Temporal Sentence Grounding

8 benchmarks43 papers

Temporal sentence grounding (TSG) aims to locate a specific moment from an untrimmed video with a given natural language query. For this task, different levels of supervision are used. 1) Weak supervision: video-level action category set; 2) Semi-weak supervision: video-level action category set, and action annotations at several timestamps; 3) Full supervision: Action category and action interval annotations of all actions in untrimmed videos.

Benchmarks

Temporal Sentence Grounding on Charades-STA

R1@0.7R1@0.5R5@0.7R5@0.5

Temporal Sentence Grounding on Ego4D-Goalstep

R@1,IoU=0.3R@1,IoU=0.5R@5,IoU=0.3R@5,IoU=0.5