db11c2cf171c239","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/03fc001dcc650c843e9f76a3740ee67f525e472dbd6761327db11c2cf171c239.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/03fc001dcc650c843e9f76a3740ee67f525e472dbd6761327db11c2cf171c239.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/03fc001dcc650c843e9f76a3740ee67f525e472dbd6761327db11c2cf171c239.json"},{"id":"0410bc563f4a46d82f03ee04029d86285b7dce4ae78c19ec7552ed9cabe7bf94","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/0410bc563f4a46d82f03ee04029d86285b7dce4ae78c19ec7552ed9cabe7bf94.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/0410bc563f4a46d82f03ee04029d86285b7dce4ae78c19ec7552ed9cabe7bf94.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/0410bc563f4a46d82f03ee04029d86285b7dce4ae78c19ec7552ed9cabe7bf94.json"},{"id":"041186b5389f195e71cee2c193717951be6247d709a3fe815a6c6e63b441788a","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/041186b5389f195e71cee2c193717951be6247d709a3fe815a6c6e63b441788a.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/041186b5389f195e71cee2c193717951be6247d709a3fe815a6c6e63b441788a.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/041186b5389f195e71cee2c193717951be6247d709a3fe815a6c6e63b441788a.json"},{"id":"046254046f781cb47a759b4e9c9e5e58a7c89662e7e1b32fce43ade4fad55859","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/046254046f781cb47a759b4e9c9e5e58a7c89662e7e1b32fce43ade4fad55859.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/046254046f781cb47a759b4e9c9e5e58a7c89662e7e1b32fce43ade4fad55859.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/046254046f781cb47a759b4e9c9e5e58a7c89662e7e1b32fce43ade4fad55859.json"},{"id":"04eb5fdd6395cb04d116b1ce5152a0c42301cc07066a0444af57644c74df847a","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/04eb5fdd6395cb04d116b1ce5152a0c42301cc07066a0444af57644c74df847a.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/04eb5fdd6395cb04d116b1ce5152a0c42301cc07066a0444af57644c74df847a.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/04eb5fdd6395cb04d116b1ce5152a0c42301cc07066a0444af57644c74df847a.json"},{"id":"056d16e4b1e70bdb5f5669d7d4a54982faebaa461a4b840cc1023b3db169cd2f","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/056d16e4b1e70bdb5f5669d7d4a54982faebaa461a4b840cc1023b3db169cd2f.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/056d16e4b1e70bdb5f5669d7d4a54982faebaa461a4b840cc1023b3db169cd2f.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/056d16e4b1e70bdb5f5669d7d4a54982faebaa461a4b840cc1023b3db169cd2f.json"},{"id":"05bec144fff71c5904aa2b68416623270a0b5f33529a05b92eb0dc24abdf3968","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/05bec144fff71c5904aa2b68416623270a0b5f33529a05b92eb0dc24abdf3968.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/05bec144fff71c5904aa2b68416623270a0b5f33529a05b92eb0dc24abdf3968.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/05bec144fff71c5904aa2b68416623270a0b5f33529a05b92eb0dc24abdf3968.json"},{"id":"05e94a79048e4892cd33761a4913b040472863af07341a83a56649611d6388bd","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/05e94a79048e4892cd33761a4913b040472863af07341a83a56649611d6388bd.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/05e94a79048e4892cd33761a4913b040472863af07341a83a56649611d6388bd.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/05e94a79048e4892cd33761a4913b040472863af07341a83a56649611d6388bd.json"},{"id":"05ec529dcdae0b8bf4baf79883a4c2a403311479262a4691dbafd2629f6ee25c","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/05ec529dcdae0b8bf4baf79883a4c2a403311479262a4691dbafd2629f6ee25c.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/05ec529dcdae0b8bf4baf79883a4c2a403311479262a4691dbafd2629f6ee25c.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/05ec529dcdae0b8bf4baf79883a4c2a403311479262a4691dbafd2629f6ee25c.json"},{"id":"062be2a29a95c913210111713ef8c1bce4a893233a24669ebe12e618b54900d0","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/062be2a29a95c913210111713ef8c1bce4a893233a24669ebe12e618b54900d0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/062be2a29a95c913210111713ef8c1bce4a893233a24669ebe12e618b54900d0.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/062be2a29a95c913210111713ef8c1bce4a893233a24669ebe12e618b54900d0.json"},{"id":"06946906558821c60b39e780d5f56f9d850cf1bc720dbb5c8a89a3700aa5cbc9","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/06946906558821c60b39e780d5f56f9d850cf1bc720dbb5c8a89a3700aa5cbc9.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/06946906558821c60b39e780d5f56f9d850cf1bc720dbb5c8a89a3700aa5cbc9.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/06946906558821c60b39e780d5f56f9d850cf1bc720dbb5c8a89a3700aa5cbc9.json"},{"id":"06e6238ac60d90b11dcf350dc2beba32d526ff9f3e5ce22661c4cbd7cda5533e","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/06e6238ac60d90b11dcf350dc2beba32d526ff9f3e5ce22661c4cbd7cda5533e.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/06e6238ac60d90b11dcf350dc2beba32d526ff9f3e5ce22661c4cbd7cda5533e.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/06e6238ac60d90b11dcf350dc2beba32d526ff9f3e5ce22661c4cbd7cda5533e.json"},{"id":"06e6892063323397663eb81061279228e68154a09199f806105c074acc4c7d9a","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/06e6892063323397663eb81061279228e68154a09199f806105c074acc4c7d9a.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/06e6892063323397663eb81061279228e68154a09199f806105c074acc4c7d9a.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/06e6892063323397663eb81061279228e68154a09199f806105c074acc4c7d9a.json"},{"id":"0728598632429b7bddb0c7b9457fd2c4c452d217017ee7e53ec97f13416e11a5","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/0728598632429b7bddb0c7b9457fd2c4c452d217017ee7e53ec97f13416e11a5.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/0728598632429b7bddb0c7b9457fd2c4c452d217017ee7e53ec97f13416e11a5.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/0728598632429b7bddb0c7b9457fd2c4c452d217017ee7e53ec97f13416e11a5.json"},{"id":"077ca5d30f35c90a58e932b5837bfd8abd078209bc083374871430ee6faa8dfd","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/077ca5d30f35c90a58e932b5837bfd8abd078209bc083374871430ee6faa8dfd.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/077ca5d30f35c90a58e932b5837bfd8abd078209bc083374871430ee6faa8dfd.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/077ca5d30f35c90a58e932b5837bfd8abd078209bc083374871430ee6faa8dfd.json"},{"id":"07d3084586717543b7f0b4d2805c1a39f6ace02baac45258e5f226d4d2d05704","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/07d3084586717543b7f0b4d2805c1a39f6ace02baac45258e5f226d4d2d05704.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/07d3084586717543b7f0b4d2805c1a39f6ace02baac45258e5f226d4d2d05704.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/07d3084586717543b7f0b4d2805c1a39f6ace02baac45258e5f226d4d2d05704.json"},{"id":"087facdb452cfd166c00c133744a79ba2e1970517bd86335fe53992f77ebf1c3","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/087facdb452cfd166c00c133744a79ba2e1970517bd86335fe53992f77ebf1c3.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/087facdb452cfd166c00c133744a79ba2e1970517bd86335fe53992f77ebf1c3.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/087facdb452cfd166c00c133744a79ba2e1970517bd86335fe53992f77ebf1c3.json"},{"id":"08c4afa9997c9f3740065319390550cc65cdd32ee7e1e5f39a8118485a6d19dc","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/08c4afa9997c9f3740065319390550cc65cdd32ee7e1e5f39a8118485a6d19dc.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/08c4afa9997c9f3740065319390550cc65cdd32ee7e1e5f39a8118485a6d19dc.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/08c4afa9997c9f3740065319390550cc65cdd32ee7e1e5f39a8118485a6d19dc.json"},{"id":"096b2912c15ea8174411d7873c788b3df53faaaeeac5965488f14bbe3c0911b2","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/096b2912c15ea8174411d7873c788b3df53faaaeeac5965488f14bbe3c0911b2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/096b2912c15ea8174411d7873c788b3df53faaaeeac5965488f14bbe3c0911b2.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/096b2912c15ea8174411d7873c788b3df53faaaeeac5965488f14bbe3c0911b2.json"},{"id":"09a0f6a8f237ecd6149d4259d99e47941f5d68f7984b120d2b2e4da2d3a39cd4","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/09a0f6a8f237ecd6149d4259d99e47941f5d68f7984b120d2b2e4da2d3a39cd4.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/09a0f6a8f237ecd6149d4259d99e47941f5d68f7984b120d2b2e4da2d3a39cd4.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/09a0f6a8f237ecd6149d4259d99e47941f5d68f7984b120d2b2e4da2d3a39cd4.json"},{"id":"09fc27f314419a25e9d394defd5b25e749518b9908a5f5d67f96a8f1ca171fc7","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/09fc27f314419a25e9d394defd5b25e749518b9908a5f5d67f96a8f1ca171fc7.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/09fc27f314419a25e9d394defd5b25e749518b9908a5f5d67f96a8f1ca171fc7.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/09fc27f314419a25e9d394defd5b25e749518b9908a5f5d67f96a8f1ca171fc7.json"},{"id":"09fd950d22c46821ae864455e64542b76564c458cec1dfa240bea647aee0c45b","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/09fd950d22c46821ae864455e64542b76564c458cec1dfa240bea647aee0c45b.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/09fd950d22c46821ae864455e64542b76564c458cec1dfa240bea647aee0c45b.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/09fd950d22c46821ae864455e64542b76564c458cec1dfa240bea647aee0c45b.json"},{"id":"0a4fdea71055944e3a4e76e463d98ffadb4ec7087c1f6d7eff3cab512c1a6994","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/0a4fdea71055944e3a4e76e463d98ffadb4ec7087c1f6d7eff3cab512c1a6994.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/0a4fdea71055944e3a4e76e463d98ffadb4ec7087c1f6d7eff3cab512c1a6994.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/0a4fdea71055944e3a4e76e463d98ffadb4ec7087c1f6d7eff3cab512c1a6994.json"},{"id":"0a5c32ef7c9a845fa429466c7e2e43225f2de91fab94632ad7e14e31e25f0571","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/0a5c32ef7c9a845fa429466c7e2e43225f2de91fab94632ad7e14e31e25f0571.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/0a5c32ef7c9a845fa429466c7e2e43225f2de91fab94632ad7e14e31e25f0571.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/0a5c32ef7c9a845fa429466c7e2e43225f2de91fab94632ad7e14e31e25f0571.json"},{"id":"0a72fa1e525e574aa5c7582c5bef6cbd1b921996c93e1f7f8c7545438b7b3ce2","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/0a72fa1e525e574aa5c7582c5bef6cbd1b921996c93e1f7f8c7545438b7b3ce2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/0a72fa1e525e574aa5c7582c5bef6cbd1b921996c93e1f7f8c7545438b7b3ce2.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/0a72fa1e525e574aa5c7582c5bef6cbd1b921996c93e1f7f8c7545438b7b3ce2.json"},{"id":"0b9716a02fbab72aef256407d5c37d0b541e9ff8efdab991401c820af7404ed1","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/0b9716a02fbab72aef256407d5c37d0b541e9ff8efdab991401c820af7404ed1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/0b9716a02fbab72aef256407d5c37d0b541e9ff8efdab991401c820af7404ed1.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/0b9716a02fbab72aef256407d5c37d0b541e9ff8efdab991401c820af7404ed1.json"},{"id":"0c53ee8e2a5eec6dddcc3d0e0a5707b62fb028c2adbe7cb4ca372233ac69306f","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/0c53ee8e2a5eec6dddcc3d0e0a5707b62fb028c2adbe7cb4ca372233ac69306f.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/0c53ee8e2a5eec6dddcc3d0e0a5707b62fb028c2adbe7cb4ca372233ac69306f.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/0c53ee8e2a5eec6dddcc3d0e0a5707b62fb028c2adbe7cb4ca372233ac69306f.json"},{"id":"0c60634a9923c3fdcd292aab3dbe4332fd6463804cca1faf8348e2aeed1e0c7a","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/0c60634a9923c3fdcd292aab3dbe4332fd6463804cca1faf8348e2aeed1e0c7a.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/0c60634a9923c3fdcd292aab3dbe4332fd6463804cca1faf8348e2aeed1e0c7a.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/0c60634a9923c3fdcd292aab3dbe4332fd6463804cca1faf8348e2aeed1e0c7a.json"},{"id":"0c75b08d5a00fe7deffe246988270dc621411851983588740c3128650aaa2917","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/0c75b08d5a00fe7deffe246988270dc621411851983588740c3128650aaa2917.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/0c75b08d5a00fe7deffe246988270dc621411851983588740c3128650aaa2917.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/0c75b08d5a00fe7deffe246988270dc621411851983588740c3128650aaa2917.json"},{"id":"0cd473fb0ba750de0e36157c5046b7aab98afdb0d776c75cb6adb4439752c21f","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/0cd473fb0ba750de0e36157c5046b7aab98afdb0d776c75cb6adb4439752c21f.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/0cd473fb0ba750de0e36157c5046b7aab98afdb0d776c75cb6adb4439752c21f.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/0cd473fb0ba750de0e36157c5046b7aab98afdb0d776c75cb6adb4439752c21f.json"},{"id":"0d236c49caf28d5a307e44c1d1fca6a6c72e99fb474aa961903f8e244306a0d6","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/0d236c49caf28d5a307e44c1d1fca6a6c72e99fb474aa961903f8e244306a0d6.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/0d236c49caf28d5a307e44c1d1fca6a6c72e99fb474aa961903f8e244306a0d6.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/0d236c49caf28d5a307e44c1d1fca6a6c72e99fb474aa961903f8e244306a0d6.json"},{"id":"0d3afca018ec48f2abd2794f9afbd23d8741f83d557a6c6fad92b7a2cb004948","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/0d3afca018ec48f2abd2794f9afbd23d8741f83d557a6c6fad92b7a2cb004948.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/0d3afca018ec48f2abd2794f9afbd23d8741f83d557a6c6fad92b7a2cb004948.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/0d3afca018ec48f2abd2794f9afbd23d8741f83d557a6c6fad92b7a2cb004948.json"},{"id":"0d52395674e58d1743ea84509de822fd2aaa2c0b371d273e9a0004e26587d717","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/0d52395674e58d1743ea84509de822fd2aaa2c0b371d273e9a0004e26587d717.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/0d52395674e58d1743ea84509de822fd2aaa2c0b371d273e9a0004e26587d717.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/0d52395674e58d1743ea84509de822fd2aaa2c0b371d273e9a0004e26587d717.json"},{"id":"0d5c3ca381a5dd7abd8852af7361a5b776d45d810598a32678a936ceb72f2a94","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/0d5c3ca381a5dd7abd8852af7361a5b776d45d810598a32678a936ceb72f2a94.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/0d5c3ca381a5dd7abd8852af7361a5b776d45d810598a32678a936ceb72f2a94.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/0d5c3ca381a5dd7abd8852af7361a5b776d45d810598a32678a936ceb72f2a94.json"},{"id":"0d5e9541f5b65188e791d901299e66b634f4abedd27886491916b8f7ae2061b4","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/0d5e9541f5b65188e791d901299e66b634f4abedd27886491916b8f7ae2061b4.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/0d5e9541f5b65188e791d901299e66b634f4abedd27886491916b8f7ae2061b4.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/0d5e9541f5b65188e791d901299e66b634f4abedd27886491916b8f7ae2061b4.json"},{"id":"0d92e623614d68de4536ec1849d62dadd4ac8ee9a731d2e8b50cae0898a75676","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/0d92e623614d68de4536ec1849d62dadd4ac8ee9a731d2e8b50cae0898a75676.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/0d92e623614d68de4536ec1849d62dadd4ac8ee9a731d2e8b50cae0898a75676.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/0d92e623614d68de4536ec1849d62dadd4ac8ee9a731d2e8b50cae0898a75676.json"},{"id":"0df9441849a2e4f315b3fec6e2f53a71ef3d5eb0209bcd0219af16a41608d990","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/0df9441849a2e4f315b3fec6e2f53a71ef3d5eb0209bcd0219af16a41608d990.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/0df9441849a2e4f315b3fec6e2f53a71ef3d5eb0209bcd0219af16a41608d990.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/0df9441849a2e4f315b3fec6e2f53a71ef3d5eb0209bcd0219af16a41608d990.json"},{"id":"0e76b7ed5697891c3c2c60fc37095d29f261df092fad52a4360d0073836e4270","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/0e76b7ed5697891c3c2c60fc37095d29f261df092fad52a4360d0073836e4270.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/0e76b7ed5697891c3c2c60fc37095d29f261df092fad52a4360d0073836e4270.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/0e76b7ed5697891c3c2c60fc37095d29f261df092fad52a4360d0073836e4270.json"},{"id":"0ea55a10542e0dbf47dcb0fcb893d6bdc55ee47d3ff35fc9b8b5833e1f9e0f19","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/0ea55a10542e0dbf47dcb0fcb893d6bdc55ee47d3ff35fc9b8b5833e1f9e0f19.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/0ea55a10542e0dbf47dcb0fcb893d6bdc55ee47d3ff35fc9b8b5833e1f9e0f19.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/0ea55a10542e0dbf47dcb0fcb893d6bdc55ee47d3ff35fc9b8b5833e1f9e0f19.json"},{"id":"0eb2c78430a710e1084d2ccdc9427c003baa31394189d3b8eec29bd377150b85","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/0eb2c78430a710e1084d2ccdc9427c003baa31394189d3b8eec29bd377150b85.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/0eb2c78430a710e1084d2ccdc9427c003baa31394189d3b8eec29bd377150b85.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/0eb2c78430a710e1084d2ccdc9427c003baa31394189d3b8eec29bd377150b85.json"},{"id":"0f45874f99d4509c6f7ae4bf6bb297ded58fcba1450d9e1c6f7186664552af6f","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/0f45874f99d4509c6f7ae4bf6bb297ded58fcba1450d9e1c6f7186664552af6f.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/0f45874f99d4509c6f7ae4bf6bb297ded58fcba1450d9e1c6f7186664552af6f.