happy8825/qweninstruct_tuned · Datasets at Hugging Face

user string	videos list	gt int64	predict string	pred_order list	top1_correct bool	gt_pos int64	latency_ms float64	index int64	request_messages list
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A weight lifting tutorial is given. The coach helps the guy in red with the proper body placement and lifting technique." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_eVTMUEYhwDE.mp4", "activitynet/videos/v_NpBZn7OHUKo.mp4", "activitynet/videos/v_uqiMw7tQ1Cc.mp4", "activitynet/videos/v_gIhVeU8xbrs.mp4", "activitynet/videos/v_1epGZvRN3Fw.mp4" ]	3	<answer>1</answer>	[ 1 ]	false	0	25,768.688315	0	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A weight lifting tutorial is given. The coach helps the guy in red with the proper body placement and lifting technique.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_eVTMUEYhwDE.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_NpBZn7OHUKo.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_uqiMw7tQ1Cc.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_gIhVeU8xbrs.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_1epGZvRN3Fw.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A man is seen speaking to the camera and pans out into more men standing behind him. The first man then begins performing martial arts moves while speaking to he camera. He continues moving around and looking to the camera." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_HktZZPJMU8s.mp4", "activitynet/videos/v_1imA9vLRd3k.mkv", "activitynet/videos/v_LmioUbGNv04.mp4", "activitynet/videos/v_bXdq2zI1Ms0.mp4", "activitynet/videos/v_6LLDsbc8XMM.mp4" ]	4	<answer>3</answer>	[ 3 ]	false	0	33,041.859635	1	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man is seen speaking to the camera and pans out into more men standing behind him. The first man then begins performing martial arts moves while speaking to he camera. He continues moving around and looking to the camera.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_HktZZPJMU8s.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_1imA9vLRd3k.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_LmioUbGNv04.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_bXdq2zI1Ms0.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_6LLDsbc8XMM.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "Several shots of boats are shown riding around as well as people riding on the boats and speaking to one another. Several shots are then shown of people sitting on the water as well as life under the water. The camera pans around old cars under water as well as people in the area." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_FsS_NCZEfaI.mp4", "activitynet/videos/v_FX4inHmWQtE.mp4", "activitynet/videos/v_sxQbiXWFdKs.mp4", "activitynet/videos/v_3TNDCTlLlGk.mkv", "activitynet/videos/v_sG3JpMuXFnU.mp4" ]	1	<answer>2</answer>	[ 2 ]	false	0	38,336.422621	2	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"Several shots of boats are shown riding around as well as people riding on the boats and speaking to one another. Several shots are then shown of people sitting on the water as well as life under the water. The camera pans around old cars under water as well as people in the area.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_FsS_NCZEfaI.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_FX4inHmWQtE.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_sxQbiXWFdKs.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_3TNDCTlLlGk.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_sG3JpMuXFnU.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A woman is seen speaking to the camera while holding an accordion and and moving her hands around. She demonstrates how to play the instrument while still speaking to the camera and moving all around." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_Rho3u46ZIEE.mp4", "activitynet/videos/v_KzZlSbM16aY.mp4", "activitynet/videos/v_K6Tm5xHkJ5c.mp4", "activitynet/videos/v_t1-GV2bAL4I.mp4", "activitynet/videos/v_91XkPU8A5hs.mp4" ]	3	<answer>3</answer>	[ 3 ]	true	1	22,048.000755	3	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A woman is seen speaking to the camera while holding an accordion and and moving her hands around. She demonstrates how to play the instrument while still speaking to the camera and moving all around.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_Rho3u46ZIEE.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_KzZlSbM16aY.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_K6Tm5xHkJ5c.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_t1-GV2bAL4I.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_91XkPU8A5hs.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "There are some people including small children near a soccer field. A small boy is playing by himself a he stands on a large square tile. A man dressed in a blue shirt come running towards him and points out his finger, indicating to the boy to go there. The boy gets off the tile and walks to another tile. Then another little boy wearing a gray shirt comes to that tile and begins playing. The other little boy moves away to another tile. There are some man playing with small children on the lawn. The little boy comes running towards some children and his father follows him." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_msiX-xky6Ac.mp4", "activitynet/videos/v_Ty0BvWyYPVA.mp4", "activitynet/videos/v_pgff9mC5y3s.mp4", "activitynet/videos/v_4Lu8ECLHvK4.mp4", "activitynet/videos/v_f6j6lb0AaxM.mp4" ]	4	<answer>4</answer>	[ 4 ]	true	1	18,662.458615	4	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"There are some people including small children near a soccer field. A small boy is playing by himself a he stands on a large square tile. A man dressed in a blue shirt come running towards him and points out his finger, indicating to the boy to go there. The boy gets off the tile and walks to another tile. Then another little boy wearing a gray shirt comes to that tile and begins playing. The other little boy moves away to another tile. There are some man playing with small children on the lawn. The little boy comes running towards some children and his father follows him.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_msiX-xky6Ac.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_Ty0BvWyYPVA.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_pgff9mC5y3s.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_4Lu8ECLHvK4.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_f6j6lb0AaxM.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "People are dancing having fun at a party. A race starts and people are running. Cheerleaders are standing on the side of the road. People are dancing on the grass." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_iA2Q4t-o58w.mp4", "activitynet/videos/v_dJ0kxnyVzFI.mp4", "activitynet/videos/v_bG7hnpAeja0.mp4", "activitynet/videos/v_HWV_ccmZVPA.mp4", "activitynet/videos/v_fG0nn2IVdDM.mp4" ]	4	<answer>4</answer>	[ 4 ]	true	1	16,536.044198	5	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"People are dancing having fun at a party. A race starts and people are running. Cheerleaders are standing on the side of the road. People are dancing on the grass.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_iA2Q4t-o58w.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_dJ0kxnyVzFI.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_bG7hnpAeja0.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_HWV_ccmZVPA.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_fG0nn2IVdDM.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A female weight lifter bends at the knees. She lifts a barbell to her chest. She then lifts it over her head before dropping it heavily to the ground." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_i1PpX1IOcIs.mp4", "activitynet/videos/v_GGSY1Qvo990.mp4", "activitynet/videos/v_j9QPrMZuegY.mp4", "activitynet/videos/v_PJysE5c1WDs.mp4", "activitynet/videos/v_aDaazrgvjJg.mp4" ]	2	<answer>2</answer>	[ 2 ]	true	1	9,994.998532	6	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A female weight lifter bends at the knees. She lifts a barbell to her chest. She then lifts it over her head before dropping it heavily to the ground.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_i1PpX1IOcIs.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_GGSY1Qvo990.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_j9QPrMZuegY.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_PJysE5c1WDs.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_aDaazrgvjJg.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A large kid playground slide is shown. Several people slide down, a woman and her little girl." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_yj2WJBqmEHk.mp4", "activitynet/videos/v__uKKSGTNJAY.mp4", "activitynet/videos/v_5I0K3y27EUM.mp4", "activitynet/videos/v_JTrwGfPJNzU.mp4", "activitynet/videos/v_hghdjiQlYko.mp4" ]	4	<answer>1</answer>	[ 1 ]	false	0	10,312.377371	8	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A large kid playground slide is shown. Several people slide down, a woman and her little girl.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_yj2WJBqmEHk.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v__uKKSGTNJAY.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_5I0K3y27EUM.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_JTrwGfPJNzU.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_hghdjiQlYko.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A guy puts a black cat on the kitchen floor. The guy reaches for a scissor and sits next to the cat. The guy carries the cat. The guy uses the scissor to cut the cat's claws. The guy puts the clippings in his palm. The guy pets the cat and puts the cat on the floor. The guy gets up and trashes the clippings. The owner and pet exit the kitchen." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_qaB0igbuKuQ.mp4", "activitynet/videos/v_tfPm9xAZ5z0.mp4", "activitynet/videos/v_xOmfJGR5fBw.mp4", "activitynet/videos/v_frePM0YGtQE.mp4", "activitynet/videos/v_U36rsW_WhUA.mp4" ]	4	<answer>4</answer>	[ 4 ]	true	1	20,151.516695	7	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A guy puts a black cat on the kitchen floor. The guy reaches for a scissor and sits next to the cat. The guy carries the cat. The guy uses the scissor to cut the cat's claws. The guy puts the clippings in his palm. The guy pets the cat and puts the cat on the floor. The guy gets up and trashes the clippings. The owner and pet exit the kitchen.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_qaB0igbuKuQ.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_tfPm9xAZ5z0.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_xOmfJGR5fBw.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_frePM0YGtQE.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_U36rsW_WhUA.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A woman is seen kneeling down next to a man. Another person is seen kneeling nearby. The man pans closely around the man." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_s1YjWVUu6pM.mp4", "activitynet/videos/v_YZvdzvM-124.mp4", "activitynet/videos/v_lfllVwgOWBk.mp4", "activitynet/videos/v_gOniW-yEZ0k.mp4", "activitynet/videos/v_5BbHu0WQZqw.mp4" ]	4	<answer>1</answer>	[ 1 ]	false	0	15,749.863021	9	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A woman is seen kneeling down next to a man. Another person is seen kneeling nearby. The man pans closely around the man.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_s1YjWVUu6pM.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_YZvdzvM-124.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_lfllVwgOWBk.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_gOniW-yEZ0k.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_5BbHu0WQZqw.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A chef is talking inside a kitchen as he fills a pan with frying oil and water. He boils pasta noodles in a pot. He then tastes the noodles when they are done." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_rwxSphRRIL8.mp4", "activitynet/videos/v_kbe4iowYMqM.mp4", "activitynet/videos/v_3j2d27w3x5Q.mp4", "activitynet/videos/v_RKDjetk5Kko.mp4", "activitynet/videos/v_Po8gmt7hVTY.mkv" ]	5	<answer>1</answer>	[ 1 ]	false	0	18,145.284797	12	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A chef is talking inside a kitchen as he fills a pan with frying oil and water. He boils pasta noodles in a pot. He then tastes the noodles when they are done.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_rwxSphRRIL8.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_kbe4iowYMqM.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_3j2d27w3x5Q.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_RKDjetk5Kko.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_Po8gmt7hVTY.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A man is sitting in a chair getting a tattoo. He stands up and yells at the man tattooing. A woman in a pink shirt is sitting in front of him. He walks out the door of the shop and walks down the street." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_smh90DBXsBg.mp4", "activitynet/videos/v_HtkuvF7VbSQ.mp4", "activitynet/videos/v_aPEqCGdCsp0.mp4", "activitynet/videos/v_qm8sJxsZ5VY.mp4", "activitynet/videos/v_j05b3qqgRxw.mp4" ]	2	<answer>2</answer>	[ 2 ]	true	1	26,017.51495	11	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man is sitting in a chair getting a tattoo. He stands up and yells at the man tattooing. A woman in a pink shirt is sitting in front of him. He walks out the door of the shop and walks down the street.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_smh90DBXsBg.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_HtkuvF7VbSQ.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_aPEqCGdCsp0.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_qm8sJxsZ5VY.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_j05b3qqgRxw.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "Two girls are outside in bathing suits cleaning the front of a green vehicle. One of the girl then walks away and goes to get something from a man cleaning the motorcycle. They continue to wash the vehicle and then the girls walks over and grabs the water hose. She comes back to rinse the vehicle and then holds it up to the girl's head and washes her hair." