-
UWGZQ/ConCor-1
Image Segmentation • 0.9B • Updated • 357 • 3 -
UWGZQ/ConCor-1-Data
Viewer • Updated • 1.28M • 317 • 3 -
ConCor-1 Concept Correspondence
🔗4All text-span ↔ image-mask correspondences in a pair
-
Vision-Language Grounding as Bidirectional Concept Correspondence
Paper • 2608.07886 • Published • 3
Ziqi Gao
UWGZQ
AI & ML interests
Multi-modal, Computer Vision
Recent Activity
updated a dataset 6 days ago
UWGZQ/ViCaS-Actions published a dataset 6 days ago
UWGZQ/ViCaS-Actions liked a dataset 29 days ago
Lostgreen/EventLens-TrainOrganizations
-
UWGZQ/ConCor-1
Image Segmentation • 0.9B • Updated • 357 • 3 -
UWGZQ/ConCor-1-Data
Viewer • Updated • 1.28M • 317 • 3 -
ConCor-1 Concept Correspondence
🔗4All text-span ↔ image-mask correspondences in a pair
-
Vision-Language Grounding as Bidirectional Concept Correspondence
Paper • 2608.07886 • Published • 3
Dataset collection
datasets 9
UWGZQ/ViCaS-Actions
Preview • Updated • 83
UWGZQ/VidSTG-SAM3.1-Masks
Viewer • Updated • 13.9M • 41
UWGZQ/Synthetic_Visual_Genome2
Viewer • Updated • 590k • 735 • 8
UWGZQ/ConCor-1-Data
Viewer • Updated • 1.28M • 317 • 3
UWGZQ/pixmo_images_external
Updated • 6
UWGZQ/pixmo_images
Viewer • Updated • 1.07M • 4.46k • 1
UWGZQ/rf100_masks
Viewer • Updated • 3 • 8
UWGZQ/VideoOlmoDefections
Viewer • Updated • 10.2k • 20
UWGZQ/GenerateAnySceneDataset
Viewer • Updated • 61k • 22 • 1