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/0f45874f99d4509c6f7ae4bf6bb297ded58fcba1450d9e1c6f7186664552af6f.json"},{"id":"0f546192a802bee88ceaa12632b9fcd0ad74e7cbb7d20f61f9d4ee0162e5f79a","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/0f546192a802bee88ceaa12632b9fcd0ad74e7cbb7d20f61f9d4ee0162e5f79a.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/0f546192a802bee88ceaa12632b9fcd0ad74e7cbb7d20f61f9d4ee0162e5f79a.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/0f546192a802bee88ceaa12632b9fcd0ad74e7cbb7d20f61f9d4ee0162e5f79a.json"},{"id":"1072b08f7e7b5aaafff1a72a2492ef197add2592e284d9ab30ac01ff80c8eaca","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/1072b08f7e7b5aaafff1a72a2492ef197add2592e284d9ab30ac01ff80c8eaca.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/1072b08f7e7b5aaafff1a72a2492ef197add2592e284d9ab30ac01ff80c8eaca.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/1072b08f7e7b5aaafff1a72a2492ef197add2592e284d9ab30ac01ff80c8eaca.json"},{"id":"1081ad7a066516917ce50c22f903cf3843a10af591c6b67986d77c72e5e6e0a5","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/1081ad7a066516917ce50c22f903cf3843a10af591c6b67986d77c72e5e6e0a5.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/1081ad7a066516917ce50c22f903cf3843a10af591c6b67986d77c72e5e6e0a5.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/1081ad7a066516917ce50c22f903cf3843a10af591c6b67986d77c72e5e6e0a5.json"},{"id":"112a57d3d0cc21b1821f0056b27b16ecdcbc67c8b00a4e93ed3557724d897efe","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/112a57d3d0cc21b1821f0056b27b16ecdcbc67c8b00a4e93ed3557724d897efe.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/112a57d3d0cc21b1821f0056b27b16ecdcbc67c8b00a4e93ed3557724d897efe.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/112a57d3d0cc21b1821f0056b27b16ecdcbc67c8b00a4e93ed3557724d897efe.json"},{"id":"11a6598d25b1f01976c9134794f395e1bed9975f5dc4940b710cadcba113625a","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/11a6598d25b1f01976c9134794f395e1bed9975f5dc4940b710cadcba113625a.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/11a6598d25b1f01976c9134794f395e1bed9975f5dc4940b710cadcba113625a.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/11a6598d25b1f01976c9134794f395e1bed9975f5dc4940b710cadcba113625a.json"},{"id":"128b01b8cc38ccb5557ed5e453acc1ef100ae059ca37e212eaf3f2df14b41c28","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/128b01b8cc38ccb5557ed5e453acc1ef100ae059ca37e212eaf3f2df14b41c28.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/128b01b8cc38ccb5557ed5e453acc1ef100ae059ca37e212eaf3f2df14b41c28.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/128b01b8cc38ccb5557ed5e453acc1ef100ae059ca37e212eaf3f2df14b41c28.json"},{"id":"12bc717c95c025495840dd99f7ff47cf102a7b23dbb16b7e82ef43809edf533a","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/12bc717c95c025495840dd99f7ff47cf102a7b23dbb16b7e82ef43809edf533a.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/12bc717c95c025495840dd99f7ff47cf102a7b23dbb16b7e82ef43809edf533a.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/12bc717c95c025495840dd99f7ff47cf102a7b23dbb16b7e82ef43809edf533a.json"},{"id":"131fde40efd37fb558a8637b33f2509e126e76083fa37bff21755d73609b80c1","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/131fde40efd37fb558a8637b33f2509e126e76083fa37bff21755d73609b80c1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/131fde40efd37fb558a8637b33f2509e126e76083fa37bff21755d73609b80c1.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/131fde40efd37fb558a8637b33f2509e126e76083fa37bff21755d73609b80c1.json"},{"id":"13465564de59d0da94b22ddfa6e2c6f7f39610a750eab40a9b75a18098d06505","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/13465564de59d0da94b22ddfa6e2c6f7f39610a750eab40a9b75a18098d06505.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/13465564de59d0da94b22ddfa6e2c6f7f39610a750eab40a9b75a18098d06505.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/13465564de59d0da94b22ddfa6e2c6f7f39610a750eab40a9b75a18098d06505.json"},{"id":"135034704645402e07cb0577ef3e73171297d64d4cdb5e29fe2126ed72c21f27","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/135034704645402e07cb0577ef3e73171297d64d4cdb5e29fe2126ed72c21f27.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/135034704645402e07cb0577ef3e73171297d64d4cdb5e29fe2126ed72c21f27.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/135034704645402e07cb0577ef3e73171297d64d4cdb5e29fe2126ed72c21f27.json"},{"id":"135dbef881a530b95f4427b71e8332fa352c22cdf82a12abc404137a2ddbca36","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/135dbef881a530b95f4427b71e8332fa352c22cdf82a12abc404137a2ddbca36.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/135dbef881a530b95f4427b71e8332fa352c22cdf82a12abc404137a2ddbca36.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/135dbef881a530b95f4427b71e8332fa352c22cdf82a12abc404137a2ddbca36.json"},{"id":"13c3a9684344c5f16bc503cae68c24de2442f09b544339213d13c23bc629f19a","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/13c3a9684344c5f16bc503cae68c24de2442f09b544339213d13c23bc629f19a.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/13c3a9684344c5f16bc503cae68c24de2442f09b544339213d13c23bc629f19a.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/13c3a9684344c5f16bc503cae68c24de2442f09b544339213d13c23bc629f19a.json"},{"id":"141a7ab57907f924e61a0fd051fca8c2a6272ad583424bbf9d768875108d1218","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/141a7ab57907f924e61a0fd051fca8c2a6272ad583424bbf9d768875108d1218.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/141a7ab57907f924e61a0fd051fca8c2a6272ad583424bbf9d768875108d1218.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/141a7ab57907f924e61a0fd051fca8c2a6272ad583424bbf9d768875108d1218.json"},{"id":"148701b149c8ddbf14cf9f70b362c7300d75eead58aedb0393e1f067fec0501c","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/148701b149c8ddbf14cf9f70b362c7300d75eead58aedb0393e1f067fec0501c.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/148701b149c8ddbf14cf9f70b362c7300d75eead58aedb0393e1f067fec0501c.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/148701b149c8ddbf14cf9f70b362c7300d75eead58aedb0393e1f067fec0501c.json"},{"id":"14b1e8773b8931e50b2ada676c5fdc66cca6bcf62340a8dfe6cc253a0821c820","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/14b1e8773b8931e50b2ada676c5fdc66cca6bcf62340a8dfe6cc253a0821c820.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/14b1e8773b8931e50b2ada676c5fdc66cca6bcf62340a8dfe6cc253a0821c820.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/14b1e8773b8931e50b2ada676c5fdc66cca6bcf62340a8dfe6cc253a0821c820.json"},{"id":"14e3c166b05f044963176711def1010b569bfb1560df108ba71a355922fbfc16","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/14e3c166b05f044963176711def1010b569bfb1560df108ba71a355922fbfc16.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/14e3c166b05f044963176711def1010b569bfb1560df108ba71a355922fbfc16.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/14e3c166b05f044963176711def1010b569bfb1560df108ba71a355922fbfc16.json"},{"id":"14e591171063bd9a5dde3a765d1629c51300d23e56dfe38f6ea34e4e4cc626a6","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/14e591171063bd9a5dde3a765d1629c51300d23e56dfe38f6ea34e4e4cc626a6.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/14e591171063bd9a5dde3a765d1629c51300d23e56dfe38f6ea34e4e4cc626a6.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/14e591171063bd9a5dde3a765d1629c51300d23e56dfe38f6ea34e4e4cc626a6.json"},{"id":"153e3dc0fba27e4ac32f726e29abf62cf17ee5f41f93951f6fa8d1f3c94965c8","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/153e3dc0fba27e4ac32f726e29abf62cf17ee5f41f93951f6fa8d1f3c94965c8.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/153e3dc0fba27e4ac32f726e29abf62cf17ee5f41f93951f6fa8d1f3c94965c8.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/153e3dc0fba27e4ac32f726e29abf62cf17ee5f41f93951f6fa8d1f3c94965c8.json"},{"id":"154bd2967a27f805a32c40098ce5b20f52864be94da7189be984fe6f1fc232e9","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/154bd2967a27f805a32c40098ce5b20f52864be94da7189be984fe6f1fc232e9.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/154bd2967a27f805a32c40098ce5b20f52864be94da7189be984fe6f1fc232e9.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/154bd2967a27f805a32c40098ce5b20f52864be94da7189be984fe6f1fc232e9.json"},{"id":"1554225a08d7ad0c43f64ca5f55c8ff89edf5fc1b64f355a4b6d4ff00afed108","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/1554225a08d7ad0c43f64ca5f55c8ff89edf5fc1b64f355a4b6d4ff00afed108.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/1554225a08d7ad0c43f64ca5f55c8ff89edf5fc1b64f355a4b6d4ff00afed108.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/1554225a08d7ad0c43f64ca5f55c8ff89edf5fc1b64f355a4b6d4ff00afed108.json"},{"id":"156b92dd1085abb429440f300950bf589c246fbb06dfbeaa86f22d766b002260","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/156b92dd1085abb429440f300950bf589c246fbb06dfbeaa86f22d766b002260.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/156b92dd1085abb429440f300950bf589c246fbb06dfbeaa86f22d766b002260.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/156b92dd1085abb429440f300950bf589c246fbb06dfbeaa86f22d766b002260.json"},{"id":"15add7ae83e5c647a6eb7ce5140ed8ad6491b7ad30f04f16738df0135365c09e","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/15add7ae83e5c647a6eb7ce5140ed8ad6491b7ad30f04f16738df0135365c09e.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/15add7ae83e5c647a6eb7ce5140ed8ad6491b7ad30f04f16738df0135365c09e.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/15add7ae83e5c647a6eb7ce5140ed8ad6491b7ad30f04f16738df0135365c09e.json"},{"id":"15c46e67ec2cf7b291a72c2fe85540c814cd2d50c9bcce95f772220adbde9b66","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/15c46e67ec2cf7b291a72c2fe85540c814cd2d50c9bcce95f772220adbde9b66.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/15c46e67ec2cf7b291a72c2fe85540c814cd2d50c9bcce95f772220adbde9b66.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/15c46e67ec2cf7b291a72c2fe85540c814cd2d50c9bcce95f772220adbde9b66.json"},{"id":"15d33a71c63df037c9fd4cbc8eef78a6728b24f515a27503ecbb73cefaae76b7","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/15d33a71c63df037c9fd4cbc8eef78a6728b24f515a27503ecbb73cefaae76b7.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/15d33a71c63df037c9fd4cbc8eef78a6728b24f515a27503ecbb73cefaae76b7.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/15d33a71c63df037c9fd4cbc8eef78a6728b24f515a27503ecbb73cefaae76b7.json"},{"id":"160a0e4fe396691ecfdaadca847b15bd6018cfd8ad601b11bd0b65c80d300b69","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/160a0e4fe396691ecfdaadca847b15bd6018cfd8ad601b11bd0b65c80d300b69.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/160a0e4fe396691ecfdaadca847b15bd6018cfd8ad601b11bd0b65c80d300b69.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/160a0e4fe396691ecfdaadca847b15bd6018cfd8ad601b11bd0b65c80d300b69.json"},{"id":"16185f8844e568e4765dd87138f806e185d7750c8099e8e722056059d171e3a0","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/16185f8844e568e4765dd87138f806e185d7750c8099e8e722056059d171e3a0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/16185f8844e568e4765dd87138f806e185d7750c8099e8e722056059d171e3a0.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/16185f8844e568e4765dd87138f806e185d7750c8099e8e722056059d171e3a0.json"},{"id":"17aa6c54b0c9d5d98079deb0fa05bd8552d8dd3b630a98b3705a9ae2eae32c7d","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/17aa6c54b0c9d5d98079deb0fa05bd8552d8dd3b630a98b3705a9ae2eae32c7d.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/17aa6c54b0c9d5d98079deb0fa05bd8552d8dd3b630a98b3705a9ae2eae32c7d.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/17aa6c54b0c9d5d98079deb0fa05bd8552d8dd3b630a98b3705a9ae2eae32c7d.json"},{"id":"1829f80f94e0706b40631cc5d0bf8936490733fb8c24b204611a237bcc571112","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/1829f80f94e0706b40631cc5d0bf8936490733fb8c24b204611a237bcc571112.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/1829f80f94e0706b40631cc5d0bf8936490733fb8c24b204611a237bcc571112.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/1829f80f94e0706b40631cc5d0bf8936490733fb8c24b204611a237bcc571112.json"},{"id":"1835a0a967ba57cddf55089a103dafae403f60d8ee66c33f5b49d4526ddfb6c2","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/1835a0a967ba57cddf55089a103dafae403f60d8ee66c33f5b49d4526ddfb6c2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/1835a0a967ba57cddf55089a103dafae403f60d8ee66c33f5b49d4526ddfb6c2.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/1835a0a967ba57cddf55089a103dafae403f60d8ee66c33f5b49d4526ddfb6c2.json"},{"id":"18380abdedede9377a078cb1b2ca5bd5dbbda7f099c7a39e9659a357ca32d32f","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/18380abdedede9377a078cb1b2ca5bd5dbbda7f099c7a39e9659a357ca32d32f.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/18380abdedede9377a078cb1b2ca5bd5dbbda7f099c7a39e9659a357ca32d32f.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/18380abdedede9377a078cb1b2ca5bd5dbbda7f099c7a39e9659a357ca32d32f.json"},{"id":"18ffe397e8de8d9f4da04e560670af83937697b341eadec0e766c180a95d1266","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/18ffe397e8de8d9f4da04e560670af83937697b341eadec0e766c180a95d1266.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/18ffe397e8de8d9f4da04e560670af83937697b341eadec0e766c180a95d1266.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/18ffe397e8de8d9f4da04e560670af83937697b341eadec0e766c180a95d1266.json"},{"id":"1912c3f50fa5836645af9ea72f7f9c85f569b9294a07fd40cd57eedba60ae4c9","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/1912c3f50fa5836645af9ea72f7f9c85f569b9294a07fd40cd57eedba60ae4c9.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/1912c3f50fa5836645af9ea72f7f9c85f569b9294a07fd40cd57eedba60ae4c9.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/1912c3f50fa5836645af9ea72f7f9c85f569b9294a07fd40cd57eedba60ae4c9.json"},{"id":"194b9e06a145a516084d98e50757fc9cf1535d72ae5eb70c8b285858fbd003a5","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/194b9e06a145a516084d98e50757fc9cf1535d72ae5eb70c8b285858fbd003a5.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/194b9e06a145a516084d98e50757fc9cf1535d72ae5eb70c8b285858fbd003a5.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/194b9e06a145a516084d98e50757fc9cf1535d72ae5eb70c8b285858fbd003a5.json"},{"id":"19d49361c32e6dd968dca15199fb7d8b26dea7abe43a72b1099f79d5f55d71b8","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/19d49361c32e6dd968dca15199fb7d8b26dea7abe43a72b1099f79d5f55d71b8.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/19d49361c32e6dd968dca15199fb7d8b26dea7abe43a72b1099f79d5f55d71b8.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/19d49361c32e6dd968dca15199fb7d8b26dea7abe43a72b1099f79d5f55d71b8.json"},{"id":"1a5b2faf5c6b29fc7ae56f10a2143b884b394320d4a10ca40a2b5e076a22144b","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/1a5b2faf5c6b29fc7ae56f10a2143b884b394320d4a10ca40a2b5e076a22144b.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/1a5b2faf5c6b29fc7ae56f10a2143b884b394320d4a10ca40a2b5e076a22144b.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/1a5b2faf5c6b29fc7ae56f10a2143b884b394320d4a10ca40a2b5e076a22144b.json"},{"id":"1aaf142c93f4ba3920ff706687db099eb63c96898fb9f33989c3b7983e905712","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/1aaf142c93f4ba3920ff706687db099eb63c96898fb9f33989c3b7983e905712.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/1aaf142c93f4ba3920ff706687db099eb63c96898fb9f33989c3b7983e905712.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/1aaf142c93f4ba3920ff706687db099eb63c96898fb9f33989c3b7983e905712.json"},{"id":"1bea5da1c1c1ad46a1b61e73791cac7d3b013387fd42718a4a27d3206342d1f5","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/1bea5da1c1c1ad46a1b61e73791cac7d3b013387fd42718a4a27d3206342d1f5.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/1bea5da1c1c1ad46a1b61e73791cac7d3b013387fd42718a4a27d3206342d1f5.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/1bea5da1c1c1ad46a1b61e73791cac7d3b013387fd42718a4a27d3206342d1f5.json"},{"id":"1bf6409eaf5e4c53fdfef7c727f5070cf923e1d03661d89e9a5a2b5aeda2e078","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/1bf6409eaf5e4c53fdfef7c727f5070cf923e1d03661d89e9a5a2b5aeda2e078.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/1bf6409eaf5e4c53fdfef7c727f5070cf923e1d03661d89e9a5a2b5aeda2e078.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/1bf6409eaf5e4c53fdfef7c727f5070cf923e1d03661d89e9a5a2b5aeda2e078.json"},{"id":"1c3312bea393959b6735e283e0dc66ef3bf06d153a9c250c6609fecbb4f5e74c","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/1c3312bea393959b6735e283e0dc66ef3bf06d153a9c250c6609fecbb4f5e74c.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/1c3312bea393959b6735e283e0dc66ef3bf06d153a9c250c6609fecbb4f5e74c.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/1c3312bea393959b6735e283e0dc66ef3bf06d153a9c250c6609fecbb4f5e74c.json"},{"id":"1c3efae8168e7bb378bfb54fdc1edababb2e8323e91a523b7834d6a08b6d839f","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/1c3efae8168e7bb378bfb54fdc1edababb2e8323e91a523b7834d6a08b6d839f.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/1c3efae8168e7bb378bfb54fdc1edababb2e8323e91a523b7834d6a08b6d839f.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/1c3efae8168e7bb378bfb54fdc1edababb2e8323e91a523b7834d6a08b6d839f.json"},{"id":"1c47164d49788d62fc87dfa18c1a24fff534d75d4d3df30232a2378e5c0e1504","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/1c47164d49788d62fc87dfa18c1a24fff534d75d4d3df30232a2378e5c0e1504.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/1c47164d49788d62fc87dfa18c1a24fff534d75d4d3df30232a2378e5c0e1504.