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_6czh95dpwAA.mp4", "activitynet/videos/v_yACg55C3IlM.mkv", "activitynet/videos/v_iSH43hQoxio.mp4", "activitynet/videos/v_Lwy92HbuZII.mkv", "activitynet/videos/v_XoFikALe8Q0.mp4" ]	2	<answer>2</answer>	[ 2 ]	true	1	16,336.017989	13	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"Two girls are outside in bathing suits cleaning the front of a green vehicle. One of the girl then walks away and goes to get something from a man cleaning the motorcycle. They continue to wash the vehicle and then the girls walks over and grabs the water hose. She comes back to rinse the vehicle and then holds it up to the girl's head and washes her hair.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_6czh95dpwAA.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_yACg55C3IlM.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_iSH43hQoxio.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_Lwy92HbuZII.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_XoFikALe8Q0.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "Three scuba divers are seen moving along the water with one giving a thumbs up to the camera and the camera panning all around the ocean. Several shots are shown of the divers taking pictures under the water as well as taking off their mask and waving to the camera. In the end the divers come to the surface." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_zGTqXydTuQs.mp4", "activitynet/videos/v_ijgLl3PHHE0.mp4", "activitynet/videos/v_W30cufYc_ZI.mp4", "activitynet/videos/v_cHYZPYLwvks.mp4", "activitynet/videos/v_FsS_NCZEfaI.mp4" ]	4	<answer>2</answer>	[ 2 ]	false	0	58,379.563186	10	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"Three scuba divers are seen moving along the water with one giving a thumbs up to the camera and the camera panning all around the ocean. Several shots are shown of the divers taking pictures under the water as well as taking off their mask and waving to the camera. In the end the divers come to the surface.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_zGTqXydTuQs.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_ijgLl3PHHE0.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_W30cufYc_ZI.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_cHYZPYLwvks.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_FsS_NCZEfaI.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A man is seen pushing a lawn mower across a lawn to cut the grass. The man continues moving the machine all along the yard while the camera captures his movements." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_iHO42zwYsu0.mp4", "activitynet/videos/v_CjPN7fw0B48.mp4", "activitynet/videos/v_E9R1H8xRIW8.mp4", "activitynet/videos/v_z1tV0-C3IBw.mp4", "activitynet/videos/v_CJWSed5v4jE.mkv" ]	3	<answer>1</answer>	[ 1 ]	false	0	32,191.08578	14	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man is seen pushing a lawn mower across a lawn to cut the grass. The man continues moving the machine all along the yard while the camera captures his movements.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_iHO42zwYsu0.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_CjPN7fw0B48.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_E9R1H8xRIW8.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_z1tV0-C3IBw.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_CJWSed5v4jE.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A wrestler is seen walking out in front of an audience and sitting on the floor. Two men are then seen walking out onto a pit with one throwing dirt and kneeling down. The men begin fighting with one pushing another out and leads into several more clips of the men wrestling." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_UqU_mAjgknQ.mp4", "activitynet/videos/v_-wXbBZDSIa8.mp4", "activitynet/videos/v_eFbZ0_TJLE0.mkv", "activitynet/videos/v_5qsXmDi8d74.mp4", "activitynet/videos/v_0zjA3KPnLK8.mp4" ]	4	<answer>2</answer>	[ 2 ]	false	0	14,964.81331	16	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A wrestler is seen walking out in front of an audience and sitting on the floor. Two men are then seen walking out onto a pit with one throwing dirt and kneeling down. The men begin fighting with one pushing another out and leads into several more clips of the men wrestling.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_UqU_mAjgknQ.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_-wXbBZDSIa8.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_eFbZ0_TJLE0.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_5qsXmDi8d74.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_0zjA3KPnLK8.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A man is seen sitting in front of a bucket holding clothes in his hands. Another person is seen sitting next to him sticking his hand in a bucket. The men continue washing clothes next to one another while dipping them into a bucket." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_ByF8Pg3xXNA.mp4", "activitynet/videos/v_4OeZViscNp4.mp4", "activitynet/videos/v_k3oPZS_Id3M.mp4", "activitynet/videos/v_V1SEaTS9hos.mp4", "activitynet/videos/v_9RAW6QibWRs.mp4" ]	4	<answer>5</answer>	[ 5 ]	false	0	30,399.536214	15	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man is seen sitting in front of a bucket holding clothes in his hands. Another person is seen sitting next to him sticking his hand in a bucket. The men continue washing clothes next to one another while dipping them into a bucket.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_ByF8Pg3xXNA.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_4OeZViscNp4.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_k3oPZS_Id3M.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_V1SEaTS9hos.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_9RAW6QibWRs.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A man is kneeling on the kitchen floor. He is using a bucket of paints and a canvas. He uses the paints to create an image on the canvas." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_WzDnorAzWVU.mp4", "activitynet/videos/v_sEGceBU8icE.mp4", "activitynet/videos/v_nB90Q8sTBgE.mp4", "activitynet/videos/v_ng14GLT_hHQ.mp4", "activitynet/videos/v_1UgjxeAPq_A.mp4" ]	4	<answer>4</answer>	[ 4 ]	true	1	20,734.282649	17	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man is kneeling on the kitchen floor. He is using a bucket of paints and a canvas. He uses the paints to create an image on the canvas.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_WzDnorAzWVU.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_sEGceBU8icE.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_nB90Q8sTBgE.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_ng14GLT_hHQ.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_1UgjxeAPq_A.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A girl is seen standing near a piece of exercise equipment talking a man. She continues speaking to him and has him watch her while she steps on the machine. She rides the bike moving back and fourth speaking to the man and switches places with the man." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_cROJALtLB1k.mp4", "activitynet/videos/v_nGABbRHJ2Ug.mp4", "activitynet/videos/v__MR8G1jwM4o.mp4", "activitynet/videos/v_f4CSejhkTd8.mp4", "activitynet/videos/v_E50qKeeMbgU.mp4" ]	2	<answer>2</answer>	[ 2 ]	true	1	13,990.917447	19	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A girl is seen standing near a piece of exercise equipment talking a man. She continues speaking to him and has him watch her while she steps on the machine. She rides the bike moving back and fourth speaking to the man and switches places with the man.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_cROJALtLB1k.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_nGABbRHJ2Ug.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v__MR8G1jwM4o.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_f4CSejhkTd8.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_E50qKeeMbgU.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "The camera is showing an arc welder in a shop. A man approaches the arc welder and begins using it to weld some metal bars. The man shows the metal bar to the camera. The man sets the bar down and begins welding it again." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_wPYr19iFxhw.mp4", "activitynet/videos/v_CfDdbeAk8LE.mp4", "activitynet/videos/v_XQaaA2UZYh8.mp4", "activitynet/videos/v_7JXae2so5-E.mp4", "activitynet/videos/v_GcE-0A4Titg.mp4" ]	1	<answer>1</answer>	[ 1 ]	true	1	14,183.498107	18	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"The camera is showing an arc welder in a shop. A man approaches the arc welder and begins using it to weld some metal bars. The man shows the metal bar to the camera. The man sets the bar down and begins welding it again.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_wPYr19iFxhw.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_CfDdbeAk8LE.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_XQaaA2UZYh8.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_7JXae2so5-E.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_GcE-0A4Titg.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A guy exercises on a stationary bike. The guy has his hand on the handles. The guy lets go of the handles and puts his hands to his side." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_arnKDX_ToxE.mp4", "activitynet/videos/v_8-QcL1k5n6k.mp4", "activitynet/videos/v_D0pVkTEYQg8.mp4", "activitynet/videos/v_tnt6Wpv_kHc.mp4", "activitynet/videos/v_c4ctwOucndQ.mp4" ]	3	<answer>3</answer>	[ 3 ]	true	1	11,617.518422	20	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A guy exercises on a stationary bike. The guy has his hand on the handles. The guy lets go of the handles and puts his hands to his side.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_arnKDX_ToxE.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_8-QcL1k5n6k.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_D0pVkTEYQg8.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_tnt6Wpv_kHc.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_c4ctwOucndQ.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A man is looking at a red vase. A woman takes her shirt off. The two begin fighting with swords." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_4OCbTYrThtc.mkv", "activitynet/videos/v_Fdzw3niNDYY.mp4", "activitynet/videos/v_tjEMbP2SODQ.mp4", "activitynet/videos/v_LUDZ7e0RdEE.mp4", "activitynet/videos/v_2icoQWmbocU.mp4" ]	2	<answer>4</answer>	[ 4 ]	false	0	14,144.183129	22	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man is looking at a red vase. A woman takes her shirt off. The two begin fighting with swords.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_4OCbTYrThtc.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_Fdzw3niNDYY.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_tjEMbP2SODQ.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_LUDZ7e0RdEE.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_2icoQWmbocU.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "We see an opening title screen. A pair of red boots sit on a table. A lady talks and pours soap in a glass then wipes the boots with the soap. The lady talks and shows a bottle of olive oil. We see the closing title screen." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_od1jHUzgrAU.mp4", "activitynet/videos/v_uyGxlvak-Bg.mkv", "activitynet/videos/v_dFVX_2UQ2WY.mp4", "activitynet/videos/v_y9kk0ptXevk.mp4", "activitynet/videos/v_k85EQoiLckw.mp4" ]	4	<answer>4</answer>	[ 4 ]	true	1	26,904.119644	21	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"We see an opening title screen. A pair of red boots sit on a table. A lady talks and pours soap in a glass then wipes the boots with the soap. The lady talks and shows a bottle of olive oil. We see the closing title screen.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_od1jHUzgrAU.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_uyGxlvak-Bg.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_dFVX_2UQ2WY.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_y9kk0ptXevk.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_k85EQoiLckw.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A man spin a girl who is blindfold and holds a bat to hit a piñata. Then, the girl swing the bat in the air, and in the second try she hits the piñata and break it. Candies fall from the piñata." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_3K_8CdJS9lE.mp4", "activitynet/videos/v_ymJTN8aKZEw.mp4", "activitynet/videos/v_rgAALWYnRrg.mp4", "activitynet/videos/v_Wgh8e4V8hBc.mp4", "activitynet/videos/v_iiqaJGokpEw.mp4" ]	3	<answer>3</answer>	[ 3 ]	true	1	13,164.366759	24	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man spin a girl who is blindfold and holds a bat to hit a piñata. Then, the girl swing the bat in the air, and in the second try she hits the piñata and break it. Candies fall from the piñata.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_3K_8CdJS9lE.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_ymJTN8aKZEw.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_rgAALWYnRrg.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_Wgh8e4V8hBc.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_iiqaJGokpEw.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A lady in short hair, wearing an orange top is standing by the kitchen counter, on the counter there are black pan, mayo, foil, plate, bread, knife. She spread the mayo on the bread, put cheese, on the black cutting board, beside the knife is a tomato, she put the tomato on the bread, put the cheese in the plastic bag, shows the sandwich, placed the other side of the bread on top of the sandwich. She moved to the stove, the black pan is on the stove, she put the butter using a bread knife, covered the kettle with foil, placed the bread on the pan and press it using the kettle with foil, she stood beside the stove while she waits, then turn over the bread, press the kettle with foil on it. She placed the bread on the plate, cut it and half, she is sitting on the green chair and started eating her sandwich." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_5JVHUcOW0GE.mp4", "activitynet/videos/v_jikOPvJPU-c.mp4", "activitynet/videos/v_ZTHsS5lQyvQ.mp4", "activitynet/videos/v_z0tiCqKa4cs.mp4", "activitynet/videos/v_EwYgRPVDQWQ.mp4" ]	2	<answer>2</answer>	[ 2 ]	true	1	25,144.143257	23	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A lady in short hair, wearing an orange top is standing by the kitchen counter, on the counter there are black pan, mayo, foil, plate, bread, knife. She spread the mayo on the bread, put cheese, on the black cutting board, beside the knife is a tomato, she put the tomato on the bread, put the cheese in the plastic bag, shows the sandwich, placed the other side of the bread on top of the sandwich. She moved to the stove, the black pan is on the stove, she put the butter using a bread knife, covered the kettle with foil, placed the bread on the pan and press it using the kettle with foil, she stood beside the stove while she waits, then turn over the bread, press the kettle with foil on it. She placed the bread on the plate, cut it and half, she is sitting on the green chair and started eating her sandwich.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_5JVHUcOW0GE.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_jikOPvJPU-c.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_ZTHsS5lQyvQ.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_z0tiCqKa4cs.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_EwYgRPVDQWQ.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A mother helps slide a boy in a playground. The boy walk away from the slide while the mother follow him, then the mother help slice the boy again. After, the boy walks away on the grass, while mother sits on a bench." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_Br1Ty6PCrv8.mp4", "activitynet/videos/v_5I0K3y27EUM.mp4", "activitynet/videos/v_q2KR3lzTrq4.mkv", "activitynet/videos/v__uKKSGTNJAY.mp4", "activitynet/videos/v_2SYTRqm4Ym4.mp4" ]	3	<answer>2</answer>	[ 2 ]	false	0	12,559.004449	26	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A mother helps slide a boy in a playground. The boy walk away from the slide while the mother follow him, then the mother help slice the boy again. After, the boy walks away on the grass, while mother sits on a bench.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_Br1Ty6PCrv8.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_5I0K3y27EUM.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_q2KR3lzTrq4.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v__uKKSGTNJAY.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_2SYTRqm4Ym4.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A man begins running down a track and doing several flips and tricks while many watch on the sides. He high fives another man and the same jumps are seen again in slow motion." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_DVXOr56dlKg.mp4", "activitynet/videos/v_5UlxCwq-LOs.mp4", "activitynet/videos/v_Rokj1EIAHHk.mp4", "activitynet/videos/v_FsS8cQbfKTQ.mp4", "activitynet/videos/v_fJ4xMCc5SKk.mp4" ]	5	<answer>4</answer>	[ 4 ]	false	0	20,835.868023	25	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man begins running down a track and doing several flips and tricks while many watch on the sides. He high fives another man and the same jumps are seen again in slow motion.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_DVXOr56dlKg.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_5UlxCwq-LOs.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_Rokj1EIAHHk.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_FsS8cQbfKTQ.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_fJ4xMCc5SKk.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "We see people dancing and light flashing in a club. The camera is tilted on its's side. A man spins a lady over and over. A man stops in front of the camera and shows the back of his shirt before turning to talk to the camera. The man spins the lady over and over and over." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_AXw2bkQyRPo.mp4", "activitynet/videos/v_V4U5SaPDL0E.mp4", "activitynet/videos/v_tY6UFSLtIoE.mp4", "activitynet/videos/v_CRzaKuaCXr8.mp4", "activitynet/videos/v_2imjxY43yYM.mkv" ]	3	<answer>3</answer>	[ 3 ]	true	1	12,228.129585	28	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"We see people dancing and light flashing in a club. The camera is tilted on its's side. A man spins a lady over and over. A man stops in front of the camera and shows the back of his shirt before turning to talk to the camera. The man spins the lady over and over and over.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_AXw2bkQyRPo.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_V4U5SaPDL0E.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_tY6UFSLtIoE.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_CRzaKuaCXr8.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_2imjxY43yYM.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A boy pushes a rake while riding a scooter down the driveway. It pushes the leaves in the driveway out to the road. He continues the pattern until the driveway is clean of debris." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_1rf7t4sYtIA.mp4", "activitynet/videos/v_oCicjtc1t9Y.mp4", "activitynet/videos/v_EvJqfGXb5Fo.mp4", "activitynet/videos/v_ll91M5topgU.mp4", "activitynet/videos/v_90vop6PS2Y0.mp4" ]	5	<answer>2</answer>	[ 2 ]	false	0	17,250.848063	27	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A boy pushes a rake while riding a scooter down the driveway. It pushes the leaves in the driveway out to the road. He continues the pattern until the driveway is clean of debris.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_1rf7t4sYtIA.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_oCicjtc1t9Y.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_EvJqfGXb5Fo.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_ll91M5topgU.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_90vop6PS2Y0.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A guy hold a shovel over his shoulder while recording himself. the camera then spins in a circle. the guy now scoops up some snow in the shovel picks it up then dumps it a couple of times. the guy use the shovel to clean the snow of the top of his bushes. finally the guy tosses his last snow he scooped up." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_fCLnOf-YjEI.mp4", "activitynet/videos/v_olBh9KMAHMQ.mp4", "activitynet/videos/v_bb9AIdvKkZU.mp4", "activitynet/videos/v_i1CVl-0-gJE.mp4", "activitynet/videos/v_a1WhnMcTbrY.mp4" ]	5	<answer>5</answer>	[ 5 ]	true	1	12,747.726318	29	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A guy hold a shovel over his shoulder while recording himself. the camera then spins in a circle. the guy now scoops up some snow in the shovel picks it up then dumps it a couple of times. the guy use the shovel to clean the snow of the top of his bushes. finally the guy tosses his last snow he scooped up.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_fCLnOf-YjEI.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_olBh9KMAHMQ.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_bb9AIdvKkZU.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_i1CVl-0-gJE.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_a1WhnMcTbrY.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A young girl is seen standing before a counter peeling potatoes with a peeler. The girl continues peeling while speaking to the camera and waving the potato all around her. The girl continues peeling while looking over and speaking to the camera." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_9PY28-zQhm4.mp4", "activitynet/videos/v_FNAt8Pew0HA.mp4", "activitynet/videos/v_57buK1yvKPk.mp4", "activitynet/videos/v_ux3h_qEusvw.mp4", "activitynet/videos/v_lgu-DBDWlEs.mp4" ]	3	<answer>2</answer>	[ 2 ]	false	0	13,339.34845	31	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A young girl is seen standing before a counter peeling potatoes with a peeler. The girl continues peeling while speaking to the camera and waving the potato all around her. The girl continues peeling while looking over and speaking to the camera.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_9PY28-zQhm4.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_FNAt8Pew0HA.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_57buK1yvKPk.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_ux3h_qEusvw.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_lgu-DBDWlEs.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A person extends their hands out towards the faucet. They turn on the faucet and wet their hands. The person pumps soap into their hands. The person scrubs their hands thoroughly with the soap. They extend the hand washing to their wrists. They turn on the faucet and rinse their hands and wrists. They extend their palms out in front of the faucet." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_e_0bMJEFiN8.mp4", "activitynet/videos/v_x44fn0snUvw.mp4", "activitynet/videos/v_sS-KyhAzeUY.mkv", "activitynet/videos/v_EwjDShmfFHM.mp4", "activitynet/videos/v_4Sf9C_vtYIs.mp4" ]	4	<answer>2</answer>	[ 2 ]	false	0	19,485.768545	30	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A person extends their hands out towards the faucet. They turn on the faucet and wet their hands. The person pumps soap into their hands. The person scrubs their hands thoroughly with the soap. They extend the hand washing to their wrists. They turn on the faucet and rinse their hands and wrists. They extend their palms out in front of the faucet.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_e_0bMJEFiN8.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_x44fn0snUvw.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_sS-KyhAzeUY.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_EwjDShmfFHM.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_4Sf9C_vtYIs.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A woman is seen pumping water out of a machine while another wheel kneels down in front and washes clothes. The people speak back and fourth to one another while the camera pans around and watches them work." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_G77y1JRjZDU.mp4", "activitynet/videos/v_L2FgftH2VD8.mp4", "activitynet/videos/v_optJ47P_5Ys.mp4", "activitynet/videos/v_gl_0jjJBUkc.mp4", "activitynet/videos/v_9RAW6QibWRs.mp4" ]	2	<answer>2</answer>	[ 2 ]	true	1	11,884.311192	33	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A woman is seen pumping water out of a machine while another wheel kneels down in front and washes clothes. The people speak back and fourth to one another while the camera pans around and watches them work.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_G77y1JRjZDU.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_L2FgftH2VD8.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_optJ47P_5Ys.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_gl_0jjJBUkc.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_9RAW6QibWRs.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A man shows to carve a pumpkin using a sharp tool. Then, the man carves a devil face in the pumpkin. Then, the woman puts a light inside the pumpkin and continues improving the carved pumpkin." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_z3xkE5Ox-2A.mp4", "activitynet/videos/v_YcjLd_XBK5Y.mp4", "activitynet/videos/v_ZVIi4lPU6h0.mp4", "activitynet/videos/v_1y2aqd5HQlU.mp4", "activitynet/videos/v_tJ2xOG_EWOg.mp4" ]	3	<answer>3</answer>	[ 3 ]	true	1	27,754.430307	32	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man shows to carve a pumpkin using a sharp tool. Then, the man carves a devil face in the pumpkin. Then, the woman puts a light inside the pumpkin and continues improving the carved pumpkin.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_z3xkE5Ox-2A.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_YcjLd_XBK5Y.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_ZVIi4lPU6h0.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_1y2aqd5HQlU.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_tJ2xOG_EWOg.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "People are sitting behind a desk talking. They start playing a game of curling. Two girls in purple are standing on the ice." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_9XmzbuByY_E.mp4", "activitynet/videos/v_RHtpBRwZ9hM.mp4", "activitynet/videos/v_Oa26_SgrY8w.mp4", "activitynet/videos/v_VAG6ECk5WYo.mp4", "activitynet/videos/v_D2TQ_RR2Q50.mp4" ]	2	<answer>4</answer>	[ 4 ]	false	0	16,463.658806	34	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"People are sitting behind a desk talking. They start playing a game of curling. Two girls in purple are standing on the ice.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_9XmzbuByY_E.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_RHtpBRwZ9hM.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_Oa26_SgrY8w.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_VAG6ECk5WYo.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_D2TQ_RR2Q50.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A woman is seen standing on a pink may while speaking to the camera. The woman then gets on knees and sits backwards. She looks forward while sitting up and does this several times while speaking to the camera." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_kCb2Km85Yn4.mp4", "activitynet/videos/v_wkSm7bUCgGQ.mp4", "activitynet/videos/v_GyBIC-DBoss.mp4", "activitynet/videos/v_zpBZ7HMNO34.mp4", "activitynet/videos/v_zYQ-WdosIwI.mp4" ]	5	<answer>5</answer>	[ 5 ]	true	1	27,831.313648	35	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A woman is seen standing on a pink may while speaking to the camera. The woman then gets on knees and sits backwards. She looks forward while sitting up and does this several times while speaking to the camera.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_kCb2Km85Yn4.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_wkSm7bUCgGQ.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_GyBIC-DBoss.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_zpBZ7HMNO34.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_zYQ-WdosIwI.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A man comes onto the screen and announces that he will show the viewers how to make a drink. He fills a cup with ice and pours all the ingredients into the glass. He takes a spoon and stirs it up. He takes out another glass and pours the drink into the new glass and places a straw into the drink." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_7NG6UrY2Foo.mp4", "activitynet/videos/v_E88Sr9H3Wi8.mp4", "activitynet/videos/v_yjazHd6a5SQ.mkv", "activitynet/videos/v_b1QkoG9hxk8.mp4", "activitynet/videos/v_PxGggNnMGtQ.mkv" ]	1	<answer>1</answer>	[ 1 ]	true	1	20,508.594909	36	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man comes onto the screen and announces that he will show the viewers how to make a drink. He fills a cup with ice and pours all the ingredients into the glass. He takes a spoon and stirs it up. He takes out another glass and pours the drink into the new glass and places a straw into the drink.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_7NG6UrY2Foo.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_E88Sr9H3Wi8.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_yjazHd6a5SQ.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_b1QkoG9hxk8.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_PxGggNnMGtQ.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A screen is shown playing video above a stage and leads into performers skating out on ice as well as hockey players behind them. The players all line up on the ice with one waving a flag and then begin skating around." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_STAvUAslEYM.mp4", "activitynet/videos/v_oD0RWEO8D1g.mp4", "activitynet/videos/v_JQavlg895jU.mp4", "activitynet/videos/v_AC9mml3mqps.mp4", "activitynet/videos/v_mjbzWcSeiwQ.mp4" ]	4	<answer>2</answer>	[ 2 ]	false	0	23,321.882361	37	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A screen is shown playing video above a stage and leads into performers skating out on ice as well as hockey players behind them. The players all line up on the ice with one waving a flag and then begin skating around.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_STAvUAslEYM.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_oD0RWEO8D1g.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_JQavlg895jU.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_AC9mml3mqps.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_mjbzWcSeiwQ.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A man is seen riding into frame on a lawn mower and looking at the camera. The man speaks to the camera until two more mowers appear and he begins riding around. He gives the camera a thumbs up while still riding around and stops to look at the camera." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_ZYwfvPJv4Rk.mp4", "activitynet/videos/v_puK4NxGKNdQ.mp4", "activitynet/videos/v_uJ_QCxMDfag.mp4", "activitynet/videos/v_86hyAYM5d3E.mp4", "activitynet/videos/v_GR6Ul2pD8_Y.mp4" ]	2	<answer>1</answer>	[ 1 ]	false	0	16,589.025418	39	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man is seen riding into frame on a lawn mower and looking at the camera. The man speaks to the camera until two more mowers appear and he begins riding around. He gives the camera a thumbs up while still riding around and stops to look at the camera.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_ZYwfvPJv4Rk.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_puK4NxGKNdQ.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_uJ_QCxMDfag.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_86hyAYM5d3E.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_GR6Ul2pD8_Y.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "Four males,three teenagers and a young boy are outside in a back yard playing croquet. As the boys take turns,only one ball goes through the arch as the other ones go in the grass and over the trees. When the ball comes back,two of the boys begin to play fight with their croquet. Suddenly,another boy has a large dodge ball like item that he hits and but then it hits the peg it is the actual ball. After,the real ball is hit from various locations,such as the clubhouse and trampoline until the end where their names are shown and credits are rolled." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_A0XGYLim9IU.mp4", "activitynet/videos/v_w7IeqGuuA7Q.mp4", "activitynet/videos/v_6VT2jBflMAM.mp4", "activitynet/videos/v_yVp99wxlW90.mp4", "activitynet/videos/v_vGcH8N8sJlM.mp4" ]	5	<answer>4</answer>	[ 4 ]	false	0	17,798.959397	40	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"Four males,three teenagers and a young boy are outside in a back yard playing croquet. As the boys take turns,only one ball goes through the arch as the other ones go in the grass and over the trees. When the ball comes back,two of the boys begin to play fight with their croquet. Suddenly,another boy has a large dodge ball like item that he hits and but then it hits the peg it is the actual ball. After,the real ball is hit from various locations,such as the clubhouse and trampoline until the end where their names are shown and credits are rolled.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_A0XGYLim9IU.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_w7IeqGuuA7Q.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_6VT2jBflMAM.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_yVp99wxlW90.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_vGcH8N8sJlM.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A man is bending over a hole in the ice, while another is trying to pull out his pole as he has caught something. He eventually pulls a large trout fish from the hole, holding it up for the camera. The men high five in celebration." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_qHRCGBIiNFg.mp4", "activitynet/videos/v_hUynCsek8I0.mp4", "activitynet/videos/v_TX8FGTL1flw.mp4", "activitynet/videos/v_FEqLmpNzxdg.mp4", "activitynet/videos/v_J8mSgO4r-kQ.mp4" ]	1	<answer>4</answer>	[ 4 ]	false	0	32,363.200881	38	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man is bending over a hole in the ice, while another is trying to pull out his pole as he has caught something. He eventually pulls a large trout fish from the hole, holding it up for the camera. The men high five in celebration.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_qHRCGBIiNFg.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_hUynCsek8I0.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_TX8FGTL1flw.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_FEqLmpNzxdg.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_J8mSgO4r-kQ.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "Students pedal stationary bikes in a classroom. A boy looks at a smart phone while pedaling a stationary bike, and other boys continue biking. A boy lowers his cap to cover his eyes. A girl pedals a bike while looking her smart phone." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_qiRrR2Nj2SQ.mp4", "activitynet/videos/v_D0pVkTEYQg8.mp4", "activitynet/videos/v_qhnWJ4G5JMA.mp4", "activitynet/videos/v_zb6WUBWwXfk.mp4", "activitynet/videos/v_Ck-9AHZNkq4.mp4" ]	5	<answer>5</answer>	[ 5 ]	true	1	12,519.178792	41	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"Students pedal stationary bikes in a classroom. A boy looks at a smart phone while pedaling a stationary bike, and other boys continue biking. A boy lowers his cap to cover his eyes. A girl pedals a bike while looking her smart phone.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_qiRrR2Nj2SQ.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_D0pVkTEYQg8.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_qhnWJ4G5JMA.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_zb6WUBWwXfk.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_Ck-9AHZNkq4.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "Clips are shown of a woman cutting a woman's hair while another speaks to the camera and he begins washing the hair. The man continues to cut and style the womans hair as he speaks to the camera with the host. He shows several different ways to style the hair and ends with the woman looking pleased." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_q6sLCLnTuik.mp4", "activitynet/videos/v_vmUbGiOyUbU.mp4", "activitynet/videos/v_uDmEOkAXTfo.mp4", "activitynet/videos/v_WqnnGmL-lmU.mp4", "activitynet/videos/v_sMITf5WBIxM.mp4" ]	4	<answer>4</answer>	[ 4 ]	true	1	17,040.870529	42	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"Clips are shown of a woman cutting a woman's hair while another speaks to the camera and he begins washing the hair. The man continues to cut and style the womans hair as he speaks to the camera with the host. He shows several different ways to style the hair and ends with the woman looking pleased.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_q6sLCLnTuik.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_vmUbGiOyUbU.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_uDmEOkAXTfo.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_WqnnGmL-lmU.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_sMITf5WBIxM.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "People are playing with a ball in the sand on the beach. A man dives for the ball and falls into the sand. The ball is shown on the sand." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_pLVCuSq560Y.mp4", "activitynet/videos/v_8fZbv6OUEm8.mp4", "activitynet/videos/v_Uc1_7BXtXZs.mp4", "activitynet/videos/v_4_wfCFTnExI.mp4", "activitynet/videos/v_bfk3xsTt0XA.mp4" ]	2	<answer>2</answer>	[ 2 ]	true	1	15,124.295168	43	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"People are playing with a ball in the sand on the beach. A man dives for the ball and falls into the sand. The ball is shown on the sand.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_pLVCuSq560Y.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_8fZbv6OUEm8.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_Uc1_7BXtXZs.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_4_wfCFTnExI.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_bfk3xsTt0XA.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "People are riding motocross bikes in the dirt and going off jumps. A man waves a white flag over the course." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_y1IjkACdnfs.mp4", "activitynet/videos/v_ZeBrPKBGb_k.mp4", "activitynet/videos/v_aTQaYDmcMDY.mp4", "activitynet/videos/v_ennVaOEePHk.mp4", "activitynet/videos/v_ZVNRQ_MPZAs.mkv" ]	3	<answer>3</answer>	[ 3 ]	true	1	36,037.562201	45	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"People are riding motocross bikes in the dirt and going off jumps. A man waves a white flag over the course.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_y1IjkACdnfs.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_ZeBrPKBGb_k.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_aTQaYDmcMDY.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_ennVaOEePHk.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_ZVNRQ_MPZAs.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A woman is seen waving to the camera and leads into her putting makeup all over her face. The woman continues putting makeup on all over her face and ends by smiling to the camera." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_LZEiFNEAyyw.mp4", "activitynet/videos/v_A8dBgZCuQow.mp4", "activitynet/videos/v_OYAyb_Ire24.mp4", "activitynet/videos/v_1RQ27XZKU1E.mp4", "activitynet/videos/v_2HmhRdKRVb4.mp4" ]	2	<answer>1</answer>	[ 1 ]	false	0	37,200.703209	46	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A woman is seen waving to the camera and leads into her putting makeup all over her face. The woman continues putting makeup on all over her face and ends by smiling to the camera.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_LZEiFNEAyyw.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_A8dBgZCuQow.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_OYAyb_Ire24.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_1RQ27XZKU1E.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_2HmhRdKRVb4.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "Two kids are crossing a slack line over a blue mat. A man in a red jacket holds a microphone. A man in a gray shirt is doing tricks on a slack line. People are seen standing in front of a stage." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_shBiO7aGy6k.mp4", "activitynet/videos/v_SSoHwNbASQQ.mp4", "activitynet/videos/v_2D22fVcAcyo.mp4", "activitynet/videos/v__Ew3g9PXhvo.mp4", "activitynet/videos/v_UTiSAR1o2nU.mp4" ]	3	<answer>2</answer>	[ 2 ]	false	0	52,181.858492	44	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"Two kids are crossing a slack line over a blue mat. A man in a red jacket holds a microphone. A man in a gray shirt is doing tricks on a slack line. People are seen standing in front of a stage.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_shBiO7aGy6k.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_SSoHwNbASQQ.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_2D22fVcAcyo.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v__Ew3g9PXhvo.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_UTiSAR1o2nU.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A man is kneeling down on grass. He is clipping the grass with large scissors. The man is wearing a yellow and red shirt." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>	[ "activitynet/videos/v_T_5ANYuDWOA.mp4", "activitynet/videos/v_fxbEiZrQQzM.mp4", "activitynet/videos/v_nezTU6Bq5hM.mp4", "activitynet/videos/v_VhzPqd0Su5I.mp4", "activitynet/videos/v_J4rzLO4u_pI.mp4" ]	3	<answer>3</answer>	[ 3 ]	true	1	20,614.693651	47	[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man is kneeling down on grass. He is clipping the grass with large scissors. The man is wearing a yellow and red shirt.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_T_5ANYuDWOA.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_fxbEiZrQQzM.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_nezTU6Bq5hM.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_VhzPqd0Su5I.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_J4rzLO4u_pI.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A weight lifting tutorial is given. The coach helps the guy in red with the proper body placement and lifting technique." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_eVTMUEYhwDE.mp4", "activitynet/videos/v_NpBZn7OHUKo.mp4", "activitynet/videos/v_uqiMw7tQ1Cc.mp4", "activitynet/videos/v_gIhVeU8xbrs.mp4", "activitynet/videos/v_1epGZvRN3Fw.mp4" ]

