-
UWGZQ/ConCor-1
Image Segmentation • 0.9B • Updated • 310 • 3 -
UWGZQ/ConCor-1-Data
Viewer • Updated • 1.28M • 219 • 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 • 6
Ziqi Gao
UWGZQ
AI & ML interests
Multi-modal, Computer Vision
Recent Activity
liked a model 5 days ago
UWGZQ/ConCor-1 updated a dataset 14 days ago
UWGZQ/Synthetic_Visual_Genome2 liked a Space 22 days ago
UWGZQ/ConCor-1-demoOrganizations
-
UWGZQ/ConCor-1
Image Segmentation • 0.9B • Updated • 310 • 3 -
UWGZQ/ConCor-1-Data
Viewer • Updated • 1.28M • 219 • 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 • 6
Dataset collection
datasets 7
UWGZQ/Synthetic_Visual_Genome2
Viewer • Updated • 590k • 2.08k • 8
UWGZQ/ConCor-1-Data
Viewer • Updated • 1.28M • 219 • 3
UWGZQ/pixmo_images_external
Updated • 4
UWGZQ/pixmo_images
Viewer • Updated • 1.07M • 1.55k • 1
UWGZQ/rf100_masks
Viewer • Updated • 3 • 5
UWGZQ/VideoOlmoDefections
Viewer • Updated • 10.2k • 23
UWGZQ/GenerateAnySceneDataset
Viewer • Updated • 61k • 10 • 1