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

Showing 471480 of 1149 papers

TitleStatusHype
Re-ID-AR: Improved Person Re-identification in Video via Joint Weakly Supervised Action RecognitionCode0
FriendsQA: A New Large-Scale Deep Video Understanding Dataset with Fine-grained Topic Categorization for Story VideosCode0
Constrained-size Tensorflow Models for YouTube-8M Video Understanding ChallengeCode0
VideoDG: Generalizing Temporal Relations in Videos to Novel DomainsCode0
SoccerDB: A Large-Scale Database for Comprehensive Video UnderstandingCode0
A Coding Framework and Benchmark towards Low-Bitrate Video UnderstandingCode0
Pooled Motion Features for First-Person VideosCode0
FitCLIP: Refining Large-Scale Pretrained Image-Text Models for Zero-Shot Video Understanding TasksCode0
ActAlign: Zero-Shot Fine-Grained Video Classification via Language-Guided Sequence AlignmentCode0
Pairwise Emotional Relationship Recognition in Drama Videos: Dataset and BenchmarkCode0
Show:102550
← PrevPage 48 of 115Next →

No leaderboard results yet.