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/1c47164d49788d62fc87dfa18c1a24fff534d75d4d3df30232a2378e5c0e1504.json"},{"id":"1c6d66649e499d8743f6b88d5358bc9a12a2165c6a65aa08ae7d0191b29b8d47","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/1c6d66649e499d8743f6b88d5358bc9a12a2165c6a65aa08ae7d0191b29b8d47.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/1c6d66649e499d8743f6b88d5358bc9a12a2165c6a65aa08ae7d0191b29b8d47.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/1c6d66649e499d8743f6b88d5358bc9a12a2165c6a65aa08ae7d0191b29b8d47.json"},{"id":"1ccc2ebffc28e5c9f9042c36a00320554417fff25869bdec37b03ae7cf46b491","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/1ccc2ebffc28e5c9f9042c36a00320554417fff25869bdec37b03ae7cf46b491.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/1ccc2ebffc28e5c9f9042c36a00320554417fff25869bdec37b03ae7cf46b491.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/1ccc2ebffc28e5c9f9042c36a00320554417fff25869bdec37b03ae7cf46b491.json"},{"id":"1cd1c4fd9d2c5829f94f1849a5edd76ea45bedce134d7b06b8e6f1d85eb09274","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/1cd1c4fd9d2c5829f94f1849a5edd76ea45bedce134d7b06b8e6f1d85eb09274.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/1cd1c4fd9d2c5829f94f1849a5edd76ea45bedce134d7b06b8e6f1d85eb09274.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/1cd1c4fd9d2c5829f94f1849a5edd76ea45bedce134d7b06b8e6f1d85eb09274.json"},{"id":"1d0e26ad152c12d037cca5ac647d94a0b52e392ad922695597c65f6322a57c0f","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/1d0e26ad152c12d037cca5ac647d94a0b52e392ad922695597c65f6322a57c0f.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/1d0e26ad152c12d037cca5ac647d94a0b52e392ad922695597c65f6322a57c0f.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/1d0e26ad152c12d037cca5ac647d94a0b52e392ad922695597c65f6322a57c0f.json"},{"id":"1d150623e5889a2de526683d6855b76f62304f221e2cf853bc00be7a7028e8b4","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/1d150623e5889a2de526683d6855b76f62304f221e2cf853bc00be7a7028e8b4.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/1d150623e5889a2de526683d6855b76f62304f221e2cf853bc00be7a7028e8b4.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/1d150623e5889a2de526683d6855b76f62304f221e2cf853bc00be7a7028e8b4.json"},{"id":"1d60505c9b260716a8a5e2783fa857c32ab6e32b5df13e8a36d224642d29c992","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/1d60505c9b260716a8a5e2783fa857c32ab6e32b5df13e8a36d224642d29c992.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/1d60505c9b260716a8a5e2783fa857c32ab6e32b5df13e8a36d224642d29c992.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/1d60505c9b260716a8a5e2783fa857c32ab6e32b5df13e8a36d224642d29c992.json"},{"id":"1d92a5c48a1b53573a2ac22e63f1334944703551325b6a9b1f8e0cb5061db772","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/1d92a5c48a1b53573a2ac22e63f1334944703551325b6a9b1f8e0cb5061db772.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/1d92a5c48a1b53573a2ac22e63f1334944703551325b6a9b1f8e0cb5061db772.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/1d92a5c48a1b53573a2ac22e63f1334944703551325b6a9b1f8e0cb5061db772.json"},{"id":"1da00c8fcb3605cca96429fc900626679eaa2b1281f20db2bc0e657d21a5a592","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/1da00c8fcb3605cca96429fc900626679eaa2b1281f20db2bc0e657d21a5a592.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/1da00c8fcb3605cca96429fc900626679eaa2b1281f20db2bc0e657d21a5a592.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/1da00c8fcb3605cca96429fc900626679eaa2b1281f20db2bc0e657d21a5a592.json"},{"id":"1dd268054c5c81692c5970d1ca40641ea4ff766c1b70dce6eab6d8b144b3acca","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/1dd268054c5c81692c5970d1ca40641ea4ff766c1b70dce6eab6d8b144b3acca.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/1dd268054c5c81692c5970d1ca40641ea4ff766c1b70dce6eab6d8b144b3acca.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/1dd268054c5c81692c5970d1ca40641ea4ff766c1b70dce6eab6d8b144b3acca.json"},{"id":"1e71f954dd3d533d88f4a13d3d940bd5bc27dad5cdd9d97197af358ba3d44846","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/1e71f954dd3d533d88f4a13d3d940bd5bc27dad5cdd9d97197af358ba3d44846.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/1e71f954dd3d533d88f4a13d3d940bd5bc27dad5cdd9d97197af358ba3d44846.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/1e71f954dd3d533d88f4a13d3d940bd5bc27dad5cdd9d97197af358ba3d44846.json"},{"id":"1e7aac88494208a267416cefaaae3495f303cfede3c15711ab70cb1b5d460942","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/1e7aac88494208a267416cefaaae3495f303cfede3c15711ab70cb1b5d460942.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/1e7aac88494208a267416cefaaae3495f303cfede3c15711ab70cb1b5d460942.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/1e7aac88494208a267416cefaaae3495f303cfede3c15711ab70cb1b5d460942.json"},{"id":"1e7e6387472f1631f0577e33f32fdc49c5dd1b309e6f50e62088b753a41a7329","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/1e7e6387472f1631f0577e33f32fdc49c5dd1b309e6f50e62088b753a41a7329.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/1e7e6387472f1631f0577e33f32fdc49c5dd1b309e6f50e62088b753a41a7329.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/1e7e6387472f1631f0577e33f32fdc49c5dd1b309e6f50e62088b753a41a7329.json"},{"id":"1ea2b3cdc7c11f7fbcd0693b4ad9c037a7f19b4957763ca627c11ac361ce6a13","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/1ea2b3cdc7c11f7fbcd0693b4ad9c037a7f19b4957763ca627c11ac361ce6a13.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/1ea2b3cdc7c11f7fbcd0693b4ad9c037a7f19b4957763ca627c11ac361ce6a13.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/1ea2b3cdc7c11f7fbcd0693b4ad9c037a7f19b4957763ca627c11ac361ce6a13.json"},{"id":"1ea56177157dacd0f2a4b8a0717e9a82679703e10715e7baeea35ba465fd77d4","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/1ea56177157dacd0f2a4b8a0717e9a82679703e10715e7baeea35ba465fd77d4.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/1ea56177157dacd0f2a4b8a0717e9a82679703e10715e7baeea35ba465fd77d4.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/1ea56177157dacd0f2a4b8a0717e9a82679703e10715e7baeea35ba465fd77d4.json"},{"id":"1eca6a7c9dc3f46709065d854d2d4a3163e19fedbfcf01b15ca32b52a4211000","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/1eca6a7c9dc3f46709065d854d2d4a3163e19fedbfcf01b15ca32b52a4211000.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/1eca6a7c9dc3f46709065d854d2d4a3163e19fedbfcf01b15ca32b52a4211000.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/1eca6a7c9dc3f46709065d854d2d4a3163e19fedbfcf01b15ca32b52a4211000.json"},{"id":"1f07630f1f3e88e9c5ae8a381d51cc9f63efde78f861f0616cb95ad7a272ba0b","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/1f07630f1f3e88e9c5ae8a381d51cc9f63efde78f861f0616cb95ad7a272ba0b.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/1f07630f1f3e88e9c5ae8a381d51cc9f63efde78f861f0616cb95ad7a272ba0b.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/1f07630f1f3e88e9c5ae8a381d51cc9f63efde78f861f0616cb95ad7a272ba0b.json"},{"id":"1f514eb063ab71a2aa0c3200081cf6719afa38e383416c2937ac9046db4b8d12","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/1f514eb063ab71a2aa0c3200081cf6719afa38e383416c2937ac9046db4b8d12.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/1f514eb063ab71a2aa0c3200081cf6719afa38e383416c2937ac9046db4b8d12.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/1f514eb063ab71a2aa0c3200081cf6719afa38e383416c2937ac9046db4b8d12.json"},{"id":"1f70a20b28519a42ac5cffe4d5017ac09243e1c3f0ae471a1e143b845c88dacd","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/1f70a20b28519a42ac5cffe4d5017ac09243e1c3f0ae471a1e143b845c88dacd.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/1f70a20b28519a42ac5cffe4d5017ac09243e1c3f0ae471a1e143b845c88dacd.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/1f70a20b28519a42ac5cffe4d5017ac09243e1c3f0ae471a1e143b845c88dacd.json"},{"id":"1f71f7829978af535ea58bc59bdc259477eadb5f14f4d30639d97f50ef4a8dab","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/1f71f7829978af535ea58bc59bdc259477eadb5f14f4d30639d97f50ef4a8dab.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/1f71f7829978af535ea58bc59bdc259477eadb5f14f4d30639d97f50ef4a8dab.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/1f71f7829978af535ea58bc59bdc259477eadb5f14f4d30639d97f50ef4a8dab.json"},{"id":"200fccdaf7c07dff22c2cd621bb1e3c4f19198a30d5fecae75a906fea948ebda","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/200fccdaf7c07dff22c2cd621bb1e3c4f19198a30d5fecae75a906fea948ebda.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/200fccdaf7c07dff22c2cd621bb1e3c4f19198a30d5fecae75a906fea948ebda.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/200fccdaf7c07dff22c2cd621bb1e3c4f19198a30d5fecae75a906fea948ebda.json"},{"id":"2057ed947ac8f3729aa355532a25aec08d1393fe8e4fbcefa0781ed4ba87d881","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/2057ed947ac8f3729aa355532a25aec08d1393fe8e4fbcefa0781ed4ba87d881.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/2057ed947ac8f3729aa355532a25aec08d1393fe8e4fbcefa0781ed4ba87d881.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/2057ed947ac8f3729aa355532a25aec08d1393fe8e4fbcefa0781ed4ba87d881.json"},{"id":"2070f6e933417c05611428e992dab75bf931c1c9524492437986abef647b80c6","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/2070f6e933417c05611428e992dab75bf931c1c9524492437986abef647b80c6.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/2070f6e933417c05611428e992dab75bf931c1c9524492437986abef647b80c6.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/2070f6e933417c05611428e992dab75bf931c1c9524492437986abef647b80c6.json"},{"id":"207e049bade5654fffe5c165fa86ddbb043b0684cc592112a4dd0b94507774f6","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/207e049bade5654fffe5c165fa86ddbb043b0684cc592112a4dd0b94507774f6.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/207e049bade5654fffe5c165fa86ddbb043b0684cc592112a4dd0b94507774f6.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/207e049bade5654fffe5c165fa86ddbb043b0684cc592112a4dd0b94507774f6.json"},{"id":"208f62cc7ef2414b2f641fb9b4a2931c5043e67c80406f4eb8b082b605ec14d1","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/208f62cc7ef2414b2f641fb9b4a2931c5043e67c80406f4eb8b082b605ec14d1.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/208f62cc7ef2414b2f641fb9b4a2931c5043e67c80406f4eb8b082b605ec14d1.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/208f62cc7ef2414b2f641fb9b4a2931c5043e67c80406f4eb8b082b605ec14d1.json"},{"id":"21663d0a8e335983464c182b0a51ccf345cba8e6d184d0c1cdd12a6b216de035","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/21663d0a8e335983464c182b0a51ccf345cba8e6d184d0c1cdd12a6b216de035.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/21663d0a8e335983464c182b0a51ccf345cba8e6d184d0c1cdd12a6b216de035.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/21663d0a8e335983464c182b0a51ccf345cba8e6d184d0c1cdd12a6b216de035.json"},{"id":"218b3275f4faeece0c1bf078671f51229fa1d1da8345e321059946f9e976fa50","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/218b3275f4faeece0c1bf078671f51229fa1d1da8345e321059946f9e976fa50.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/218b3275f4faeece0c1bf078671f51229fa1d1da8345e321059946f9e976fa50.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/218b3275f4faeece0c1bf078671f51229fa1d1da8345e321059946f9e976fa50.json"},{"id":"21a4f801c8171082517c12aa2369322ad256332f42a9a231234606a7671e0db9","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/21a4f801c8171082517c12aa2369322ad256332f42a9a231234606a7671e0db9.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/21a4f801c8171082517c12aa2369322ad256332f42a9a231234606a7671e0db9.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/21a4f801c8171082517c12aa2369322ad256332f42a9a231234606a7671e0db9.json"},{"id":"220fea437b609d72d3efbf05c2a3bc0d80c66ac7823a2b0c3f5f57916df1859f","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/220fea437b609d72d3efbf05c2a3bc0d80c66ac7823a2b0c3f5f57916df1859f.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/220fea437b609d72d3efbf05c2a3bc0d80c66ac7823a2b0c3f5f57916df1859f.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/220fea437b609d72d3efbf05c2a3bc0d80c66ac7823a2b0c3f5f57916df1859f.json"},{"id":"2217c0145d0e0a12d1ed533f301b74bace59fe6f08572695bf6ff57d3709ad21","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/2217c0145d0e0a12d1ed533f301b74bace59fe6f08572695bf6ff57d3709ad21.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/2217c0145d0e0a12d1ed533f301b74bace59fe6f08572695bf6ff57d3709ad21.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/2217c0145d0e0a12d1ed533f301b74bace59fe6f08572695bf6ff57d3709ad21.json"},{"id":"225d44d7af2f78721e3d5b7003e45f8a1f057a276095cc2b608724e93fcc39a5","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/225d44d7af2f78721e3d5b7003e45f8a1f057a276095cc2b608724e93fcc39a5.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/225d44d7af2f78721e3d5b7003e45f8a1f057a276095cc2b608724e93fcc39a5.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/225d44d7af2f78721e3d5b7003e45f8a1f057a276095cc2b608724e93fcc39a5.json"},{"id":"22b72d0c2df8ad79759175a1e9251310260e82d68b4a2a2f15b1cb581fc25300","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/22b72d0c2df8ad79759175a1e9251310260e82d68b4a2a2f15b1cb581fc25300.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/22b72d0c2df8ad79759175a1e9251310260e82d68b4a2a2f15b1cb581fc25300.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/22b72d0c2df8ad79759175a1e9251310260e82d68b4a2a2f15b1cb581fc25300.json"},{"id":"231b356a440c74da94db05570ef000a3f4da95d027366cc1ecda6c13a440f6e3","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/231b356a440c74da94db05570ef000a3f4da95d027366cc1ecda6c13a440f6e3.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/231b356a440c74da94db05570ef000a3f4da95d027366cc1ecda6c13a440f6e3.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/231b356a440c74da94db05570ef000a3f4da95d027366cc1ecda6c13a440f6e3.json"},{"id":"235db83da9af052cff15681ce42e8e285fec9059f2e83b95304cb49c6cb289da","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/235db83da9af052cff15681ce42e8e285fec9059f2e83b95304cb49c6cb289da.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/235db83da9af052cff15681ce42e8e285fec9059f2e83b95304cb49c6cb289da.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/235db83da9af052cff15681ce42e8e285fec9059f2e83b95304cb49c6cb289da.json"},{"id":"23973fbec4ca00149a120ca80c58c9b4714d2c29fa1605e8fcefc6086f514309","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/23973fbec4ca00149a120ca80c58c9b4714d2c29fa1605e8fcefc6086f514309.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/23973fbec4ca00149a120ca80c58c9b4714d2c29fa1605e8fcefc6086f514309.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/23973fbec4ca00149a120ca80c58c9b4714d2c29fa1605e8fcefc6086f514309.json"},{"id":"23de33f8955855641a97f6ebcc2985a5a4461ea6dcf075ee984d473b3a82832e","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/23de33f8955855641a97f6ebcc2985a5a4461ea6dcf075ee984d473b3a82832e.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/23de33f8955855641a97f6ebcc2985a5a4461ea6dcf075ee984d473b3a82832e.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/23de33f8955855641a97f6ebcc2985a5a4461ea6dcf075ee984d473b3a82832e.json"},{"id":"24426546c24a82dc0d48e0a77bddf1110b06ec5a8a98ee309b38477b58dbb268","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/24426546c24a82dc0d48e0a77bddf1110b06ec5a8a98ee309b38477b58dbb268.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/24426546c24a82dc0d48e0a77bddf1110b06ec5a8a98ee309b38477b58dbb268.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/24426546c24a82dc0d48e0a77bddf1110b06ec5a8a98ee309b38477b58dbb268.json"},{"id":"246b1e82874c6216d868887899311aa0fbfde786899f7572ae46d5455fa19bea","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/246b1e82874c6216d868887899311aa0fbfde786899f7572ae46d5455fa19bea.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/246b1e82874c6216d868887899311aa0fbfde786899f7572ae46d5455fa19bea.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/246b1e82874c6216d868887899311aa0fbfde786899f7572ae46d5455fa19bea.json"},{"id":"2482921f780861749c251f7f3dac4d72b35c88f698d330b889b15a5d9c5f768e","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/2482921f780861749c251f7f3dac4d72b35c88f698d330b889b15a5d9c5f768e.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/2482921f780861749c251f7f3dac4d72b35c88f698d330b889b15a5d9c5f768e.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/2482921f780861749c251f7f3dac4d72b35c88f698d330b889b15a5d9c5f768e.json"},{"id":"249b954176305e33cf45e2803df6d4971fa89c582d12c4db8e2daa6fec2fdaaa","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/249b954176305e33cf45e2803df6d4971fa89c582d12c4db8e2daa6fec2fdaaa.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/249b954176305e33cf45e2803df6d4971fa89c582d12c4db8e2daa6fec2fdaaa.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/249b954176305e33cf45e2803df6d4971fa89c582d12c4db8e2daa6fec2fdaaa.json"},{"id":"255c2d96a9eca9d3a1377ba6927531ef17055918fded2a7c70bc47afa402941a","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/255c2d96a9eca9d3a1377ba6927531ef17055918fded2a7c70bc47afa402941a.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/255c2d96a9eca9d3a1377ba6927531ef17055918fded2a7c70bc47afa402941a.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/255c2d96a9eca9d3a1377ba6927531ef17055918fded2a7c70bc47afa402941a.json"},{"id":"2585c3a46f177c654c091674712cc2cd3955f1ae7e96f704f4b1a406696382fc","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/2585c3a46f177c654c091674712cc2cd3955f1ae7e96f704f4b1a406696382fc.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/2585c3a46f177c654c091674712cc2cd3955f1ae7e96f704f4b1a406696382fc.