3

[ 1 ]

false

0

25,768.688315

0

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A weight lifting tutorial is given. The coach helps the guy in red with the proper body placement and lifting technique.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_eVTMUEYhwDE.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_NpBZn7OHUKo.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_uqiMw7tQ1Cc.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_gIhVeU8xbrs.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_1epGZvRN3Fw.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A man is seen speaking to the camera and pans out into more men standing behind him. The first man then begins performing martial arts moves while speaking to he camera. He continues moving around and looking to the camera." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_HktZZPJMU8s.mp4", "activitynet/videos/v_1imA9vLRd3k.mkv", "activitynet/videos/v_LmioUbGNv04.mp4", "activitynet/videos/v_bXdq2zI1Ms0.mp4", "activitynet/videos/v_6LLDsbc8XMM.mp4" ]

4

[ 3 ]

false

0

33,041.859635

1

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man is seen speaking to the camera and pans out into more men standing behind him. The first man then begins performing martial arts moves while speaking to he camera. He continues moving around and looking to the camera.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_HktZZPJMU8s.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_1imA9vLRd3k.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_LmioUbGNv04.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_bXdq2zI1Ms0.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_6LLDsbc8XMM.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "Several shots of boats are shown riding around as well as people riding on the boats and speaking to one another. Several shots are then shown of people sitting on the water as well as life under the water. The camera pans around old cars under water as well as people in the area." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_FsS_NCZEfaI.mp4", "activitynet/videos/v_FX4inHmWQtE.mp4", "activitynet/videos/v_sxQbiXWFdKs.mp4", "activitynet/videos/v_3TNDCTlLlGk.mkv", "activitynet/videos/v_sG3JpMuXFnU.mp4" ]

1

[ 2 ]

false

0

38,336.422621

2

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"Several shots of boats are shown riding around as well as people riding on the boats and speaking to one another. Several shots are then shown of people sitting on the water as well as life under the water. The camera pans around old cars under water as well as people in the area.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_FsS_NCZEfaI.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_FX4inHmWQtE.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_sxQbiXWFdKs.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_3TNDCTlLlGk.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_sG3JpMuXFnU.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A woman is seen speaking to the camera while holding an accordion and and moving her hands around. She demonstrates how to play the instrument while still speaking to the camera and moving all around." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_Rho3u46ZIEE.mp4", "activitynet/videos/v_KzZlSbM16aY.mp4", "activitynet/videos/v_K6Tm5xHkJ5c.mp4", "activitynet/videos/v_t1-GV2bAL4I.mp4", "activitynet/videos/v_91XkPU8A5hs.mp4" ]

3

[ 3 ]

true

1

22,048.000755

3

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A woman is seen speaking to the camera while holding an accordion and and moving her hands around. She demonstrates how to play the instrument while still speaking to the camera and moving all around.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_Rho3u46ZIEE.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_KzZlSbM16aY.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_K6Tm5xHkJ5c.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_t1-GV2bAL4I.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_91XkPU8A5hs.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "There are some people including small children near a soccer field. A small boy is playing by himself a he stands on a large square tile. A man dressed in a blue shirt come running towards him and points out his finger, indicating to the boy to go there. The boy gets off the tile and walks to another tile. Then another little boy wearing a gray shirt comes to that tile and begins playing. The other little boy moves away to another tile. There are some man playing with small children on the lawn. The little boy comes running towards some children and his father follows him." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_msiX-xky6Ac.mp4", "activitynet/videos/v_Ty0BvWyYPVA.mp4", "activitynet/videos/v_pgff9mC5y3s.mp4", "activitynet/videos/v_4Lu8ECLHvK4.mp4", "activitynet/videos/v_f6j6lb0AaxM.mp4" ]

4

[ 4 ]

true

1

18,662.458615

4

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"There are some people including small children near a soccer field. A small boy is playing by himself a he stands on a large square tile. A man dressed in a blue shirt come running towards him and points out his finger, indicating to the boy to go there. The boy gets off the tile and walks to another tile. Then another little boy wearing a gray shirt comes to that tile and begins playing. The other little boy moves away to another tile. There are some man playing with small children on the lawn. The little boy comes running towards some children and his father follows him.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_msiX-xky6Ac.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_Ty0BvWyYPVA.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_pgff9mC5y3s.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_4Lu8ECLHvK4.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_f6j6lb0AaxM.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "People are dancing having fun at a party. A race starts and people are running. Cheerleaders are standing on the side of the road. People are dancing on the grass." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_iA2Q4t-o58w.mp4", "activitynet/videos/v_dJ0kxnyVzFI.mp4", "activitynet/videos/v_bG7hnpAeja0.mp4", "activitynet/videos/v_HWV_ccmZVPA.mp4", "activitynet/videos/v_fG0nn2IVdDM.mp4" ]

4

[ 4 ]

true

1

16,536.044198

5

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"People are dancing having fun at a party. A race starts and people are running. Cheerleaders are standing on the side of the road. People are dancing on the grass.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_iA2Q4t-o58w.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_dJ0kxnyVzFI.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_bG7hnpAeja0.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_HWV_ccmZVPA.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_fG0nn2IVdDM.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A female weight lifter bends at the knees. She lifts a barbell to her chest. She then lifts it over her head before dropping it heavily to the ground." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_i1PpX1IOcIs.mp4", "activitynet/videos/v_GGSY1Qvo990.mp4", "activitynet/videos/v_j9QPrMZuegY.mp4", "activitynet/videos/v_PJysE5c1WDs.mp4", "activitynet/videos/v_aDaazrgvjJg.mp4" ]

2

[ 2 ]

true

1

9,994.998532

6

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A female weight lifter bends at the knees. She lifts a barbell to her chest. She then lifts it over her head before dropping it heavily to the ground.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_i1PpX1IOcIs.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_GGSY1Qvo990.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_j9QPrMZuegY.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_PJysE5c1WDs.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_aDaazrgvjJg.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A large kid playground slide is shown. Several people slide down, a woman and her little girl." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_yj2WJBqmEHk.mp4", "activitynet/videos/v__uKKSGTNJAY.mp4", "activitynet/videos/v_5I0K3y27EUM.mp4", "activitynet/videos/v_JTrwGfPJNzU.mp4", "activitynet/videos/v_hghdjiQlYko.mp4" ]

4

[ 1 ]

false

0

10,312.377371

8

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A large kid playground slide is shown. Several people slide down, a woman and her little girl.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_yj2WJBqmEHk.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v__uKKSGTNJAY.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_5I0K3y27EUM.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_JTrwGfPJNzU.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_hghdjiQlYko.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A guy puts a black cat on the kitchen floor. The guy reaches for a scissor and sits next to the cat. The guy carries the cat. The guy uses the scissor to cut the cat's claws. The guy puts the clippings in his palm. The guy pets the cat and puts the cat on the floor. The guy gets up and trashes the clippings. The owner and pet exit the kitchen." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_qaB0igbuKuQ.mp4", "activitynet/videos/v_tfPm9xAZ5z0.mp4", "activitynet/videos/v_xOmfJGR5fBw.mp4", "activitynet/videos/v_frePM0YGtQE.mp4", "activitynet/videos/v_U36rsW_WhUA.mp4" ]

4

[ 4 ]

true

1

20,151.516695

7

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A guy puts a black cat on the kitchen floor. The guy reaches for a scissor and sits next to the cat. The guy carries the cat. The guy uses the scissor to cut the cat's claws. The guy puts the clippings in his palm. The guy pets the cat and puts the cat on the floor. The guy gets up and trashes the clippings. The owner and pet exit the kitchen.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_qaB0igbuKuQ.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_tfPm9xAZ5z0.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_xOmfJGR5fBw.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_frePM0YGtQE.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_U36rsW_WhUA.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A woman is seen kneeling down next to a man. Another person is seen kneeling nearby. The man pans closely around the man." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_s1YjWVUu6pM.mp4", "activitynet/videos/v_YZvdzvM-124.mp4", "activitynet/videos/v_lfllVwgOWBk.mp4", "activitynet/videos/v_gOniW-yEZ0k.mp4", "activitynet/videos/v_5BbHu0WQZqw.mp4" ]

4

[ 1 ]

false

0

15,749.863021

9

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A woman is seen kneeling down next to a man. Another person is seen kneeling nearby. The man pans closely around the man.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_s1YjWVUu6pM.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_YZvdzvM-124.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_lfllVwgOWBk.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_gOniW-yEZ0k.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_5BbHu0WQZqw.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A chef is talking inside a kitchen as he fills a pan with frying oil and water. He boils pasta noodles in a pot. He then tastes the noodles when they are done." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_rwxSphRRIL8.mp4", "activitynet/videos/v_kbe4iowYMqM.mp4", "activitynet/videos/v_3j2d27w3x5Q.mp4", "activitynet/videos/v_RKDjetk5Kko.mp4", "activitynet/videos/v_Po8gmt7hVTY.mkv" ]

5

[ 1 ]

false

0

18,145.284797

12

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A chef is talking inside a kitchen as he fills a pan with frying oil and water. He boils pasta noodles in a pot. He then tastes the noodles when they are done.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_rwxSphRRIL8.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_kbe4iowYMqM.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_3j2d27w3x5Q.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_RKDjetk5Kko.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_Po8gmt7hVTY.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A man is sitting in a chair getting a tattoo. He stands up and yells at the man tattooing. A woman in a pink shirt is sitting in front of him. He walks out the door of the shop and walks down the street." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_smh90DBXsBg.mp4", "activitynet/videos/v_HtkuvF7VbSQ.mp4", "activitynet/videos/v_aPEqCGdCsp0.mp4", "activitynet/videos/v_qm8sJxsZ5VY.mp4", "activitynet/videos/v_j05b3qqgRxw.mp4" ]

2

[ 2 ]

true

1

26,017.51495

11

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man is sitting in a chair getting a tattoo. He stands up and yells at the man tattooing. A woman in a pink shirt is sitting in front of him. He walks out the door of the shop and walks down the street.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_smh90DBXsBg.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_HtkuvF7VbSQ.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_aPEqCGdCsp0.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_qm8sJxsZ5VY.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_j05b3qqgRxw.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "Two girls are outside in bathing suits cleaning the front of a green vehicle. One of the girl then walks away and goes to get something from a man cleaning the motorcycle. They continue to wash the vehicle and then the girls walks over and grabs the water hose. She comes back to rinse the vehicle and then holds it up to the girl's head and washes her hair." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_6czh95dpwAA.mp4", "activitynet/videos/v_yACg55C3IlM.mkv", "activitynet/videos/v_iSH43hQoxio.mp4", "activitynet/videos/v_Lwy92HbuZII.mkv", "activitynet/videos/v_XoFikALe8Q0.mp4" ]

