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 951–960 of 1149 papers

TitleStatusHype
Temporally-Weighted Hierarchical Clustering for Unsupervised Action SegmentationCode1
ClawCraneNet: Leveraging Object-level Relation for Text-based Video Segmentation—0
Enhancing Transformer for Video Understanding Using Gated Multi-Level Attention and Temporal Adversarial Training—0
PcmNet: Position-Sensitive Context Modeling Network for Temporal Action Localization—0
Unsupervised Motion Representation Enhanced Network for Action Recognition—0
Win-Fail Action RecognitionCode0
Learning Self-Similarity in Space and Time as Generalized Motion for Video Action RecognitionCode1
Is Space-Time Attention All You Need for Video Understanding?Code2
Relaxed Transformer Decoders for Direct Action Proposal GenerationCode1
Occluded Video Instance Segmentation: A BenchmarkCode1
Show:102550
← PrevPage 96 of 115Next →

No leaderboard results yet.