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/2585c3a46f177c654c091674712cc2cd3955f1ae7e96f704f4b1a406696382fc.json"},{"id":"258861184f93757ff87d30ebb06ee9d8b49236a8b2983da06d89cdbd4e770508","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/258861184f93757ff87d30ebb06ee9d8b49236a8b2983da06d89cdbd4e770508.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/258861184f93757ff87d30ebb06ee9d8b49236a8b2983da06d89cdbd4e770508.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/258861184f93757ff87d30ebb06ee9d8b49236a8b2983da06d89cdbd4e770508.json"},{"id":"25e56b28da3a6f10dcc59cc73517eb7430ee57cafc7c5ee8b6fdd33ceed49a3f","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/25e56b28da3a6f10dcc59cc73517eb7430ee57cafc7c5ee8b6fdd33ceed49a3f.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/25e56b28da3a6f10dcc59cc73517eb7430ee57cafc7c5ee8b6fdd33ceed49a3f.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/25e56b28da3a6f10dcc59cc73517eb7430ee57cafc7c5ee8b6fdd33ceed49a3f.json"},{"id":"26000ef4986cbc11316f7aaf451ab06cb085114cc2d257d371f8f19b82d46b37","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/26000ef4986cbc11316f7aaf451ab06cb085114cc2d257d371f8f19b82d46b37.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/26000ef4986cbc11316f7aaf451ab06cb085114cc2d257d371f8f19b82d46b37.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/26000ef4986cbc11316f7aaf451ab06cb085114cc2d257d371f8f19b82d46b37.json"},{"id":"2642606e4af633977df2590d91873e00e5867fe0bd60c887c943dcca4d41526b","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/2642606e4af633977df2590d91873e00e5867fe0bd60c887c943dcca4d41526b.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/2642606e4af633977df2590d91873e00e5867fe0bd60c887c943dcca4d41526b.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/2642606e4af633977df2590d91873e00e5867fe0bd60c887c943dcca4d41526b.json"},{"id":"26496277890e91b4adf14b039945c542aecbea3251135f4dce9ff4c7fa9fb301","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/26496277890e91b4adf14b039945c542aecbea3251135f4dce9ff4c7fa9fb301.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/26496277890e91b4adf14b039945c542aecbea3251135f4dce9ff4c7fa9fb301.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/26496277890e91b4adf14b039945c542aecbea3251135f4dce9ff4c7fa9fb301.json"},{"id":"2666c4314fa9c2feccde48f6edec21e84072d8048d5d10b7c6c1f19eb4c2c757","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/2666c4314fa9c2feccde48f6edec21e84072d8048d5d10b7c6c1f19eb4c2c757.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/2666c4314fa9c2feccde48f6edec21e84072d8048d5d10b7c6c1f19eb4c2c757.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/2666c4314fa9c2feccde48f6edec21e84072d8048d5d10b7c6c1f19eb4c2c757.json"},{"id":"26dad8f526083b9e2d22c1fdcc018fa20691c3da0dac37363d654cf035a0df27","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/26dad8f526083b9e2d22c1fdcc018fa20691c3da0dac37363d654cf035a0df27.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/26dad8f526083b9e2d22c1fdcc018fa20691c3da0dac37363d654cf035a0df27.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/26dad8f526083b9e2d22c1fdcc018fa20691c3da0dac37363d654cf035a0df27.json"},{"id":"26e29e6ea5418e322f828f1d483aef68e6c8fbe87bef9fc2749ebad347eded5f","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/26e29e6ea5418e322f828f1d483aef68e6c8fbe87bef9fc2749ebad347eded5f.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/26e29e6ea5418e322f828f1d483aef68e6c8fbe87bef9fc2749ebad347eded5f.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/26e29e6ea5418e322f828f1d483aef68e6c8fbe87bef9fc2749ebad347eded5f.json"},{"id":"2727a9708f594892988ef67500f0be70e7e49814feb739be77fa704e67f1e187","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/2727a9708f594892988ef67500f0be70e7e49814feb739be77fa704e67f1e187.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/2727a9708f594892988ef67500f0be70e7e49814feb739be77fa704e67f1e187.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/2727a9708f594892988ef67500f0be70e7e49814feb739be77fa704e67f1e187.json"},{"id":"2753ab9f148ccb03acd6ebdee019c7f1943b1800e630b0383c81db3c2a8e7d71","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/2753ab9f148ccb03acd6ebdee019c7f1943b1800e630b0383c81db3c2a8e7d71.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/2753ab9f148ccb03acd6ebdee019c7f1943b1800e630b0383c81db3c2a8e7d71.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/2753ab9f148ccb03acd6ebdee019c7f1943b1800e630b0383c81db3c2a8e7d71.json"},{"id":"27567f693dd13966815e72a59bd9b61ff741f22c95398782dbe2c292f6df861f","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/27567f693dd13966815e72a59bd9b61ff741f22c95398782dbe2c292f6df861f.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/27567f693dd13966815e72a59bd9b61ff741f22c95398782dbe2c292f6df861f.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/27567f693dd13966815e72a59bd9b61ff741f22c95398782dbe2c292f6df861f.json"},{"id":"28252625b087c99562553bdfb3a98e335bc6dca5f54761824398de276c9ec6b7","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/28252625b087c99562553bdfb3a98e335bc6dca5f54761824398de276c9ec6b7.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/28252625b087c99562553bdfb3a98e335bc6dca5f54761824398de276c9ec6b7.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/28252625b087c99562553bdfb3a98e335bc6dca5f54761824398de276c9ec6b7.json"},{"id":"282c10c297c66c92ce30865e0ea002fe7739aae3b1facfd499ba7ec25a346bdb","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/282c10c297c66c92ce30865e0ea002fe7739aae3b1facfd499ba7ec25a346bdb.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/282c10c297c66c92ce30865e0ea002fe7739aae3b1facfd499ba7ec25a346bdb.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/282c10c297c66c92ce30865e0ea002fe7739aae3b1facfd499ba7ec25a346bdb.json"},{"id":"284808800c789cc8754f565d44a9847489e345235c851583964cdde396fe7db7","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/284808800c789cc8754f565d44a9847489e345235c851583964cdde396fe7db7.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/284808800c789cc8754f565d44a9847489e345235c851583964cdde396fe7db7.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/284808800c789cc8754f565d44a9847489e345235c851583964cdde396fe7db7.json"},{"id":"2886e4e9a32a9646e99889e705b003c31364dbfb491db527534c22bace3c4e90","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/2886e4e9a32a9646e99889e705b003c31364dbfb491db527534c22bace3c4e90.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/2886e4e9a32a9646e99889e705b003c31364dbfb491db527534c22bace3c4e90.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/2886e4e9a32a9646e99889e705b003c31364dbfb491db527534c22bace3c4e90.json"},{"id":"28c63d105ae63fe564c452197c19c3d9bdb1930dd298af92bc013a0f739a79d4","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/28c63d105ae63fe564c452197c19c3d9bdb1930dd298af92bc013a0f739a79d4.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/28c63d105ae63fe564c452197c19c3d9bdb1930dd298af92bc013a0f739a79d4.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/28c63d105ae63fe564c452197c19c3d9bdb1930dd298af92bc013a0f739a79d4.json"},{"id":"28dd536ad57eb0dcb2b19e7e98f487064ef45a1c77984cc4cfc5397acef86257","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/28dd536ad57eb0dcb2b19e7e98f487064ef45a1c77984cc4cfc5397acef86257.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/28dd536ad57eb0dcb2b19e7e98f487064ef45a1c77984cc4cfc5397acef86257.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/28dd536ad57eb0dcb2b19e7e98f487064ef45a1c77984cc4cfc5397acef86257.json"},{"id":"29625798aa5f9f7468c47b2771666f55f3b5c43c882f52a7295a9b8b18ad3a44","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/29625798aa5f9f7468c47b2771666f55f3b5c43c882f52a7295a9b8b18ad3a44.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/29625798aa5f9f7468c47b2771666f55f3b5c43c882f52a7295a9b8b18ad3a44.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/29625798aa5f9f7468c47b2771666f55f3b5c43c882f52a7295a9b8b18ad3a44.json"},{"id":"2a0edbbe5d944c9b712cfb64891bb59e15a370c6ce82ed4b11cc3eba62cf9f6a","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/2a0edbbe5d944c9b712cfb64891bb59e15a370c6ce82ed4b11cc3eba62cf9f6a.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/2a0edbbe5d944c9b712cfb64891bb59e15a370c6ce82ed4b11cc3eba62cf9f6a.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/2a0edbbe5d944c9b712cfb64891bb59e15a370c6ce82ed4b11cc3eba62cf9f6a.json"},{"id":"2a2e75080622c93a9fe1780c066642f734c5833b069040bf94960ac79999b914","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/2a2e75080622c93a9fe1780c066642f734c5833b069040bf94960ac79999b914.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/2a2e75080622c93a9fe1780c066642f734c5833b069040bf94960ac79999b914.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/2a2e75080622c93a9fe1780c066642f734c5833b069040bf94960ac79999b914.json"},{"id":"2a9b781b0603133286028ba35f9512a927e24c9ed646b1f0b34f1744d8bf4d84","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/2a9b781b0603133286028ba35f9512a927e24c9ed646b1f0b34f1744d8bf4d84.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/2a9b781b0603133286028ba35f9512a927e24c9ed646b1f0b34f1744d8bf4d84.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/2a9b781b0603133286028ba35f9512a927e24c9ed646b1f0b34f1744d8bf4d84.json"},{"id":"2a9c13af249679d032324250e28758e0ccb233a23aa98783d83692ec9fb5c875","videoPath":"curated/wisa-80k-scene-causal-seeds/v3/videos/2a9c13af249679d032324250e28758e0ccb233a23aa98783d83692ec9fb5c875.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/wisa-80k-scene-causal-seeds/v3/videos/2a9c13af249679d032324250e28758e0ccb233a23aa98783d83692ec9fb5c875.mp4","initialFrameUrl":"","sourceDataset":"WISA-80K","suggestedTrack":"","scene":"","spatialAbility":"","perspective":"","caption":"","annotationPath":"curated/wisa-80k-scene-causal-seeds/v3/annotations/2a9c13af249679d032324250e28758e0ccb233a23aa98783d83692ec9fb5c875.json"},{"id":"wisa_005247195cbd2c3ed8f38f567a76b7ae0458074013a29be03002c48c95381074","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/wisa_005247195cbd2c3ed8f38f567a76b7ae0458074013a29be03002c48c95381074.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/wisa_005247195cbd2c3ed8f38f567a76b7ae0458074013a29be03002c48c95381074.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/wisa_005247195cbd2c3ed8f38f567a76b7ae0458074013a29be03002c48c95381074.jpg","sourceDataset":"WISA-80K","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video showcases a mesmerizing close-up of a vibrant, swirling liquid, likely a soap or oil mixture, creating a kaleidoscopic effect. The colors transition smoothly from deep blue at the top to bright green at the bottom, with a vivid purple and red band in the middle, forming concentric circles. Small bubbles of varying sizes float gently throughout the liquid, reflecting light and adding a dynamic element to the scene. As the video progresses, these bubbles move slightly, altering their positions and sizes, enhancing the fluidity and depth of the visual display. The overall effect is both calming and captivating, drawing the viewer into the intricate dance of colors and light within the liquid's surface.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/wisa_005247195cbd2c3ed8f38f567a76b7ae0458074013a29be03002c48c95381074.json"},{"id":"wisa_046254046f781cb47a759b4e9c9e5e58a7c89662e7e1b32fce43ade4fad55859","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/wisa_046254046f781cb47a759b4e9c9e5e58a7c89662e7e1b32fce43ade4fad55859.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/wisa_046254046f781cb47a759b4e9c9e5e58a7c89662e7e1b32fce43ade4fad55859.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/wisa_046254046f781cb47a759b4e9c9e5e58a7c89662e7e1b32fce43ade4fad55859.jpg","sourceDataset":"WISA-80K","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures an aerial view of a coastal cityscape, showcasing a long stretch of sandy beach bordered by the ocean on one side and a dense cluster of modern high-rise buildings on the other. The beach is populated with a few individuals scattered along its length, some walking and others standing near the water's edge. The waves gently lap against the shore, creating white foam as they break. The sky above is overcast, casting a soft, diffused light over the scene. The camera slowly pans across the beach, providing a continuous view of the shoreline and the urban skyline. As the camera moves, it reveals more of the beachgoers and the architectural details of the buildings, which vary in height and design, reflecting a mix of contemporary and possibly older structures. The overall atmosphere is serene and picturesque, highlighting the contrast between the natural beauty of the beach and the urban environment.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/wisa_046254046f781cb47a759b4e9c9e5e58a7c89662e7e1b32fce43ade4fad55859.json"},{"id":"wisa_06e6238ac60d90b11dcf350dc2beba32d526ff9f3e5ce22661c4cbd7cda5533e","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_06e6238ac60d90b11dcf350dc2beba32d526ff9f3e5ce22661c4cbd7cda5533e.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_06e6238ac60d90b11dcf350dc2beba32d526ff9f3e5ce22661c4cbd7cda5533e.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/wisa_06e6238ac60d90b11dcf350dc2beba32d526ff9f3e5ce22661c4cbd7cda5533e.jpg","sourceDataset":"WISA-80K","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a close-up view of a person pouring steamed milk into a cup of coffee. The individual is wearing a gray sweatshirt with bold white text on it. They hold the cup steady with one hand while pouring the milk from a metallic pitcher with a pink handle. As the milk flows, it creates a swirling pattern on the surface of the coffee, forming a heart shape. The background reveals a kitchen setting with a wooden cabinet and a yellow cloth hanging nearby. The camera remains stationary throughout the sequence, focusing on the pouring action and the evolving design in the coffee. The scene emphasizes the artistry involved in creating latte art, highlighting the smooth flow of the milk and the intricate pattern it forms.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/wisa_06e6238ac60d90b11dcf350dc2beba32d526ff9f3e5ce22661c4cbd7cda5533e.json"},{"id":"wisa_1554225a08d7ad0c43f64ca5f55c8ff89edf5fc1b64f355a4b6d4ff00afed108","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_1554225a08d7ad0c43f64ca5f55c8ff89edf5fc1b64f355a4b6d4ff00afed108.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_1554225a08d7ad0c43f64ca5f55c8ff89edf5fc1b64f355a4b6d4ff00afed108.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/wisa_1554225a08d7ad0c43f64ca5f55c8ff89edf5fc1b64f355a4b6d4ff00afed108.jpg","sourceDataset":"WISA-80K","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a serene coastal scene under a dynamic sky. The ocean waves gently roll towards the shore, creating a rhythmic pattern of white foam against the darker water. The sky above is filled with a mix of dark clouds and patches of lighter, brighter areas, suggesting an impending storm or a break in the weather. As the video progresses, the clouds shift slightly, revealing more of the sunlit portions, which cast a soft glow on the water's surface. The overall atmosphere is tranquil yet dramatic, with the natural elements of the sea and sky dominating the visual narrative. There are no visible animals or human characters in the frame, allowing the viewer to fully immerse themselves in the natural beauty and the subtle changes in the environment.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/wisa_1554225a08d7ad0c43f64ca5f55c8ff89edf5fc1b64f355a4b6d4ff00afed108.json"},{"id":"wisa_1da00c8fcb3605cca96429fc900626679eaa2b1281f20db2bc0e657d21a5a592","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_1da00c8fcb3605cca96429fc900626679eaa2b1281f20db2bc0e657d21a5a592.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_1da00c8fcb3605cca96429fc900626679eaa2b1281f20db2bc0e657d21a5a592.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/wisa_1da00c8fcb3605cca96429fc900626679eaa2b1281f20db2bc0e657d21a5a592.jpg","sourceDataset":"WISA-80K","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a close-up view of a melting ice cube resting on a wooden surface. The ice cube is irregularly shaped, with a rough, textured surface that appears to be covered in small air bubbles, indicating it might have been freshly formed or recently exposed to air. As the video progresses, the ice cube gradually begins to melt, with water droplets forming at its base and spreading across the wooden surface. The liquid water reflects light, creating a shimmering effect. The background remains consistently dark throughout the sequence, which emphasizes the contrast between the white ice and the warm tones of the wood. There are no visible characters or animals in the scene, and the camera maintains a steady, fixed position, focusing solely on the melting process of the ice cube. The overall atmosphere is one of quiet observation, capturing the simple yet fascinating transformation of solid ice into liquid water.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/wisa_1da00c8fcb3605cca96429fc900626679eaa2b1281f20db2bc0e657d21a5a592.json"},{"id":"wisa_2057ed947ac8f3729aa355532a25aec08d1393fe8e4fbcefa0781ed4ba87d881","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_2057ed947ac8f3729aa355532a25aec08d1393fe8e4fbcefa0781ed4ba87d881.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_2057ed947ac8f3729aa355532a25aec08d1393fe8e4fbcefa0781ed4ba87d881.