2

[ 2 ]

true

1

16,336.017989

13

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"Two girls are outside in bathing suits cleaning the front of a green vehicle. One of the girl then walks away and goes to get something from a man cleaning the motorcycle. They continue to wash the vehicle and then the girls walks over and grabs the water hose. She comes back to rinse the vehicle and then holds it up to the girl's head and washes her hair.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_6czh95dpwAA.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_yACg55C3IlM.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_iSH43hQoxio.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_Lwy92HbuZII.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_XoFikALe8Q0.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "Three scuba divers are seen moving along the water with one giving a thumbs up to the camera and the camera panning all around the ocean. Several shots are shown of the divers taking pictures under the water as well as taking off their mask and waving to the camera. In the end the divers come to the surface." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_zGTqXydTuQs.mp4", "activitynet/videos/v_ijgLl3PHHE0.mp4", "activitynet/videos/v_W30cufYc_ZI.mp4", "activitynet/videos/v_cHYZPYLwvks.mp4", "activitynet/videos/v_FsS_NCZEfaI.mp4" ]

4

[ 2 ]

false

0

58,379.563186

10

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"Three scuba divers are seen moving along the water with one giving a thumbs up to the camera and the camera panning all around the ocean. Several shots are shown of the divers taking pictures under the water as well as taking off their mask and waving to the camera. In the end the divers come to the surface.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_zGTqXydTuQs.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_ijgLl3PHHE0.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_W30cufYc_ZI.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_cHYZPYLwvks.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_FsS_NCZEfaI.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A man is seen pushing a lawn mower across a lawn to cut the grass. The man continues moving the machine all along the yard while the camera captures his movements." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_iHO42zwYsu0.mp4", "activitynet/videos/v_CjPN7fw0B48.mp4", "activitynet/videos/v_E9R1H8xRIW8.mp4", "activitynet/videos/v_z1tV0-C3IBw.mp4", "activitynet/videos/v_CJWSed5v4jE.mkv" ]

3

[ 1 ]

false

0

32,191.08578

14

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man is seen pushing a lawn mower across a lawn to cut the grass. The man continues moving the machine all along the yard while the camera captures his movements.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_iHO42zwYsu0.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_CjPN7fw0B48.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_E9R1H8xRIW8.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_z1tV0-C3IBw.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_CJWSed5v4jE.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A wrestler is seen walking out in front of an audience and sitting on the floor. Two men are then seen walking out onto a pit with one throwing dirt and kneeling down. The men begin fighting with one pushing another out and leads into several more clips of the men wrestling." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_UqU_mAjgknQ.mp4", "activitynet/videos/v_-wXbBZDSIa8.mp4", "activitynet/videos/v_eFbZ0_TJLE0.mkv", "activitynet/videos/v_5qsXmDi8d74.mp4", "activitynet/videos/v_0zjA3KPnLK8.mp4" ]

4

[ 2 ]

false

0

14,964.81331

16

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A wrestler is seen walking out in front of an audience and sitting on the floor. Two men are then seen walking out onto a pit with one throwing dirt and kneeling down. The men begin fighting with one pushing another out and leads into several more clips of the men wrestling.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_UqU_mAjgknQ.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_-wXbBZDSIa8.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_eFbZ0_TJLE0.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_5qsXmDi8d74.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_0zjA3KPnLK8.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A man is seen sitting in front of a bucket holding clothes in his hands. Another person is seen sitting next to him sticking his hand in a bucket. The men continue washing clothes next to one another while dipping them into a bucket." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_ByF8Pg3xXNA.mp4", "activitynet/videos/v_4OeZViscNp4.mp4", "activitynet/videos/v_k3oPZS_Id3M.mp4", "activitynet/videos/v_V1SEaTS9hos.mp4", "activitynet/videos/v_9RAW6QibWRs.mp4" ]

4

[ 5 ]

false

0

30,399.536214

15

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man is seen sitting in front of a bucket holding clothes in his hands. Another person is seen sitting next to him sticking his hand in a bucket. The men continue washing clothes next to one another while dipping them into a bucket.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_ByF8Pg3xXNA.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_4OeZViscNp4.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_k3oPZS_Id3M.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_V1SEaTS9hos.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_9RAW6QibWRs.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A man is kneeling on the kitchen floor. He is using a bucket of paints and a canvas. He uses the paints to create an image on the canvas." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_WzDnorAzWVU.mp4", "activitynet/videos/v_sEGceBU8icE.mp4", "activitynet/videos/v_nB90Q8sTBgE.mp4", "activitynet/videos/v_ng14GLT_hHQ.mp4", "activitynet/videos/v_1UgjxeAPq_A.mp4" ]

4

[ 4 ]

true

1

20,734.282649

17

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man is kneeling on the kitchen floor. He is using a bucket of paints and a canvas. He uses the paints to create an image on the canvas.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_WzDnorAzWVU.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_sEGceBU8icE.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_nB90Q8sTBgE.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_ng14GLT_hHQ.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_1UgjxeAPq_A.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A girl is seen standing near a piece of exercise equipment talking a man. She continues speaking to him and has him watch her while she steps on the machine. She rides the bike moving back and fourth speaking to the man and switches places with the man." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_cROJALtLB1k.mp4", "activitynet/videos/v_nGABbRHJ2Ug.mp4", "activitynet/videos/v__MR8G1jwM4o.mp4", "activitynet/videos/v_f4CSejhkTd8.mp4", "activitynet/videos/v_E50qKeeMbgU.mp4" ]

2

[ 2 ]

true

1

13,990.917447

19

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A girl is seen standing near a piece of exercise equipment talking a man. She continues speaking to him and has him watch her while she steps on the machine. She rides the bike moving back and fourth speaking to the man and switches places with the man.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_cROJALtLB1k.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_nGABbRHJ2Ug.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v__MR8G1jwM4o.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_f4CSejhkTd8.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_E50qKeeMbgU.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "The camera is showing an arc welder in a shop. A man approaches the arc welder and begins using it to weld some metal bars. The man shows the metal bar to the camera. The man sets the bar down and begins welding it again." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_wPYr19iFxhw.mp4", "activitynet/videos/v_CfDdbeAk8LE.mp4", "activitynet/videos/v_XQaaA2UZYh8.mp4", "activitynet/videos/v_7JXae2so5-E.mp4", "activitynet/videos/v_GcE-0A4Titg.mp4" ]

1

[ 1 ]

true

1

14,183.498107

18

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"The camera is showing an arc welder in a shop. A man approaches the arc welder and begins using it to weld some metal bars. The man shows the metal bar to the camera. The man sets the bar down and begins welding it again.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_wPYr19iFxhw.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_CfDdbeAk8LE.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_XQaaA2UZYh8.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_7JXae2so5-E.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_GcE-0A4Titg.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A guy exercises on a stationary bike. The guy has his hand on the handles. The guy lets go of the handles and puts his hands to his side." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_arnKDX_ToxE.mp4", "activitynet/videos/v_8-QcL1k5n6k.mp4", "activitynet/videos/v_D0pVkTEYQg8.mp4", "activitynet/videos/v_tnt6Wpv_kHc.mp4", "activitynet/videos/v_c4ctwOucndQ.mp4" ]

3

[ 3 ]

true

1

11,617.518422

20

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A guy exercises on a stationary bike. The guy has his hand on the handles. The guy lets go of the handles and puts his hands to his side.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_arnKDX_ToxE.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_8-QcL1k5n6k.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_D0pVkTEYQg8.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_tnt6Wpv_kHc.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_c4ctwOucndQ.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A man is looking at a red vase. A woman takes her shirt off. The two begin fighting with swords." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_4OCbTYrThtc.mkv", "activitynet/videos/v_Fdzw3niNDYY.mp4", "activitynet/videos/v_tjEMbP2SODQ.mp4", "activitynet/videos/v_LUDZ7e0RdEE.mp4", "activitynet/videos/v_2icoQWmbocU.mp4" ]

2

[ 4 ]

false

0

14,144.183129

22

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man is looking at a red vase. A woman takes her shirt off. The two begin fighting with swords.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_4OCbTYrThtc.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_Fdzw3niNDYY.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_tjEMbP2SODQ.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_LUDZ7e0RdEE.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_2icoQWmbocU.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "We see an opening title screen. A pair of red boots sit on a table. A lady talks and pours soap in a glass then wipes the boots with the soap. The lady talks and shows a bottle of olive oil. We see the closing title screen." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_od1jHUzgrAU.mp4", "activitynet/videos/v_uyGxlvak-Bg.mkv", "activitynet/videos/v_dFVX_2UQ2WY.mp4", "activitynet/videos/v_y9kk0ptXevk.mp4", "activitynet/videos/v_k85EQoiLckw.mp4" ]

4

[ 4 ]

true

1

26,904.119644

21

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"We see an opening title screen. A pair of red boots sit on a table. A lady talks and pours soap in a glass then wipes the boots with the soap. The lady talks and shows a bottle of olive oil. We see the closing title screen.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_od1jHUzgrAU.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_uyGxlvak-Bg.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_dFVX_2UQ2WY.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_y9kk0ptXevk.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_k85EQoiLckw.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A man spin a girl who is blindfold and holds a bat to hit a piñata. Then, the girl swing the bat in the air, and in the second try she hits the piñata and break it. Candies fall from the piñata." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_3K_8CdJS9lE.mp4", "activitynet/videos/v_ymJTN8aKZEw.mp4", "activitynet/videos/v_rgAALWYnRrg.mp4", "activitynet/videos/v_Wgh8e4V8hBc.mp4", "activitynet/videos/v_iiqaJGokpEw.mp4" ]

3

[ 3 ]

true

1

13,164.366759

24

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man spin a girl who is blindfold and holds a bat to hit a piñata. Then, the girl swing the bat in the air, and in the second try she hits the piñata and break it. Candies fall from the piñata.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_3K_8CdJS9lE.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_ymJTN8aKZEw.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_rgAALWYnRrg.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_Wgh8e4V8hBc.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_iiqaJGokpEw.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A lady in short hair, wearing an orange top is standing by the kitchen counter, on the counter there are black pan, mayo, foil, plate, bread, knife. She spread the mayo on the bread, put cheese, on the black cutting board, beside the knife is a tomato, she put the tomato on the bread, put the cheese in the plastic bag, shows the sandwich, placed the other side of the bread on top of the sandwich. She moved to the stove, the black pan is on the stove, she put the butter using a bread knife, covered the kettle with foil, placed the bread on the pan and press it using the kettle with foil, she stood beside the stove while she waits, then turn over the bread, press the kettle with foil on it. She placed the bread on the plate, cut it and half, she is sitting on the green chair and started eating her sandwich." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_5JVHUcOW0GE.mp4", "activitynet/videos/v_jikOPvJPU-c.mp4", "activitynet/videos/v_ZTHsS5lQyvQ.mp4", "activitynet/videos/v_z0tiCqKa4cs.mp4", "activitynet/videos/v_EwYgRPVDQWQ.mp4" ]

