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 371380 of 1149 papers

TitleStatusHype
InternVideo-Ego4D: A Pack of Champion Solutions to Ego4D ChallengesCode1
EgoCVR: An Egocentric Benchmark for Fine-Grained Composed Video RetrievalCode1
IntentVizor: Towards Generic Query Guided Interactive Video SummarizationCode1
An Empirical Study of End-to-End Temporal Action DetectionCode1
Is Appearance Free Action Recognition Possible?Code1
Technical Report: Temporal Aggregate RepresentationsCode1
-Video: A Training-Free Approach to Long Video Understanding via Continuous-Time Memory ConsolidationCode1
Temporal Aggregate Representations for Long-Range Video UnderstandingCode1
Temporal Context Aggregation Network for Temporal Action Proposal RefinementCode1
EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal TokensCode1
Show:102550
← PrevPage 38 of 115Next →

No leaderboard results yet.