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/wisa_2057ed947ac8f3729aa355532a25aec08d1393fe8e4fbcefa0781ed4ba87d881.jpg","sourceDataset":"WISA-80K","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a dynamic scene where several sausages are being tossed into a wooden tray filled with fresh green lettuce leaves. The background features a rustic setting with a dark, textured backdrop that enhances the vibrant colors of the food items. Surrounding the tray are various vegetables, including ripe red tomatoes and a whole red bell pepper, adding to the colorful composition. A bottle of olive oil is also visible in the background, suggesting a culinary context.\n\nInitially, the sausages are seen mid-air, their bright orange color contrasting sharply against the dark background. As they fall into the tray, they land on top of the lettuce, causing some leaves to shift and scatter slightly. The sausages bounce and roll around the tray, creating a lively and energetic visual effect. The camera remains stationary throughout the sequence, focusing on the tray and its contents, allowing viewers to observe the detailed textures and movements of the falling sausages and the interaction with the lettuce. The overall atmosphere is one of freshness and","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/wisa_2057ed947ac8f3729aa355532a25aec08d1393fe8e4fbcefa0781ed4ba87d881.json"},{"id":"wisa_255c2d96a9eca9d3a1377ba6927531ef17055918fded2a7c70bc47afa402941a","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_255c2d96a9eca9d3a1377ba6927531ef17055918fded2a7c70bc47afa402941a.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_255c2d96a9eca9d3a1377ba6927531ef17055918fded2a7c70bc47afa402941a.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/wisa_255c2d96a9eca9d3a1377ba6927531ef17055918fded2a7c70bc47afa402941a.jpg","sourceDataset":"WISA-80K","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video begins with a close-up shot of a wooden spoon placed against a black background. A stream of honey is being poured into the bowl of the spoon from above. As the honey flows, it creates a smooth, golden cascade that fills the spoon's bowl. The honey's surface tension causes it to form small, delicate droplets at the tip of the stream. These droplets glisten under the light, adding a shimmering effect to the scene. The honey gradually fills the spoon, creating a rich, amber pool that contrasts beautifully with the dark background. The camera remains stationary throughout, focusing on the spoon and the honey, capturing the fluid motion and the gradual filling of the spoon's bowl. The video ends with the spoon nearly full of honey, showcasing the smooth texture and the way the liquid clings to the wood.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/wisa_255c2d96a9eca9d3a1377ba6927531ef17055918fded2a7c70bc47afa402941a.json"},{"id":"wisa_2b4ae24d27dbc0e04dca9eaaebf3df06ee905a00798587c51c41d403a320708f","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/wisa_2b4ae24d27dbc0e04dca9eaaebf3df06ee905a00798587c51c41d403a320708f.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/wisa_2b4ae24d27dbc0e04dca9eaaebf3df06ee905a00798587c51c41d403a320708f.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/wisa_2b4ae24d27dbc0e04dca9eaaebf3df06ee905a00798587c51c41d403a320708f.jpg","sourceDataset":"WISA-80K","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures an exhilarating whitewater kayaking adventure through a narrow, rocky canyon. The scene opens with two kayakers navigating a turbulent river, surrounded by towering, light-colored rock formations. The kayaker in the foreground is piloting a vibrant pink kayak, while the second kayaker, wearing a red jacket and helmet, maneuvers a yellow kayak. Both paddlers are actively steering their boats through the frothy, white water, which churns around them. The camera, likely mounted on one of the kayaks, provides a first-person perspective, immersing the viewer in the action.\n\nAs the kayakers progress, they encounter a series of rapids and small cascades, each adding to the intensity of the journey. The water's surface is a dynamic mix of white foam and clear patches, reflecting the sunlight and emphasizing the speed and power of the current. The rocky walls of the canyon rise steeply on either side, creating a dramatic and enclosed environment that enhances the sense of adventure","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/wisa_2b4ae24d27dbc0e04dca9eaaebf3df06ee905a00798587c51c41d403a320708f.json"},{"id":"wisa_2b83f7b7eb5195f2db0940fe199138a811e9297c511fbe0cba473b4e31e353f5","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_2b83f7b7eb5195f2db0940fe199138a811e9297c511fbe0cba473b4e31e353f5.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_2b83f7b7eb5195f2db0940fe199138a811e9297c511fbe0cba473b4e31e353f5.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/wisa_2b83f7b7eb5195f2db0940fe199138a811e9297c511fbe0cba473b4e31e353f5.jpg","sourceDataset":"WISA-80K","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a close-up view of an espresso machine in action. The focus is on the machine's spout, which is dispensing a rich, dark brown stream of espresso into a shiny, metallic cup below. The cup is positioned directly beneath the spout, ensuring a smooth pour without spillage. The background is blurred, drawing attention to the machine and the cup, but hints at a warm, possibly indoor setting with soft lighting. The machine itself has a sleek, modern design with a black handle and silver body, reflecting light and adding to the visual appeal. As the video progresses, the espresso continues to flow steadily, filling the cup gradually. The scene emphasizes the precision and care involved in making a perfect espresso shot, highlighting the machine's functionality and the appealing aesthetic of the process.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/wisa_2b83f7b7eb5195f2db0940fe199138a811e9297c511fbe0cba473b4e31e353f5.json"},{"id":"wisa_3372f669cf0954272173572df7fd008d01552bb330d8f9bef28e9d2909e408c0","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_3372f669cf0954272173572df7fd008d01552bb330d8f9bef28e9d2909e408c0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_3372f669cf0954272173572df7fd008d01552bb330d8f9bef28e9d2909e408c0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/wisa_3372f669cf0954272173572df7fd008d01552bb330d8f9bef28e9d2909e408c0.jpg","sourceDataset":"WISA-80K","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a serene moment in what appears to be a cozy kitchen or café setting. A person is seen pouring coffee from a sleek, stainless steel French press into a clear glass mug. The individual's hands are prominently featured, with one hand holding the lid of the French press steady while the other steadies the mug below. The background reveals a rustic wooden shelf filled with various bottles, likely containing oils or vinegars, adding a warm, homey feel to the scene. The lighting is soft and natural, suggesting the video was shot during the day, possibly near a window. The camera remains stationary throughout the sequence, focusing closely on the action of pouring the coffee, emphasizing the smooth flow of the dark liquid into the mug. The overall atmosphere is calm and inviting, highlighting the simple pleasure of enjoying a freshly brewed cup of coffee.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/wisa_3372f669cf0954272173572df7fd008d01552bb330d8f9bef28e9d2909e408c0.json"},{"id":"wisa_33ea8e443d63888a609d1060b81a0f9025c6ba3675e2007ce0a19ad6e41e63fd","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_33ea8e443d63888a609d1060b81a0f9025c6ba3675e2007ce0a19ad6e41e63fd.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_33ea8e443d63888a609d1060b81a0f9025c6ba3675e2007ce0a19ad6e41e63fd.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/wisa_33ea8e443d63888a609d1060b81a0f9025c6ba3675e2007ce0a19ad6e41e63fd.jpg","sourceDataset":"WISA-80K","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a dynamic scene of a river flowing vigorously through a rocky landscape. The river, with its white, frothy rapids, is the central focus, showcasing the powerful movement of water as it cascades over rocks and boulders. The surrounding environment features steep, rocky cliffs covered with patches of green vegetation, adding a natural frame to the scene. A large bridge spans across the river in the background, partially obscured by the lush greenery on the far side. The sky above is partly cloudy, allowing for a mix of sunlight and shadows that enhance the textures of the rocks and foliage. Throughout the video, there are no visible animals or characters, and the camera remains stationary, providing a steady view of the river's flow and the serene yet powerful interaction between the water and the rugged terrain. The overall atmosphere is one of natural beauty and tranquility, with the continuous motion of the river creating a sense of life and energy.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/wisa_33ea8e443d63888a609d1060b81a0f9025c6ba3675e2007ce0a19ad6e41e63fd.json"},{"id":"wisa_38fcb53ea0591231ddcdc2b0673a8479a368aa71b0ef20ddcd5966cd1cf59e49","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_38fcb53ea0591231ddcdc2b0673a8479a368aa71b0ef20ddcd5966cd1cf59e49.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_38fcb53ea0591231ddcdc2b0673a8479a368aa71b0ef20ddcd5966cd1cf59e49.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/wisa_38fcb53ea0591231ddcdc2b0673a8479a368aa71b0ef20ddcd5966cd1cf59e49.jpg","sourceDataset":"WISA-80K","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a close-up view of a burning object placed on a metal grate, set against a dark, textured background that appears to be a stone wall. The object is a rectangular block, partially covered with what looks like blackened, shredded material, possibly charred paper or fabric. Flames lick at the edges of the block, with bright orange and yellow hues dominating the scene. As the video progresses, the flames grow more intense, consuming the shredded material and causing it to curl and fall away from the block. The smoke rises steadily, adding a dynamic element to the scene. The metal grate beneath the block shows signs of heat, with some areas appearing slightly melted or discolored. The overall atmosphere is one of controlled destruction, with the focus remaining tightly on the burning object throughout the sequence.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/wisa_38fcb53ea0591231ddcdc2b0673a8479a368aa71b0ef20ddcd5966cd1cf59e49.json"},{"id":"wisa_3bf3e701ef68d1539e8499ecfaea338791ddc0c316bad4e710898f25cb8ac4fb","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/wisa_3bf3e701ef68d1539e8499ecfaea338791ddc0c316bad4e710898f25cb8ac4fb.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/wisa_3bf3e701ef68d1539e8499ecfaea338791ddc0c316bad4e710898f25cb8ac4fb.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/wisa_3bf3e701ef68d1539e8499ecfaea338791ddc0c316bad4e710898f25cb8ac4fb.jpg","sourceDataset":"WISA-80K","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video begins with a close-up shot of a Pepsi Max can placed on a wooden surface, alongside a black cylindrical object. A large hydraulic press descends onto the can, applying immense pressure. As the press compresses the can, it bursts open, releasing a spray of liquid and debris. The liquid splashes outward, creating a dynamic burst of motion. The press continues to descend, flattening the can completely, leaving behind a flattened can and scattered remnants of the drink. The background features a green wall with yellow warning signs, adding an industrial feel to the scene. The camera remains stationary throughout, focusing on capturing the dramatic transformation of the can under the force of the press.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/wisa_3bf3e701ef68d1539e8499ecfaea338791ddc0c316bad4e710898f25cb8ac4fb.json"},{"id":"wisa_4a02871b01c155663c3c4e2f72ddf921fa4dcfef181f4008f9a1e89439f9f392","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_4a02871b01c155663c3c4e2f72ddf921fa4dcfef181f4008f9a1e89439f9f392.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_4a02871b01c155663c3c4e2f72ddf921fa4dcfef181f4008f9a1e89439f9f392.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/wisa_4a02871b01c155663c3c4e2f72ddf921fa4dcfef181f4008f9a1e89439f9f392.jpg","sourceDataset":"WISA-80K","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a close-up view of a large, transparent bubble resting on a weathered wooden post. The bubble is positioned slightly off-center, leaning against the post, which has a rough texture and shows signs of wear. The background reveals a snowy landscape, with snow covering the ground and faint outlines of trees and possibly a fence line visible in the distance. The lighting suggests it is either early morning or late afternoon, casting a soft glow over the scene.\n\nAs the video progresses, the bubble begins to freeze, starting from its base and gradually spreading upwards. The ice formation becomes more pronounced, creating a textured surface that contrasts with the smooth, liquid-like appearance of the bubble at the beginning. The process of freezing is gradual, with the ice layer thickening and becoming more defined. By the end of the sequence, the bubble is mostly frozen, with only a small portion remaining unfrozen at the top, reflecting the surrounding environment. The overall atmosphere remains serene and still throughout the video, emphasizing the","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/wisa_4a02871b01c155663c3c4e2f72ddf921fa4dcfef181f4008f9a1e89439f9f392.json"},{"id":"wisa_55b51b9d6e4de5f13a0464eda02e6cf55383cc90442e87886d4ee32d91fd6aa0","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/wisa_55b51b9d6e4de5f13a0464eda02e6cf55383cc90442e87886d4ee32d91fd6aa0.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/wisa_55b51b9d6e4de5f13a0464eda02e6cf55383cc90442e87886d4ee32d91fd6aa0.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/wisa_55b51b9d6e4de5f13a0464eda02e6cf55383cc90442e87886d4ee32d91fd6aa0.jpg","sourceDataset":"WISA-80K","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a mechanical process where a cylindrical metal object, likely part of a press or hydraulic machine, is positioned above a stack of white rectangular blocks. The background features a green wall with two yellow warning signs displaying red lightning bolts, indicating potential electrical hazards. As the video progresses, the metal cylinder descends onto the stack of blocks, applying pressure. The blocks begin to compress and deform under the force, with visible cracks forming on their surfaces. The deformation intensifies, causing the blocks to split apart and collapse into a more compact form. The scene is set in an industrial environment, evident from the metallic surface of the table and the utilitarian design of the machinery. The camera remains stationary throughout, focusing on the interaction between the press and the blocks, highlighting the transformation of the material under pressure.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/wisa_55b51b9d6e4de5f13a0464eda02e6cf55383cc90442e87886d4ee32d91fd6aa0.json"},{"id":"wisa_56d68f4c5a8b9861948fe6879ce2699630eff35513655d9c10bd33f646835263","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_56d68f4c5a8b9861948fe6879ce2699630eff35513655d9c10bd33f646835263.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_56d68f4c5a8b9861948fe6879ce2699630eff35513655d9c10bd33f646835263.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/wisa_56d68f4c5a8b9861948fe6879ce2699630eff35513655d9c10bd33f646835263.jpg","sourceDataset":"WISA-80K","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a serene beach scene under a vast sky filled with clouds. The ocean waves gently crash onto the shore, creating white foam that spreads across the sandy beach. The water is a vibrant turquoise color, reflecting the sunlight and adding to the tranquil atmosphere. The sky above is a mix of light and dark clouds, with patches of blue peeking through, suggesting a partly cloudy day. The horizon line is clearly visible, separating the sea from the sky. There are no animals or people present in the scene, emphasizing the peacefulness of the environment. The camera remains stationary throughout the video, allowing viewers to fully absorb the beauty of the natural setting. The waves continue to roll in rhythmically, and the overall mood of the video is calm and soothing.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/wisa_56d68f4c5a8b9861948fe6879ce2699630eff35513655d9c10bd33f646835263.json"},{"id":"wisa_62e47da93d56f4e1ee778b7d04d1168dadc4c691864bc4e19864bf68582287c5","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_62e47da93d56f4e1ee778b7d04d1168dadc4c691864bc4e19864bf68582287c5.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_62e47da93d56f4e1ee778b7d04d1168dadc4c691864bc4e19864bf68582287c5.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/wisa_62e47da93d56f4e1ee778b7d04d1168dadc4c691864bc4e19864bf68582287c5.jpg","sourceDataset":"WISA-80K","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a dynamic scene of a river flowing rapidly through a rocky landscape. The river's water is a vibrant blue-green, churning and frothing as it rushes over and around large rocks and boulders. The riverbanks are lined with steep cliffs, covered in patches of green vegetation, suggesting a mix of grasses and shrubs. A prominent feature in the background is a steel bridge spanning across the river, its structure contrasting against the natural surroundings. The sky above is partly cloudy, allowing for patches of sunlight to filter through, casting a bright light on the scene. The overall atmosphere is one of natural beauty and power, with the river's movement being the central focus. There are no visible animals or characters in the video, and the camera remains stationary throughout, providing a steady view of the river and its surroundings.