computer-vision-17
Grounded Situation Recognition
3260 papers • 126 benchmarks • 313 datasets
Grounded Situation Recognition aims to produce the structured image summary which describes the primary activity (verb), its relevant entities (nouns), and their bounding-box groundings.
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in grounded-situation-recognition-34
Trend
Dataset
Best Model
Actions
SWiG
SWiG
Libraries
iUse these libraries to find grounded-situation-recognition-34 models and implementations
Datasets
No datasets available.
Subtasks
No subtasks available.