2

[ 2 ]

true

1

25,144.143257

23

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A lady in short hair, wearing an orange top is standing by the kitchen counter, on the counter there are black pan, mayo, foil, plate, bread, knife. She spread the mayo on the bread, put cheese, on the black cutting board, beside the knife is a tomato, she put the tomato on the bread, put the cheese in the plastic bag, shows the sandwich, placed the other side of the bread on top of the sandwich. She moved to the stove, the black pan is on the stove, she put the butter using a bread knife, covered the kettle with foil, placed the bread on the pan and press it using the kettle with foil, she stood beside the stove while she waits, then turn over the bread, press the kettle with foil on it. She placed the bread on the plate, cut it and half, she is sitting on the green chair and started eating her sandwich.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_5JVHUcOW0GE.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_jikOPvJPU-c.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_ZTHsS5lQyvQ.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_z0tiCqKa4cs.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_EwYgRPVDQWQ.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A mother helps slide a boy in a playground. The boy walk away from the slide while the mother follow him, then the mother help slice the boy again. After, the boy walks away on the grass, while mother sits on a bench." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_Br1Ty6PCrv8.mp4", "activitynet/videos/v_5I0K3y27EUM.mp4", "activitynet/videos/v_q2KR3lzTrq4.mkv", "activitynet/videos/v__uKKSGTNJAY.mp4", "activitynet/videos/v_2SYTRqm4Ym4.mp4" ]

3

[ 2 ]

false

0

12,559.004449

26

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A mother helps slide a boy in a playground. The boy walk away from the slide while the mother follow him, then the mother help slice the boy again. After, the boy walks away on the grass, while mother sits on a bench.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_Br1Ty6PCrv8.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_5I0K3y27EUM.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_q2KR3lzTrq4.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v__uKKSGTNJAY.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_2SYTRqm4Ym4.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A man begins running down a track and doing several flips and tricks while many watch on the sides. He high fives another man and the same jumps are seen again in slow motion." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_DVXOr56dlKg.mp4", "activitynet/videos/v_5UlxCwq-LOs.mp4", "activitynet/videos/v_Rokj1EIAHHk.mp4", "activitynet/videos/v_FsS8cQbfKTQ.mp4", "activitynet/videos/v_fJ4xMCc5SKk.mp4" ]

5

[ 4 ]

false

0

20,835.868023

25

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man begins running down a track and doing several flips and tricks while many watch on the sides. He high fives another man and the same jumps are seen again in slow motion.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_DVXOr56dlKg.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_5UlxCwq-LOs.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_Rokj1EIAHHk.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_FsS8cQbfKTQ.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_fJ4xMCc5SKk.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "We see people dancing and light flashing in a club. The camera is tilted on its's side. A man spins a lady over and over. A man stops in front of the camera and shows the back of his shirt before turning to talk to the camera. The man spins the lady over and over and over." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_AXw2bkQyRPo.mp4", "activitynet/videos/v_V4U5SaPDL0E.mp4", "activitynet/videos/v_tY6UFSLtIoE.mp4", "activitynet/videos/v_CRzaKuaCXr8.mp4", "activitynet/videos/v_2imjxY43yYM.mkv" ]

3

[ 3 ]

true

1

12,228.129585

28

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"We see people dancing and light flashing in a club. The camera is tilted on its's side. A man spins a lady over and over. A man stops in front of the camera and shows the back of his shirt before turning to talk to the camera. The man spins the lady over and over and over.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_AXw2bkQyRPo.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_V4U5SaPDL0E.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_tY6UFSLtIoE.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_CRzaKuaCXr8.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_2imjxY43yYM.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A boy pushes a rake while riding a scooter down the driveway. It pushes the leaves in the driveway out to the road. He continues the pattern until the driveway is clean of debris." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_1rf7t4sYtIA.mp4", "activitynet/videos/v_oCicjtc1t9Y.mp4", "activitynet/videos/v_EvJqfGXb5Fo.mp4", "activitynet/videos/v_ll91M5topgU.mp4", "activitynet/videos/v_90vop6PS2Y0.mp4" ]

5

[ 2 ]

false

0

17,250.848063

27

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A boy pushes a rake while riding a scooter down the driveway. It pushes the leaves in the driveway out to the road. He continues the pattern until the driveway is clean of debris.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_1rf7t4sYtIA.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_oCicjtc1t9Y.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_EvJqfGXb5Fo.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_ll91M5topgU.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_90vop6PS2Y0.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A guy hold a shovel over his shoulder while recording himself. the camera then spins in a circle. the guy now scoops up some snow in the shovel picks it up then dumps it a couple of times. the guy use the shovel to clean the snow of the top of his bushes. finally the guy tosses his last snow he scooped up." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_fCLnOf-YjEI.mp4", "activitynet/videos/v_olBh9KMAHMQ.mp4", "activitynet/videos/v_bb9AIdvKkZU.mp4", "activitynet/videos/v_i1CVl-0-gJE.mp4", "activitynet/videos/v_a1WhnMcTbrY.mp4" ]

5

[ 5 ]

true

1

12,747.726318

29

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A guy hold a shovel over his shoulder while recording himself. the camera then spins in a circle. the guy now scoops up some snow in the shovel picks it up then dumps it a couple of times. the guy use the shovel to clean the snow of the top of his bushes. finally the guy tosses his last snow he scooped up.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_fCLnOf-YjEI.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_olBh9KMAHMQ.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_bb9AIdvKkZU.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_i1CVl-0-gJE.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_a1WhnMcTbrY.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A young girl is seen standing before a counter peeling potatoes with a peeler. The girl continues peeling while speaking to the camera and waving the potato all around her. The girl continues peeling while looking over and speaking to the camera." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_9PY28-zQhm4.mp4", "activitynet/videos/v_FNAt8Pew0HA.mp4", "activitynet/videos/v_57buK1yvKPk.mp4", "activitynet/videos/v_ux3h_qEusvw.mp4", "activitynet/videos/v_lgu-DBDWlEs.mp4" ]

3

[ 2 ]

false

0

13,339.34845

31

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A young girl is seen standing before a counter peeling potatoes with a peeler. The girl continues peeling while speaking to the camera and waving the potato all around her. The girl continues peeling while looking over and speaking to the camera.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_9PY28-zQhm4.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_FNAt8Pew0HA.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_57buK1yvKPk.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_ux3h_qEusvw.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_lgu-DBDWlEs.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A person extends their hands out towards the faucet. They turn on the faucet and wet their hands. The person pumps soap into their hands. The person scrubs their hands thoroughly with the soap. They extend the hand washing to their wrists. They turn on the faucet and rinse their hands and wrists. They extend their palms out in front of the faucet." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_e_0bMJEFiN8.mp4", "activitynet/videos/v_x44fn0snUvw.mp4", "activitynet/videos/v_sS-KyhAzeUY.mkv", "activitynet/videos/v_EwjDShmfFHM.mp4", "activitynet/videos/v_4Sf9C_vtYIs.mp4" ]

4

[ 2 ]

false

0

19,485.768545

30

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A person extends their hands out towards the faucet. They turn on the faucet and wet their hands. The person pumps soap into their hands. The person scrubs their hands thoroughly with the soap. They extend the hand washing to their wrists. They turn on the faucet and rinse their hands and wrists. They extend their palms out in front of the faucet.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_e_0bMJEFiN8.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_x44fn0snUvw.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_sS-KyhAzeUY.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_EwjDShmfFHM.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_4Sf9C_vtYIs.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A woman is seen pumping water out of a machine while another wheel kneels down in front and washes clothes. The people speak back and fourth to one another while the camera pans around and watches them work." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_G77y1JRjZDU.mp4", "activitynet/videos/v_L2FgftH2VD8.mp4", "activitynet/videos/v_optJ47P_5Ys.mp4", "activitynet/videos/v_gl_0jjJBUkc.mp4", "activitynet/videos/v_9RAW6QibWRs.mp4" ]

2

[ 2 ]

true

1

11,884.311192

33

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A woman is seen pumping water out of a machine while another wheel kneels down in front and washes clothes. The people speak back and fourth to one another while the camera pans around and watches them work.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_G77y1JRjZDU.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_L2FgftH2VD8.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_optJ47P_5Ys.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_gl_0jjJBUkc.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_9RAW6QibWRs.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A man shows to carve a pumpkin using a sharp tool. Then, the man carves a devil face in the pumpkin. Then, the woman puts a light inside the pumpkin and continues improving the carved pumpkin." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_z3xkE5Ox-2A.mp4", "activitynet/videos/v_YcjLd_XBK5Y.mp4", "activitynet/videos/v_ZVIi4lPU6h0.mp4", "activitynet/videos/v_1y2aqd5HQlU.mp4", "activitynet/videos/v_tJ2xOG_EWOg.mp4" ]

3

[ 3 ]

true

1

27,754.430307

32

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man shows to carve a pumpkin using a sharp tool. Then, the man carves a devil face in the pumpkin. Then, the woman puts a light inside the pumpkin and continues improving the carved pumpkin.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_z3xkE5Ox-2A.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_YcjLd_XBK5Y.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_ZVIi4lPU6h0.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_1y2aqd5HQlU.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_tJ2xOG_EWOg.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "People are sitting behind a desk talking. They start playing a game of curling. Two girls in purple are standing on the ice." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_9XmzbuByY_E.mp4", "activitynet/videos/v_RHtpBRwZ9hM.mp4", "activitynet/videos/v_Oa26_SgrY8w.mp4", "activitynet/videos/v_VAG6ECk5WYo.mp4", "activitynet/videos/v_D2TQ_RR2Q50.mp4" ]

2

[ 4 ]

false

0

16,463.658806

34

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"People are sitting behind a desk talking. They start playing a game of curling. Two girls in purple are standing on the ice.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_9XmzbuByY_E.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_RHtpBRwZ9hM.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_Oa26_SgrY8w.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_VAG6ECk5WYo.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_D2TQ_RR2Q50.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A woman is seen standing on a pink may while speaking to the camera. The woman then gets on knees and sits backwards. She looks forward while sitting up and does this several times while speaking to the camera." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_kCb2Km85Yn4.mp4", "activitynet/videos/v_wkSm7bUCgGQ.mp4", "activitynet/videos/v_GyBIC-DBoss.mp4", "activitynet/videos/v_zpBZ7HMNO34.mp4", "activitynet/videos/v_zYQ-WdosIwI.mp4" ]

5

[ 5 ]

true

1

27,831.313648

35

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A woman is seen standing on a pink may while speaking to the camera. The woman then gets on knees and sits backwards. She looks forward while sitting up and does this several times while speaking to the camera.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_kCb2Km85Yn4.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_wkSm7bUCgGQ.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_GyBIC-DBoss.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_zpBZ7HMNO34.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_zYQ-WdosIwI.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A man comes onto the screen and announces that he will show the viewers how to make a drink. He fills a cup with ice and pours all the ingredients into the glass. He takes a spoon and stirs it up. He takes out another glass and pours the drink into the new glass and places a straw into the drink." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_7NG6UrY2Foo.mp4", "activitynet/videos/v_E88Sr9H3Wi8.mp4", "activitynet/videos/v_yjazHd6a5SQ.mkv", "activitynet/videos/v_b1QkoG9hxk8.mp4", "activitynet/videos/v_PxGggNnMGtQ.mkv" ]

1

[ 1 ]

true

1

20,508.594909

36

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man comes onto the screen and announces that he will show the viewers how to make a drink. He fills a cup with ice and pours all the ingredients into the glass. He takes a spoon and stirs it up. He takes out another glass and pours the drink into the new glass and places a straw into the drink.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_7NG6UrY2Foo.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_E88Sr9H3Wi8.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_yjazHd6a5SQ.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_b1QkoG9hxk8.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_PxGggNnMGtQ.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A screen is shown playing video above a stage and leads into performers skating out on ice as well as hockey players behind them. The players all line up on the ice with one waving a flag and then begin skating around." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_STAvUAslEYM.mp4", "activitynet/videos/v_oD0RWEO8D1g.mp4", "activitynet/videos/v_JQavlg895jU.mp4", "activitynet/videos/v_AC9mml3mqps.mp4", "activitynet/videos/v_mjbzWcSeiwQ.mp4" ]