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/wisa_62e47da93d56f4e1ee778b7d04d1168dadc4c691864bc4e19864bf68582287c5.json"},{"id":"wisa_6331d657f97b3f43557d949771eb24d585e298e6387ef648eb5a28f20c48cea2","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/wisa_6331d657f97b3f43557d949771eb24d585e298e6387ef648eb5a28f20c48cea2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/wisa_6331d657f97b3f43557d949771eb24d585e298e6387ef648eb5a28f20c48cea2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/wisa_6331d657f97b3f43557d949771eb24d585e298e6387ef648eb5a28f20c48cea2.jpg","sourceDataset":"WISA-80K","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a dramatic scene where a hydraulic press is being used to crush four test tubes filled with colored liquids. The test tubes, each containing a different color—red, blue, black, and clear—are arranged in a metal frame. As the press descends, it exerts immense pressure on the tubes, causing them to shatter explosively. The red liquid spills out first, followed by the blue and black liquids, which mix and splash around the base of the press. The clear liquid remains mostly intact but eventually succumbs to the pressure, spilling out as well. The cork stoppers are also ejected from their positions, adding to the chaotic scene. The background features a green wall with a yellow warning sign, emphasizing the controlled yet dangerous nature of the experiment. The camera remains stationary throughout, focusing on the crushing process, capturing the vivid colors and the dynamic motion of the liquids and glass fragments.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/wisa_6331d657f97b3f43557d949771eb24d585e298e6387ef648eb5a28f20c48cea2.json"},{"id":"wisa_6743e356c96d7eb73f1d04f187f7bbf075f97da0196e31dc045d34a7a12a6619","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/wisa_6743e356c96d7eb73f1d04f187f7bbf075f97da0196e31dc045d34a7a12a6619.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/wisa_6743e356c96d7eb73f1d04f187f7bbf075f97da0196e31dc045d34a7a12a6619.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/wisa_6743e356c96d7eb73f1d04f187f7bbf075f97da0196e31dc045d34a7a12a6619.jpg","sourceDataset":"WISA-80K","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a group of individuals experiencing zero gravity inside an aircraft. They are dressed in dark blue jumpsuits adorned with patches, suggesting they are part of a specialized program or experiment. The setting is the interior of an aircraft, characterized by its curved walls and ceiling, typical of a plane designed for zero-gravity flights. The lighting is bright, illuminating the scene clearly.\n\nInitially, the group is seen lying on their backs on the floor of the aircraft, appearing to float due to the lack of gravity. Their expressions range from excitement to concentration, indicating they are engaged in the experience. As the video progresses, some individuals begin to move, standing up and interacting with each other. One person is seen holding a small object, possibly a camera or a device related to the experience. The camera movement is dynamic, capturing the fluid motion of the participants as they adjust to the weightless environment. The camera pans around the group, showing different angles and perspectives of their activities and reactions. The overall","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/wisa_6743e356c96d7eb73f1d04f187f7bbf075f97da0196e31dc045d34a7a12a6619.json"},{"id":"wisa_705dba3db4082059a668a4ca9184cc274508303c5eb51565c2402062da2cf85a","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/wisa_705dba3db4082059a668a4ca9184cc274508303c5eb51565c2402062da2cf85a.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/wisa_705dba3db4082059a668a4ca9184cc274508303c5eb51565c2402062da2cf85a.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/wisa_705dba3db4082059a668a4ca9184cc274508303c5eb51565c2402062da2cf85a.jpg","sourceDataset":"WISA-80K","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a close-up view of a mechanical press in action, set against a backdrop of a green industrial door with yellow warning signs. The press, characterized by its metallic components and a prominent yellow and black striped cylinder at the top, is positioned over a cylindrical metal base. Initially, the press descends onto a small mound of soil or sand placed on the metal base. As it compresses, the soil begins to compact and flatten under the pressure. The camera remains stationary throughout, focusing on the interaction between the press and the soil. The lighting is consistent, highlighting the textures and details of both the machinery and the material being compressed. The sequence progresses smoothly, showing the gradual transformation of the soil's shape and consistency as the press exerts force.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/wisa_705dba3db4082059a668a4ca9184cc274508303c5eb51565c2402062da2cf85a.json"},{"id":"wisa_70c57fb1238a799f39de2f499082de154275270663dd3d97c85cc06292d7fde8","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/wisa_70c57fb1238a799f39de2f499082de154275270663dd3d97c85cc06292d7fde8.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/wisa_70c57fb1238a799f39de2f499082de154275270663dd3d97c85cc06292d7fde8.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/wisa_70c57fb1238a799f39de2f499082de154275270663dd3d97c85cc06292d7fde8.jpg","sourceDataset":"WISA-80K","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a mechanical test setup where a hydraulic press is being used to crush a red metal hook attached to a black and yellow striped cylindrical base. The press, a large metallic cylinder, descends slowly onto the hook, applying increasing pressure. As the press descends, the hook bends and eventually breaks under the force, scattering small pieces of metal around the base. The camera remains stationary throughout the sequence, focusing on the interaction between the press and the hook. The background includes a wall with a striped pattern and some electrical outlets, indicating an industrial or laboratory setting. The lighting is consistent, highlighting the action at the center of the frame.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/wisa_70c57fb1238a799f39de2f499082de154275270663dd3d97c85cc06292d7fde8.json"},{"id":"wisa_74ce70de3291f0d44d95d818f56360faff4e55e1a88f86e48cc05ea934da87a8","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/wisa_74ce70de3291f0d44d95d818f56360faff4e55e1a88f86e48cc05ea934da87a8.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/wisa_74ce70de3291f0d44d95d818f56360faff4e55e1a88f86e48cc05ea934da87a8.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/wisa_74ce70de3291f0d44d95d818f56360faff4e55e1a88f86e48cc05ea934da87a8.jpg","sourceDataset":"WISA-80K","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a mechanical process where a large, metallic cylindrical object, likely part of a hydraulic press, descends onto a block of rock placed on a yellow and black striped base. The rock is initially intact but begins to crack under the pressure. As the press continues to descend, the rock shatters into smaller fragments, scattering debris around the base. The background features a plain wall and a control panel with a yellow button and black and yellow striped warning tape, indicating a controlled industrial environment. The lighting is consistent throughout, highlighting the action and the materials involved. The sequence shows the gradual destruction of the rock, emphasizing the power and precision of the mechanical force applied.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/wisa_74ce70de3291f0d44d95d818f56360faff4e55e1a88f86e48cc05ea934da87a8.json"},{"id":"wisa_7907626d01e3b78cb6544856ef3210a087d0dd508797a73a586a5cebfbb935be","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_7907626d01e3b78cb6544856ef3210a087d0dd508797a73a586a5cebfbb935be.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_7907626d01e3b78cb6544856ef3210a087d0dd508797a73a586a5cebfbb935be.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/wisa_7907626d01e3b78cb6544856ef3210a087d0dd508797a73a586a5cebfbb935be.jpg","sourceDataset":"WISA-80K","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a close-up view of an espresso machine in action, focusing on the process of brewing coffee. The machine's spout is prominently featured, with a steady stream of rich, dark brown espresso flowing into a shiny, metallic cup below. The cup is positioned directly beneath the spout, ensuring a smooth pour without spillage. The background is blurred, drawing attention to the machine and the cup, which reflects light, adding a subtle shimmer to the scene. The camera remains stationary throughout the sequence, maintaining a consistent angle that highlights the precision and smoothness of the espresso extraction. The video emphasizes the artistry and craftsmanship involved in making a perfect espresso shot, with no other objects or characters present in the frame.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/wisa_7907626d01e3b78cb6544856ef3210a087d0dd508797a73a586a5cebfbb935be.json"},{"id":"wisa_7e6734f077170178bb3484b6aabf461072f82629f995619d177f4ecb89e11a63","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_7e6734f077170178bb3484b6aabf461072f82629f995619d177f4ecb89e11a63.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_7e6734f077170178bb3484b6aabf461072f82629f995619d177f4ecb89e11a63.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/wisa_7e6734f077170178bb3484b6aabf461072f82629f995619d177f4ecb89e11a63.jpg","sourceDataset":"WISA-80K","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a breathtaking scene of a sunrise over a sea of clouds. The sky is painted with hues of orange and pink, gradually transitioning into a soft blue as it meets the horizon. In the distance, a prominent plume of smoke rises from a distant mountain, adding an element of mystery to the serene landscape. As the sun begins to rise, its golden light bathes the clouds in a warm glow, creating a stunning contrast against the cool tones of the sky.\n\nIn the foreground, a tall electrical tower stands amidst the clouds, its structure partially obscured by the mist. The tower's wires stretch across the frame, connecting to other unseen structures, hinting at human presence in this otherwise natural setting. The clouds flow gently around the tower, creating a dynamic interplay between the man-made and the natural elements.\n\nAs the video progresses, the clouds continue to shift and change shape, their movement creating a sense of fluidity and life. The sun gradually ascends higher in the sky, casting","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/wisa_7e6734f077170178bb3484b6aabf461072f82629f995619d177f4ecb89e11a63.json"},{"id":"wisa_7ff3e28bf3162d9dc25147098a00c8dbeabc5d6bdabf718fce0128dd480bcf05","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/wisa_7ff3e28bf3162d9dc25147098a00c8dbeabc5d6bdabf718fce0128dd480bcf05.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/coupled_motion/wisa_7ff3e28bf3162d9dc25147098a00c8dbeabc5d6bdabf718fce0128dd480bcf05.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/coupled_motion/wisa_7ff3e28bf3162d9dc25147098a00c8dbeabc5d6bdabf718fce0128dd480bcf05.jpg","sourceDataset":"WISA-80K","suggestedTrack":"coupled_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a dynamic scene of various fruits and vegetables splashing into water. The sequence begins with a close-up view of sliced lemons, cucumbers, carrots, and cherry tomatoes. These ingredients are dropped into the water, creating ripples and bubbles around them. As they sink, the camera follows their descent, highlighting the vibrant colors and textures of the produce against the clear, glistening water. The movement is fluid and continuous, emphasizing the freshness and crispness of the ingredients. The background remains a neutral gray, ensuring that the focus stays on the falling produce. The video concludes with the ingredients fully submerged, floating gently at the bottom of the frame, surrounded by the shimmering water.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/coupled_motion/wisa_7ff3e28bf3162d9dc25147098a00c8dbeabc5d6bdabf718fce0128dd480bcf05.json"},{"id":"wisa_8efcc536926eb1118436250bc09f275fc06e797bfe38e9a29c26e42878ecef6b","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_8efcc536926eb1118436250bc09f275fc06e797bfe38e9a29c26e42878ecef6b.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_8efcc536926eb1118436250bc09f275fc06e797bfe38e9a29c26e42878ecef6b.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/wisa_8efcc536926eb1118436250bc09f275fc06e797bfe38e9a29c26e42878ecef6b.jpg","sourceDataset":"WISA-80K","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video depicts a close-up scene where a roll of toilet paper is being subjected to intense heat from a blowtorch. The toilet paper is positioned on a perforated white surface, likely a workbench or table. As the blowtorch is applied, the outer layer of the toilet paper begins to char and burn, producing bright orange flames and visible sparks. The heat causes the paper to curl and blacken, indicating the progression of the burning process. The camera remains stationary throughout the sequence, focusing tightly on the interaction between the blowtorch and the toilet paper. The background remains consistent, showing no significant changes or additional elements entering the frame. The primary focus is on the transformation of the toilet paper under the heat, highlighting the contrast between the initial white material and the darkened, burnt sections as the flame moves across it.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/wisa_8efcc536926eb1118436250bc09f275fc06e797bfe38e9a29c26e42878ecef6b.json"},{"id":"wisa_9186d51d96e4eb74036fb12bcd9223eaaca31d411404caee92762e2a869774cc","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_9186d51d96e4eb74036fb12bcd9223eaaca31d411404caee92762e2a869774cc.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_9186d51d96e4eb74036fb12bcd9223eaaca31d411404caee92762e2a869774cc.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/wisa_9186d51d96e4eb74036fb12bcd9223eaaca31d411404caee92762e2a869774cc.jpg","sourceDataset":"WISA-80K","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a serene scene of a small waterfall cascading over rocks, surrounded by autumn leaves. The water flows smoothly, creating a gentle stream that splashes against the rocks, some of which are partially covered in ice. The rocks are large and dark, with patches of green moss adding texture to their surfaces. Scattered around the base of the waterfall are vibrant red and orange leaves, indicating the season is fall. The leaves appear wet, possibly from the misty spray of the waterfall. The overall atmosphere is peaceful and natural, with no visible animals or human characters present. The camera remains stationary throughout the sequence, focusing on the waterfall and its immediate surroundings, allowing viewers to fully absorb the tranquil beauty of the scene.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/wisa_9186d51d96e4eb74036fb12bcd9223eaaca31d411404caee92762e2a869774cc.json"},{"id":"wisa_91890a6a4d6b686207dfb192e839a33c2eddce9e353f7aa89e722f2f4f859022","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_91890a6a4d6b686207dfb192e839a33c2eddce9e353f7aa89e722f2f4f859022.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_91890a6a4d6b686207dfb192e839a33c2eddce9e353f7aa89e722f2f4f859022.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/wisa_91890a6a4d6b686207dfb192e839a33c2eddce9e353f7aa89e722f2f4f859022.jpg","sourceDataset":"WISA-80K","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a dynamic scene of water splashing dramatically from a cylindrical container against a stark black background. Initially, the water is seen cascading out of the container, forming a crown-like shape with droplets and bubbles scattering around it. As the sequence progresses, the water continues to pour out, creating a mesmerizing display of movement and fluid dynamics. The liquid's surface tension and the force of the flow are highlighted by the formation of small, sparkling droplets that rise and float away. The container remains stationary throughout, serving as the focal point for the viewer's attention. The overall effect is one of energy and motion, emphasizing the beauty and complexity of water in action.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/wisa_91890a6a4d6b686207dfb192e839a33c2eddce9e353f7aa89e722f2f4f859022.json"},{"id":"wisa_91f100d60d8f05200f7705f2d78dd218a7a95cd86e4ca3ac4c2fd1baa5a1db54","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_91f100d60d8f05200f7705f2d78dd218a7a95cd86e4ca3ac4c2fd1baa5a1db54.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_91f100d60d8f05200f7705f2d78dd218a7a95cd86e4ca3ac4c2fd1baa5a1db54.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/wisa_91f100d60d8f05200f7705f2d78dd218a7a95cd86e4ca3ac4c2fd1baa5a1db54.jpg","sourceDataset":"WISA-80K","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video showcases a breathtaking aerial view of Victoria Falls, one of the world's most famous waterfalls. The camera pans slowly from left to right, capturing the immense scale and power of the falls. The water cascades down a sheer cliff face, creating a misty veil that rises into the air. Below the falls, the river flows calmly, dotted with small islands and surrounded by lush greenery. The landscape is a mix of dense vegetation and open grasslands, with trees and bushes scattered across the terrain. The sky above is clear and blue, indicating a sunny day. As the camera moves, it reveals more of the falls' grandeur and the surrounding natural beauty, emphasizing the serene yet dynamic environment. There are no visible animals or characters in the scene; the focus remains on the natural elements and the majestic waterfall.