SOTAVerified

Video Understanding

A crucial task of Video Understanding is to recognise and localise (in space and time) different actions or events appearing in the video.

Source: Action Detection from a Robot-Car Perspective

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 361–370 of 1149 papers

TitleStatusHype
FrameExit: Conditional Early Exiting for Efficient Video RecognitionCode1
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip RetrievalCode1
Crossover Learning for Fast Online Video Instance SegmentationCode1
TubeR: Tubelet Transformer for Video Action DetectionCode1
Visual Semantic Role Labeling for Video UnderstandingCode1
Temporal Context Aggregation Network for Temporal Action Proposal RefinementCode1
Learning Salient Boundary Feature for Anchor-free Temporal Action LocalizationCode1
Temporally-Weighted Hierarchical Clustering for Unsupervised Action SegmentationCode1
Learning Self-Similarity in Space and Time as Generalized Motion for Video Action RecognitionCode1
Relaxed Transformer Decoders for Direct Action Proposal GenerationCode1
Show:102550
← PrevPage 37 of 115Next →

No leaderboard results yet.