4

[ 2 ]

false

0

23,321.882361

37

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A screen is shown playing video above a stage and leads into performers skating out on ice as well as hockey players behind them. The players all line up on the ice with one waving a flag and then begin skating around.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_STAvUAslEYM.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_oD0RWEO8D1g.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_JQavlg895jU.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_AC9mml3mqps.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_mjbzWcSeiwQ.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A man is seen riding into frame on a lawn mower and looking at the camera. The man speaks to the camera until two more mowers appear and he begins riding around. He gives the camera a thumbs up while still riding around and stops to look at the camera." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_ZYwfvPJv4Rk.mp4", "activitynet/videos/v_puK4NxGKNdQ.mp4", "activitynet/videos/v_uJ_QCxMDfag.mp4", "activitynet/videos/v_86hyAYM5d3E.mp4", "activitynet/videos/v_GR6Ul2pD8_Y.mp4" ]

2

[ 1 ]

false

0

16,589.025418

39

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man is seen riding into frame on a lawn mower and looking at the camera. The man speaks to the camera until two more mowers appear and he begins riding around. He gives the camera a thumbs up while still riding around and stops to look at the camera.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_ZYwfvPJv4Rk.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_puK4NxGKNdQ.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_uJ_QCxMDfag.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_86hyAYM5d3E.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_GR6Ul2pD8_Y.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "Four males,three teenagers and a young boy are outside in a back yard playing croquet. As the boys take turns,only one ball goes through the arch as the other ones go in the grass and over the trees. When the ball comes back,two of the boys begin to play fight with their croquet. Suddenly,another boy has a large dodge ball like item that he hits and but then it hits the peg it is the actual ball. After,the real ball is hit from various locations,such as the clubhouse and trampoline until the end where their names are shown and credits are rolled." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_A0XGYLim9IU.mp4", "activitynet/videos/v_w7IeqGuuA7Q.mp4", "activitynet/videos/v_6VT2jBflMAM.mp4", "activitynet/videos/v_yVp99wxlW90.mp4", "activitynet/videos/v_vGcH8N8sJlM.mp4" ]

5

[ 4 ]

false

0

17,798.959397

40

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"Four males,three teenagers and a young boy are outside in a back yard playing croquet. As the boys take turns,only one ball goes through the arch as the other ones go in the grass and over the trees. When the ball comes back,two of the boys begin to play fight with their croquet. Suddenly,another boy has a large dodge ball like item that he hits and but then it hits the peg it is the actual ball. After,the real ball is hit from various locations,such as the clubhouse and trampoline until the end where their names are shown and credits are rolled.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_A0XGYLim9IU.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_w7IeqGuuA7Q.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_6VT2jBflMAM.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_yVp99wxlW90.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_vGcH8N8sJlM.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A man is bending over a hole in the ice, while another is trying to pull out his pole as he has caught something. He eventually pulls a large trout fish from the hole, holding it up for the camera. The men high five in celebration." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_qHRCGBIiNFg.mp4", "activitynet/videos/v_hUynCsek8I0.mp4", "activitynet/videos/v_TX8FGTL1flw.mp4", "activitynet/videos/v_FEqLmpNzxdg.mp4", "activitynet/videos/v_J8mSgO4r-kQ.mp4" ]

1

[ 4 ]

false

0

32,363.200881

38

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man is bending over a hole in the ice, while another is trying to pull out his pole as he has caught something. He eventually pulls a large trout fish from the hole, holding it up for the camera. The men high five in celebration.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_qHRCGBIiNFg.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_hUynCsek8I0.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_TX8FGTL1flw.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_FEqLmpNzxdg.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_J8mSgO4r-kQ.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "Students pedal stationary bikes in a classroom. A boy looks at a smart phone while pedaling a stationary bike, and other boys continue biking. A boy lowers his cap to cover his eyes. A girl pedals a bike while looking her smart phone." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_qiRrR2Nj2SQ.mp4", "activitynet/videos/v_D0pVkTEYQg8.mp4", "activitynet/videos/v_qhnWJ4G5JMA.mp4", "activitynet/videos/v_zb6WUBWwXfk.mp4", "activitynet/videos/v_Ck-9AHZNkq4.mp4" ]

5

[ 5 ]

true

1

12,519.178792

41

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"Students pedal stationary bikes in a classroom. A boy looks at a smart phone while pedaling a stationary bike, and other boys continue biking. A boy lowers his cap to cover his eyes. A girl pedals a bike while looking her smart phone.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_qiRrR2Nj2SQ.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_D0pVkTEYQg8.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_qhnWJ4G5JMA.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_zb6WUBWwXfk.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_Ck-9AHZNkq4.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "Clips are shown of a woman cutting a woman's hair while another speaks to the camera and he begins washing the hair. The man continues to cut and style the womans hair as he speaks to the camera with the host. He shows several different ways to style the hair and ends with the woman looking pleased." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_q6sLCLnTuik.mp4", "activitynet/videos/v_vmUbGiOyUbU.mp4", "activitynet/videos/v_uDmEOkAXTfo.mp4", "activitynet/videos/v_WqnnGmL-lmU.mp4", "activitynet/videos/v_sMITf5WBIxM.mp4" ]

4

[ 4 ]

true

1

17,040.870529

42

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"Clips are shown of a woman cutting a woman's hair while another speaks to the camera and he begins washing the hair. The man continues to cut and style the womans hair as he speaks to the camera with the host. He shows several different ways to style the hair and ends with the woman looking pleased.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_q6sLCLnTuik.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_vmUbGiOyUbU.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_uDmEOkAXTfo.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_WqnnGmL-lmU.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_sMITf5WBIxM.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "People are playing with a ball in the sand on the beach. A man dives for the ball and falls into the sand. The ball is shown on the sand." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_pLVCuSq560Y.mp4", "activitynet/videos/v_8fZbv6OUEm8.mp4", "activitynet/videos/v_Uc1_7BXtXZs.mp4", "activitynet/videos/v_4_wfCFTnExI.mp4", "activitynet/videos/v_bfk3xsTt0XA.mp4" ]

2

[ 2 ]

true

1

15,124.295168

43

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"People are playing with a ball in the sand on the beach. A man dives for the ball and falls into the sand. The ball is shown on the sand.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_pLVCuSq560Y.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_8fZbv6OUEm8.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_Uc1_7BXtXZs.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_4_wfCFTnExI.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_bfk3xsTt0XA.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "People are riding motocross bikes in the dirt and going off jumps. A man waves a white flag over the course." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_y1IjkACdnfs.mp4", "activitynet/videos/v_ZeBrPKBGb_k.mp4", "activitynet/videos/v_aTQaYDmcMDY.mp4", "activitynet/videos/v_ennVaOEePHk.mp4", "activitynet/videos/v_ZVNRQ_MPZAs.mkv" ]

3

[ 3 ]

true

1

36,037.562201

45

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"People are riding motocross bikes in the dirt and going off jumps. A man waves a white flag over the course.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_y1IjkACdnfs.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_ZeBrPKBGb_k.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_aTQaYDmcMDY.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_ennVaOEePHk.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_ZVNRQ_MPZAs.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A woman is seen waving to the camera and leads into her putting makeup all over her face. The woman continues putting makeup on all over her face and ends by smiling to the camera." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_LZEiFNEAyyw.mp4", "activitynet/videos/v_A8dBgZCuQow.mp4", "activitynet/videos/v_OYAyb_Ire24.mp4", "activitynet/videos/v_1RQ27XZKU1E.mp4", "activitynet/videos/v_2HmhRdKRVb4.mp4" ]

2

[ 1 ]

false

0

37,200.703209

46

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A woman is seen waving to the camera and leads into her putting makeup all over her face. The woman continues putting makeup on all over her face and ends by smiling to the camera.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_LZEiFNEAyyw.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_A8dBgZCuQow.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_OYAyb_Ire24.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_1RQ27XZKU1E.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_2HmhRdKRVb4.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "Two kids are crossing a slack line over a blue mat. A man in a red jacket holds a microphone. A man in a gray shirt is doing tricks on a slack line. People are seen standing in front of a stage." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_shBiO7aGy6k.mp4", "activitynet/videos/v_SSoHwNbASQQ.mp4", "activitynet/videos/v_2D22fVcAcyo.mp4", "activitynet/videos/v__Ew3g9PXhvo.mp4", "activitynet/videos/v_UTiSAR1o2nU.mp4" ]

3

[ 2 ]

false

0

52,181.858492

44

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"Two kids are crossing a slack line over a blue mat. A man in a red jacket holds a microphone. A man in a gray shirt is doing tricks on a slack line. People are seen standing in front of a stage.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_shBiO7aGy6k.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_SSoHwNbASQQ.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_2D22fVcAcyo.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v__Ew3g9PXhvo.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_UTiSAR1o2nU.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags. System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. Decision rules (concise): - Judge relevance ONLY from what is visible in the frames. - Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence. - Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage. ABSOLUTE OUTPUT CONTRACT: <answer> [a] > [b] > [c] > [d] > [e] </answer> Constraints: - Do NOT use per-candidate XML tags. - a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e. - Always output a total order in <answer>. Query: "A man is kneeling down on grass. He is clipping the grass with large scissors. The man is wearing a yellow and red shirt." Candidates: [1] video:<video> [2] video:<video> [3] video:<video> [4] video:<video> [5] video:<video>

[ "activitynet/videos/v_T_5ANYuDWOA.mp4", "activitynet/videos/v_fxbEiZrQQzM.mp4", "activitynet/videos/v_nezTU6Bq5hM.mp4", "activitynet/videos/v_VhzPqd0Su5I.mp4", "activitynet/videos/v_J4rzLO4u_pI.mp4" ]

3

[ 3 ]

true

1

20,614.693651

47

[ { "role": "user", "content": [ { "type": "text", "text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man is kneeling down on grass. He is clipping the grass with large scissors. The man is wearing a yellow and red shirt.\"\n\nCandidates:\n[1] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_T_5ANYuDWOA.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[2] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_fxbEiZrQQzM.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[3] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_nezTU6Bq5hM.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[4] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_VhzPqd0Su5I.mp4", "nframes": 48, "total_pixels": 50176 } }, { "type": "text", "text": "\n[5] video:", "video_url": null }, { "type": "video_url", "text": null, "video_url": { "url": "file:///hub_data3/seohyun/activitynet/videos/v_J4rzLO4u_pI.mp4", "nframes": 48, "total_pixels": 50176 } } ] } ]

Metric	Value
Total samples	4917
With GT	4917
Parsed answers	4913
Top-1 accuracy	0.449258
Recall@5	0.449258
MRR	1

Datasets:

happy8825
/

qweninstruct_tuned

/hub_data2/seohyun/saves/qwen3vl-2b-instruct_tuned/full/sft · happy8825/activitynet_validset results

Metrics

Collection including happy8825/qweninstruct_tuned

video experiment result