R1@0.5: 62.4R1@0.7: 38.6R5@0.7: 66.4R5@0.5: 89.4
Papers with Code · CC BY-SA 4.0
Temporal Sentence Grounding
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.
논문
R@1,IoU=0.3: 23.20R@1,IoU=0.5: 19.40R@5,IoU=0.3: 51.38R@5,IoU=0.5: 44.17
R1@0.5: 46.0R1@0.7: 20.2R5@0.7: 50.2R5@0.5: 83.1
R1@0.5: 55.2R1@0.7: 32.2R5@0.7: 62.7R5@0.5: 88.3
R1@0.5: 47.8R1@0.7: 21.8R5@0.7: 50.4R5@0.5: 84.6
R@1,IoU=0.3: 11.70