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/wisa_91f100d60d8f05200f7705f2d78dd218a7a95cd86e4ca3ac4c2fd1baa5a1db54.json"},{"id":"wisa_9d057ce44814680ac1e3dc344247d4b5987b4eca72c6e712b802ffaa3369da84","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/wisa_9d057ce44814680ac1e3dc344247d4b5987b4eca72c6e712b802ffaa3369da84.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/wisa_9d057ce44814680ac1e3dc344247d4b5987b4eca72c6e712b802ffaa3369da84.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/wisa_9d057ce44814680ac1e3dc344247d4b5987b4eca72c6e712b802ffaa3369da84.jpg","sourceDataset":"WISA-80K","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a close-up view of a hydraulic press in action. A large, cylindrical metal ram descends from above, positioned directly over a metallic hammer placed on top of a yellow and black striped base. The background features a plain wall with two vertical poles painted in alternating black and yellow stripes, likely for safety or visibility purposes. The scene is industrial, with a focus on the mechanical process. As the ram moves downward, it exerts pressure on the hammer, causing it to compress slightly. The hammer remains stationary throughout the sequence, indicating that the force applied by the ram is sufficient to deform the hammer without moving it. The video emphasizes the precision and power of the hydraulic press, highlighting its capability to apply significant force to small objects. There are no visible characters or animals in the frame, and the camera remains static, maintaining a consistent angle that centers on the interaction between the ram and the hammer.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/wisa_9d057ce44814680ac1e3dc344247d4b5987b4eca72c6e712b802ffaa3369da84.json"},{"id":"wisa_a090016dacbec60d83ffaa0496f91c17d1b0c06073545a6bf9f149090476b8cf","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_a090016dacbec60d83ffaa0496f91c17d1b0c06073545a6bf9f149090476b8cf.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_a090016dacbec60d83ffaa0496f91c17d1b0c06073545a6bf9f149090476b8cf.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/wisa_a090016dacbec60d83ffaa0496f91c17d1b0c06073545a6bf9f149090476b8cf.jpg","sourceDataset":"WISA-80K","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video begins with a close-up shot of a clear glass bowl placed on a wooden surface. Inside the bowl, there is a single egg yolk surrounded by a small pool of egg white. A hand enters the frame from the top left corner, holding a white paper towel. The hand gently places the paper towel over the bowl, partially covering it. The scene remains static for a moment, focusing on the egg and the paper towel.\n\nNext, the hand reappears, this time holding another egg. The hand carefully cracks the egg and pours its contents into the bowl, adding a second yolk to the existing one. The egg white mixes with the first egg white, creating a larger pool around the yolks. The hand then exits the frame, leaving the bowl with two yolks and a larger amount of egg white.\n\nThe video concludes with the bowl containing two egg yolks and a larger pool of egg white, all resting on the wooden surface. The paper towel remains in place,","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/wisa_a090016dacbec60d83ffaa0496f91c17d1b0c06073545a6bf9f149090476b8cf.json"},{"id":"wisa_a0e74919b8ccaebd1dd9825fbdc4a42f6335519e40910d26b7e47377e2caf042","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/wisa_a0e74919b8ccaebd1dd9825fbdc4a42f6335519e40910d26b7e47377e2caf042.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/wisa_a0e74919b8ccaebd1dd9825fbdc4a42f6335519e40910d26b7e47377e2caf042.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/wisa_a0e74919b8ccaebd1dd9825fbdc4a42f6335519e40910d26b7e47377e2caf042.jpg","sourceDataset":"WISA-80K","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a dramatic scene where a golden champagne bottle, adorned with the inscription \"HAPPY 2000,\" is being crushed by a hydraulic press. The bottle stands upright on a metallic platform, its surface gleaming under the light. As the press descends, it begins to crush the bottle from the top, causing the foil seal at the neck to burst open and shatter into pieces. The force of the press continues to apply pressure, flattening the bottle and scattering fragments of glass and foil around the base. The background features a green wall with some yellow warning signs, adding an industrial feel to the setting. The camera remains stationary throughout, focusing closely on the interaction between the press and the bottle, highlighting the destruction in vivid detail.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/wisa_a0e74919b8ccaebd1dd9825fbdc4a42f6335519e40910d26b7e47377e2caf042.json"},{"id":"wisa_a2b6156f0c4f108fd7ae9faf7abaed237cad292f1092707bb3a03ff6c69022ef","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_a2b6156f0c4f108fd7ae9faf7abaed237cad292f1092707bb3a03ff6c69022ef.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_a2b6156f0c4f108fd7ae9faf7abaed237cad292f1092707bb3a03ff6c69022ef.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/wisa_a2b6156f0c4f108fd7ae9faf7abaed237cad292f1092707bb3a03ff6c69022ef.jpg","sourceDataset":"WISA-80K","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a close-up scene set against a stark black background, focusing on a tall glass filled with ice and a slice of lime perched on the rim. A hand enters the frame from the right, holding a clear glass bottle labeled \"GINGER BEER.\" The hand tilts the bottle, pouring a stream of ginger beer into the glass. As the liquid flows, it creates a dynamic splash effect, with droplets scattering around the glass. The hand then moves away, leaving the glass filled with ice and ginger beer, ready to be enjoyed. The entire sequence is smooth and deliberate, emphasizing the refreshing nature of the drink.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/wisa_a2b6156f0c4f108fd7ae9faf7abaed237cad292f1092707bb3a03ff6c69022ef.json"},{"id":"wisa_a36830443c837e9cb4adeb5378a6adb259b50373cce84976fa695835dab35a37","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_a36830443c837e9cb4adeb5378a6adb259b50373cce84976fa695835dab35a37.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_a36830443c837e9cb4adeb5378a6adb259b50373cce84976fa695835dab35a37.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/wisa_a36830443c837e9cb4adeb5378a6adb259b50373cce84976fa695835dab35a37.jpg","sourceDataset":"WISA-80K","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a serene scene of a small waterfall cascading over rocks, surrounded by autumn leaves. The water flows steadily, creating a gentle stream that splashes against the icy surfaces formed by the cold temperatures. The rocks, partially covered in moss, add a touch of green to the otherwise earthy tones of the scene. Leaves in shades of red and orange are scattered around the base of the waterfall, indicating the season is fall. The camera remains stationary throughout the sequence, focusing on the natural beauty of the waterfall and its surroundings. There are no visible animals or human characters in the frame, allowing the viewer to fully immerse themselves in the tranquil environment. The consistent flow of water and the stillness of the leaves create a peaceful and contemplative atmosphere.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/wisa_a36830443c837e9cb4adeb5378a6adb259b50373cce84976fa695835dab35a37.json"},{"id":"wisa_a5d5a734528056e455dafd8291f4776777ac38d1c9887a5b419bd8e21ba98396","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/wisa_a5d5a734528056e455dafd8291f4776777ac38d1c9887a5b419bd8e21ba98396.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/wisa_a5d5a734528056e455dafd8291f4776777ac38d1c9887a5b419bd8e21ba98396.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/wisa_a5d5a734528056e455dafd8291f4776777ac38d1c9887a5b419bd8e21ba98396.jpg","sourceDataset":"WISA-80K","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a close-up view of a hydraulic press in action. The press is composed of a metallic cylinder mounted on a cylindrical base painted with black and yellow diagonal stripes, indicating a hazardous area. Initially, the press is positioned above a row of colorful glass beads arranged in a line. As the press descends, it exerts pressure on the beads, causing them to compress and deform under the force. The beads, which include shades of blue, brown, and amber, gradually flatten and merge together due to the increasing pressure. The press continues its descent until it reaches the bottom of the frame, where the beads are visibly squished into a compact pile. The entire sequence is captured from a fixed angle, focusing solely on the interaction between the press and the beads without any additional elements or background distractions.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/wisa_a5d5a734528056e455dafd8291f4776777ac38d1c9887a5b419bd8e21ba98396.json"},{"id":"wisa_ab07ff3b2b534ee359fc998e3b57f1a87a4cc7ad929e081309a991225fc8f583","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_ab07ff3b2b534ee359fc998e3b57f1a87a4cc7ad929e081309a991225fc8f583.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_ab07ff3b2b534ee359fc998e3b57f1a87a4cc7ad929e081309a991225fc8f583.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/wisa_ab07ff3b2b534ee359fc998e3b57f1a87a4cc7ad929e081309a991225fc8f583.jpg","sourceDataset":"WISA-80K","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a dynamic scene of a river flowing vigorously through a rocky landscape. The river's water is a mix of white frothy rapids and deeper blue-green sections, indicating strong currents and varying depths. In the foreground, large rocks and boulders line the riverbank, some partially submerged, adding texture to the scene. A prominent rock formation sits near the center, partially submerged and surrounded by churning water.\n\nIn the background, a steep cliff rises, covered with patches of green vegetation clinging to its rocky surface. The cliff's rugged texture contrasts sharply with the smooth flow of the river below. On the right side of the frame, a bridge spans across the river, its structure visible against the sky. The bridge appears sturdy and modern, contrasting with the natural elements around it.\n\nThe sky above is partly cloudy, with soft white clouds scattered across a light blue expanse, suggesting a bright but slightly overcast day. The overall atmosphere is one of natural beauty and power, with the","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/wisa_ab07ff3b2b534ee359fc998e3b57f1a87a4cc7ad929e081309a991225fc8f583.json"},{"id":"wisa_b38fdf0ce4f0300f4c216a58f91f8f7cfa5939ac4ea968e8e572ac9127d4b76b","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/wisa_b38fdf0ce4f0300f4c216a58f91f8f7cfa5939ac4ea968e8e572ac9127d4b76b.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/wisa_b38fdf0ce4f0300f4c216a58f91f8f7cfa5939ac4ea968e8e572ac9127d4b76b.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/wisa_b38fdf0ce4f0300f4c216a58f91f8f7cfa5939ac4ea968e8e572ac9127d4b76b.jpg","sourceDataset":"WISA-80K","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a close-up view of an orange slice falling into a pool of orange juice. Initially, the orange slice is centered in the frame, its vibrant yellow color contrasting sharply with the surrounding orange liquid. As it descends, the surface of the juice ripples outward, creating a dynamic splash effect. The orange slice continues to sink, causing the juice to swirl around it, forming concentric circles of ripples. The camera remains stationary throughout, focusing on the interaction between the orange slice and the juice, highlighting the fluid dynamics and the visual impact of the splash. The overall scene is bright and vivid, emphasizing the natural beauty and movement of the fruit and liquid.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/wisa_b38fdf0ce4f0300f4c216a58f91f8f7cfa5939ac4ea968e8e572ac9127d4b76b.json"},{"id":"wisa_b58a660508b693c7bd9b69c1dd50c757d9bce09bd33ad57e7bb4181965f8b348","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/wisa_b58a660508b693c7bd9b69c1dd50c757d9bce09bd33ad57e7bb4181965f8b348.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/wisa_b58a660508b693c7bd9b69c1dd50c757d9bce09bd33ad57e7bb4181965f8b348.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/wisa_b58a660508b693c7bd9b69c1dd50c757d9bce09bd33ad57e7bb4181965f8b348.jpg","sourceDataset":"WISA-80K","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a mechanical press in action, focusing on the process of crushing a small metallic object. The press, composed of a large, cylindrical metal component, descends onto a smaller, rectangular metallic piece placed atop a yellow and black striped base. As the press begins to descend, the metallic piece starts to deform under the immense pressure. The material crumbles and shatters into smaller fragments, scattering debris around the base. The press continues its downward motion, further compressing the object until it is completely flattened. Throughout the sequence, the camera remains stationary, providing a clear view of the entire process without any noticeable changes in angle or movement. The background features a plain wall with some structural elements, emphasizing the industrial setting of the scene.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/wisa_b58a660508b693c7bd9b69c1dd50c757d9bce09bd33ad57e7bb4181965f8b348.json"},{"id":"wisa_ba2d1a2e4d63ad89e8b8f1304eff9b5cb66db87abb11bd9d1111fb1f95ddd335","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_ba2d1a2e4d63ad89e8b8f1304eff9b5cb66db87abb11bd9d1111fb1f95ddd335.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_ba2d1a2e4d63ad89e8b8f1304eff9b5cb66db87abb11bd9d1111fb1f95ddd335.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/wisa_ba2d1a2e4d63ad89e8b8f1304eff9b5cb66db87abb11bd9d1111fb1f95ddd335.jpg","sourceDataset":"WISA-80K","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video showcases a close-up view of a plated meal on a wooden table. The plate is white and rectangular, holding a piece of grilled salmon with a golden-brown crust, seasoned with visible black pepper. Surrounding the salmon are neatly arranged vegetables: vibrant orange carrot slices, a small ear of corn, and green broccoli florets. A creamy white sauce is being poured over the salmon from a white container held by an unseen hand, creating a smooth, glossy layer across the fish's surface. The sauce flows steadily, covering more of the salmon with each frame. The background remains consistent throughout, focusing solely on the plate and its contents, emphasizing the textures and colors of the food. There are no characters or animals present, and the camera maintains a steady, fixed position, capturing the pouring action in a continuous shot.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/wisa_ba2d1a2e4d63ad89e8b8f1304eff9b5cb66db87abb11bd9d1111fb1f95ddd335.json"},{"id":"wisa_bacf7ba51b460ff4f22e82bb0239ab53bdec2d6ebd7bfb8744a22a9ed41ccaa7","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_bacf7ba51b460ff4f22e82bb0239ab53bdec2d6ebd7bfb8744a22a9ed41ccaa7.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_bacf7ba51b460ff4f22e82bb0239ab53bdec2d6ebd7bfb8744a22a9ed41ccaa7.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/wisa_bacf7ba51b460ff4f22e82bb0239ab53bdec2d6ebd7bfb8744a22a9ed41ccaa7.jpg","sourceDataset":"WISA-80K","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a close-up scene set outdoors, likely on a table or flat surface. A rectangular stone block serves as the base for an experiment involving fire. Atop the stone block, a small object, possibly a piece of fabric or material, is ignited, producing bright orange flames that flicker vigorously. The background reveals a natural setting with trees and foliage, suggesting the experiment is taking place in a garden or forested area.\n\nAs the video progresses, a hand enters the frame from the left side, holding a white cloth or napkin. The hand carefully places the cloth over the burning object, covering it partially. This action seems to be part of a controlled experiment, possibly to extinguish the fire or to observe the reaction of the material under heat. The flame initially continues to burn beneath the cloth but gradually diminishes as the heat is absorbed by the fabric. Smoke begins to rise, indicating the cooling effect of the cloth.\n\nThroughout the sequence, the camera remains stationary, focusing closely on","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/wisa_bacf7ba51b460ff4f22e82bb0239ab53bdec2d6ebd7bfb8744a22a9ed41ccaa7.json"},{"id":"wisa_bba05b6b9ee74d2bbcd17d3a2f8360d99ea6768eb1b7d86e7e17d811898e594c","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_bba05b6b9ee74d2bbcd17d3a2f8360d99ea6768eb1b7d86e7e17d811898e594c.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_bba05b6b9ee74d2bbcd17d3a2f8360d99ea6768eb1b7d86e7e17d811898e594c.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/wisa_bba05b6b9ee74d2bbcd17d3a2f8360d99ea6768eb1b7d86e7e17d811898e594c.jpg","sourceDataset":"WISA-80K","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a serene moment in a cozy kitchen setting where a person is pouring coffee from a sleek, stainless steel French press into a clear glass mug. The individual's hands are prominently featured, with one hand holding the mug steady while the other presses down on the plunger of the French press to release the coffee. The background reveals a rustic charm with wooden shelves lined with various jars and bottles, adding warmth to the scene. The lighting is soft and natural, suggesting the time might be during the day. As the coffee flows smoothly into the mug, the camera remains stationary, focusing closely on the action of pouring, emphasizing the simplicity and tranquility of the moment. The overall atmosphere is calm and inviting, highlighting the ritualistic pleasure of enjoying a freshly brewed cup of coffee.