computer-vision-17
Person-centric Visual Grounding
3260 papers • 126 benchmarks • 313 datasets
Person-centric visual grounding is the problem of linking between people named in a caption and people pictured in an image. Introduced in "Who's Waldo? Linking People Across Text and Images" (Cui et al, ICCV 2021).
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in person-centric-visual-grounding-17
Trend
Dataset
Best Model
Actions
Who’s Waldo
Who’s Waldo
Libraries
iUse these libraries to find person-centric-visual-grounding-17 models and implementations
Datasets
No datasets available.
Subtasks
No subtasks available.