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/wisa_bba05b6b9ee74d2bbcd17d3a2f8360d99ea6768eb1b7d86e7e17d811898e594c.json"},{"id":"wisa_c6d3f0b9c3a485b0653f321f7dfd002f520cd8b80f344ed4b99622c2126889c8","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_c6d3f0b9c3a485b0653f321f7dfd002f520cd8b80f344ed4b99622c2126889c8.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_c6d3f0b9c3a485b0653f321f7dfd002f520cd8b80f344ed4b99622c2126889c8.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/wisa_c6d3f0b9c3a485b0653f321f7dfd002f520cd8b80f344ed4b99622c2126889c8.jpg","sourceDataset":"WISA-80K","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a dramatic scene of volcanic activity at night. The primary focus is on the glowing lava flowing into the ocean, creating a mesmerizing display of fiery streams against the dark backdrop. The lava flows are vividly illuminated by the intense orange and yellow hues, casting a warm glow that contrasts sharply with the surrounding darkness. As the lava meets the water, it produces billowing plumes of steam and smoke, which rise into the air, adding to the dynamic visual spectacle. The camera remains stationary throughout the sequence, allowing viewers to fully absorb the raw power and beauty of nature's force. The continuous flow of lava and the ever-changing shapes of the steam clouds create a captivating and almost hypnotic effect, emphasizing the relentless and unpredictable nature of volcanic eruptions.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/wisa_c6d3f0b9c3a485b0653f321f7dfd002f520cd8b80f344ed4b99622c2126889c8.json"},{"id":"wisa_c79b35ec415cda2ffddd15d930c8a6b748cdc31968d6c91d7f988d4ff97d3f40","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_c79b35ec415cda2ffddd15d930c8a6b748cdc31968d6c91d7f988d4ff97d3f40.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_c79b35ec415cda2ffddd15d930c8a6b748cdc31968d6c91d7f988d4ff97d3f40.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/wisa_c79b35ec415cda2ffddd15d930c8a6b748cdc31968d6c91d7f988d4ff97d3f40.jpg","sourceDataset":"WISA-80K","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a serene tea ceremony scene. A hand holds a red teapot, pouring a light yellow liquid into three white ceramic cups arranged on a round, glossy red tray. The tray is placed on a wooden surface, adding a warm tone to the setting. In the background, a blue and white patterned cloth partially covers another surface, and a decorative plate with floral designs is visible, enhancing the traditional aesthetic. The pouring action is smooth and deliberate, filling each cup evenly. The liquid's gentle flow and the cups' steady placement suggest a calm and methodical process, emphasizing the ritualistic nature of the tea ceremony. The overall atmosphere is tranquil, focusing on the beauty and tradition of tea preparation.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/wisa_c79b35ec415cda2ffddd15d930c8a6b748cdc31968d6c91d7f988d4ff97d3f40.json"},{"id":"wisa_cfa27c95054e3d2314f89d7509db1db52fb45fe68a06a9a27a02ac12959554c2","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_cfa27c95054e3d2314f89d7509db1db52fb45fe68a06a9a27a02ac12959554c2.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_cfa27c95054e3d2314f89d7509db1db52fb45fe68a06a9a27a02ac12959554c2.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/wisa_cfa27c95054e3d2314f89d7509db1db52fb45fe68a06a9a27a02ac12959554c2.jpg","sourceDataset":"WISA-80K","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a close-up view of honey being poured onto a surface, creating a mesmerizing display of fluid dynamics. The honey flows smoothly from a small, transparent container, forming a thin stream that curves gently as it descends. Upon contact with the honey already on the surface, the stream thickens and spreads out, forming a dome-like shape. The surface tension of the honey causes the liquid to stretch and form a delicate, translucent film around the base of the stream. As the honey continues to pour, the dome grows larger and more defined, with the edges becoming slightly wavy due to the surface tension. The golden hue of the honey is vivid and warm, reflecting light and creating a shimmering effect. The background remains blurred, ensuring that the focus stays on the intricate details of the honey's flow and the formation of the dome. The overall scene is one of natural beauty and the captivating movement of a simple substance in motion.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/wisa_cfa27c95054e3d2314f89d7509db1db52fb45fe68a06a9a27a02ac12959554c2.json"},{"id":"wisa_d7184e9b5e990d53bc98f21c13713c8afb4925ad3365f87ed330b5c46979763b","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_d7184e9b5e990d53bc98f21c13713c8afb4925ad3365f87ed330b5c46979763b.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_d7184e9b5e990d53bc98f21c13713c8afb4925ad3365f87ed330b5c46979763b.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/wisa_d7184e9b5e990d53bc98f21c13713c8afb4925ad3365f87ed330b5c46979763b.jpg","sourceDataset":"WISA-80K","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a close-up view of a barista skillfully pouring steamed milk into an espresso cup to create latte art. The barista's hands are steady as they hold a stainless steel pitcher, pouring the milk in a controlled manner. The milk flows smoothly, forming a heart shape on the surface of the espresso. The background reveals part of a modern coffee machine, indicating a professional setting. The lighting is bright, highlighting the rich brown color of the espresso and the creamy white of the milk. The barista's movements are precise, showcasing their expertise in crafting a visually appealing drink. The video focuses on the process, emphasizing the artistry involved in creating latte art.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/wisa_d7184e9b5e990d53bc98f21c13713c8afb4925ad3365f87ed330b5c46979763b.json"},{"id":"wisa_d87381a335c66c311e235107d1492e9e115ac5d718e711568fdd66ddf585ee82","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_d87381a335c66c311e235107d1492e9e115ac5d718e711568fdd66ddf585ee82.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_d87381a335c66c311e235107d1492e9e115ac5d718e711568fdd66ddf585ee82.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/wisa_d87381a335c66c311e235107d1492e9e115ac5d718e711568fdd66ddf585ee82.jpg","sourceDataset":"WISA-80K","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video showcases an aerial view of a majestic bridge spanning across a deep canyon. The bridge, constructed with a robust metal framework, arches gracefully over a turbulent river below. The surrounding landscape is lush with dense greenery, featuring a mix of trees and shrubs that cover the steep cliffs on either side of the canyon. In the distance, misty waterfalls can be seen cascading down the cliffs, adding a dynamic element to the serene environment. The sky above is clear with a few scattered clouds, indicating a bright and sunny day. As the camera pans slowly from left to right, it captures the intricate details of the bridge's structure and the powerful flow of the river beneath. The scene remains tranquil throughout, emphasizing the natural beauty and engineering marvel of the bridge.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/wisa_d87381a335c66c311e235107d1492e9e115ac5d718e711568fdd66ddf585ee82.json"},{"id":"wisa_dba1b94a80c96e9f8d2d8749836cc60a58af5400bf21a2719ce36f7a4ea43701","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/wisa_dba1b94a80c96e9f8d2d8749836cc60a58af5400bf21a2719ce36f7a4ea43701.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/wisa_dba1b94a80c96e9f8d2d8749836cc60a58af5400bf21a2719ce36f7a4ea43701.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/wisa_dba1b94a80c96e9f8d2d8749836cc60a58af5400bf21a2719ce36f7a4ea43701.jpg","sourceDataset":"WISA-80K","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video depicts a mechanical press in operation, focusing on the process of compressing a cylindrical object. The scene is set in an industrial environment, characterized by a plain wall and a metal table. The press mechanism, a large metallic cylinder, descends onto a black and yellow striped cylinder placed on the table. As the press descends, it exerts pressure on the striped cylinder, causing it to deform slightly. Small fragments of material begin to break off and scatter around the base of the striped cylinder. The press continues its downward motion, applying increasing force until the striped cylinder is visibly compressed and deformed. The camera remains stationary throughout the sequence, capturing the entire process from a fixed angle, emphasizing the mechanical action and the resulting deformation of the object under pressure.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/wisa_dba1b94a80c96e9f8d2d8749836cc60a58af5400bf21a2719ce36f7a4ea43701.json"},{"id":"wisa_dddfb43a1a3c38c365be28a99b99222bc7d6c512f8edd0c2a6a467b56adbf8ca","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_dddfb43a1a3c38c365be28a99b99222bc7d6c512f8edd0c2a6a467b56adbf8ca.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_dddfb43a1a3c38c365be28a99b99222bc7d6c512f8edd0c2a6a467b56adbf8ca.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/wisa_dddfb43a1a3c38c365be28a99b99222bc7d6c512f8edd0c2a6a467b56adbf8ca.jpg","sourceDataset":"WISA-80K","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a close-up view of the process of brewing coffee using the pour-over method. A metal kettle is positioned above a glass carafe, which holds a cone-shaped filter filled with ground coffee. The filter is placed on top of the carafe, which has a black base to catch any drips. As the video progresses, hot water is poured from the kettle into the center of the coffee grounds, creating a swirling motion as it filters through the grounds. The water gradually spreads out, allowing the coffee to drip down into the carafe below. The steam rising from the coffee indicates its warmth and freshness. The background remains blurred, keeping the focus entirely on the brewing process. The lighting highlights the rich brown color of the coffee and the clarity of the water as it flows through the grounds. There are no other objects or characters present in the scene, ensuring that the viewer's attention is solely on the meticulous preparation of the coffee.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/wisa_dddfb43a1a3c38c365be28a99b99222bc7d6c512f8edd0c2a6a467b56adbf8ca.json"},{"id":"wisa_e5c0145e4dde8a5164cf67d8130031e3299889f5016e6546d4679bf0043953a3","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/wisa_e5c0145e4dde8a5164cf67d8130031e3299889f5016e6546d4679bf0043953a3.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/viewpoint_motion/wisa_e5c0145e4dde8a5164cf67d8130031e3299889f5016e6546d4679bf0043953a3.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/viewpoint_motion/wisa_e5c0145e4dde8a5164cf67d8130031e3299889f5016e6546d4679bf0043953a3.jpg","sourceDataset":"WISA-80K","suggestedTrack":"viewpoint_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video depicts a mechanical test setup where a large, metallic hydraulic press is positioned above a cylindrical object marked with black and yellow hazard stripes. Atop this cylinder rests a padlock with two keys attached to it. The hydraulic press slowly descends towards the padlock, applying increasing pressure. As the press continues its descent, the padlock begins to deform under the force, with the metal body of the lock starting to buckle and the shackle bending. The keys remain intact but are visibly stressed by the pressure. The background remains static, showing a plain wall and part of the machinery's structure, emphasizing the focus on the padlock's durability under extreme pressure. The video captures the gradual deformation of the padlock until it eventually fails, demonstrating the strength or weakness of the lock under such conditions.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/viewpoint_motion/wisa_e5c0145e4dde8a5164cf67d8130031e3299889f5016e6546d4679bf0043953a3.json"},{"id":"wisa_e9d2557b7e5dc5761efb6948039a8f5abf85fe7ecdfa730662d46de87424f3bd","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_e9d2557b7e5dc5761efb6948039a8f5abf85fe7ecdfa730662d46de87424f3bd.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_e9d2557b7e5dc5761efb6948039a8f5abf85fe7ecdfa730662d46de87424f3bd.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/wisa_e9d2557b7e5dc5761efb6948039a8f5abf85fe7ecdfa730662d46de87424f3bd.jpg","sourceDataset":"WISA-80K","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video captures a close-up view of a person skillfully pouring steamed milk into a cup of coffee to create intricate latte art. The cup is held steadily by the individual's hands, which are visible in the frame. The background reveals a clean, modern kitchen setting with a marble countertop and a yellow cloth neatly placed on it. A coffee machine is partially visible, indicating the setting is likely a café or a home kitchen equipped for coffee preparation. The milk is poured from a colorful pitcher, adding a vibrant touch to the scene. As the milk flows, it forms a beautiful, swirling pattern on the surface of the coffee, showcasing the precision and artistry involved in latte art. The camera remains steady throughout, focusing on the pouring action and the evolving design on the coffee's surface. The overall atmosphere is one of calm concentration and the enjoyment of a meticulous craft.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/wisa_e9d2557b7e5dc5761efb6948039a8f5abf85fe7ecdfa730662d46de87424f3bd.json"},{"id":"wisa_fbb409f97b796033761e4f6938ca7804b098e56faebe829e9607ee899dd67039","videoPath":"curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_fbb409f97b796033761e4f6938ca7804b098e56faebe829e9607ee899dd67039.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/videos/scene_motion/wisa_fbb409f97b796033761e4f6938ca7804b098e56faebe829e9607ee899dd67039.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v4/stage-b/batch-001/initial_frames/scene_motion/wisa_fbb409f97b796033761e4f6938ca7804b098e56faebe829e9607ee899dd67039.jpg","sourceDataset":"WISA-80K","suggestedTrack":"scene_motion","scene":"","spatialAbility":"","perspective":"uncertain","caption":"The video begins with a close-up shot of a roll of toilet paper placed on a dark surface against a black background. A gloved hand holding a lit match approaches the toilet paper. The match is brought close to the paper, and upon contact, the toilet paper ignites, producing flames and smoke. The fire spreads rapidly across the surface of the toilet paper, causing it to curl and twist as it burns. The flames are bright orange and yellow, with sparks flying off the burning material. As the fire consumes the toilet paper, it leaves behind a smoldering residue. The scene captures the dramatic transformation of the toilet paper from a static object to one engulfed in flames, emphasizing the destructive power of fire. The entire sequence is set against a stark black background, which accentuates the vivid colors of the fire and the smoke.","annotationPath":"curated/spatial-world-model/v4/stage-b/batch-001/annotations/scene_motion/wisa_fbb409f97b796033761e4f6938ca7804b098e56faebe829e9607ee899dd67039.json"},{"id":"wisa_glass_marble_wooden_table","videoPath":"curated/spatial-world-model/v5/screenshot-references/videos/scene_motion/index_11.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v5/screenshot-references/videos/scene_motion/index_11.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v5/screenshot-references/initial_frames/wisa_glass_marble_wooden_table.jpg","sourceDataset":"WISA-80K","suggestedTrack":"scene_motion","scene":"glass marble, polished wooden table, window light","spatialAbility":"direction, rolling_support, contact, relative_position, specular_reflection","perspective":"low table-level view with the marble moving against a stable window-lit background","caption":"a solitary glass marble rolls across a polished wooden table. as it glides, sunlight filters through a nearby window, casting a bright halo around it. the marble's surface perfectly reflects the warm glow and the faint outlines of the room, creating a captivating interplay of light and shape.","annotationPath":"curated/spatial-world-model/v5/screenshot-references/annotations/wisa_glass_marble_wooden_table.json"},{"id":"wisa_red_balloon_reflection","videoPath":"curated/spatial-world-model/v5/screenshot-references/videos/scene_motion/index_10.mp4","videoUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v5/screenshot-references/videos/scene_motion/index_10.mp4","initialFrameUrl":"https://huggingface.co/datasets/Xinyun-Liu/WorldModelBench/resolve/main/curated/spatial-world-model/v5/screenshot-references/initial_frames/wisa_red_balloon_reflection.jpg","sourceDataset":"WISA-80K","suggestedTrack":"scene_motion","scene":"red balloon, still pond, reflection and ripples","spatialAbility":"above_below, reflection, surface_interface, lateral_drift, ripple_deformation","perspective":"static close view looking down at the balloon and its reflected image on water","caption":"a solitary red balloon floats silently against a still pond. its vibrant surface mirrors the sky's blue and soft clouds, creating a perfect reflection. as a gentle breeze stirs, the balloon sways slightly, causing ripples that distort its mirrored image, blending reality with illusion.","annotationPath":"curated/spatial-world-model/v5/screenshot-references/annotations/wisa_red_balloon_reflection.json"}];