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 771780 of 1149 papers

TitleStatusHype
DeepSportradar-v1: Computer Vision Dataset for Sports Understanding with High Quality AnnotationsCode1
Motion Sensitive Contrastive Learning for Self-supervised Video Representation0
Exploring Anchor-based Detection for Ego4D Natural Language Query0
SA-NET.v2: Real-time vehicle detection from oblique UAV images with use of uncertainty estimation in deep meta-learning0
Two-Stream Transformer Architecture for Long Video Understanding0
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation0
Point Primitive Transformer for Long-Term 4D Point Cloud Video UnderstandingCode1
Static and Dynamic Concepts for Self-supervised Video Representation LearningCode1
EgoEnv: Human-centric environment representations from egocentric video0
Video Swin Transformers for Egocentric Video Understanding @ Ego4D Challenges 20220
Show:102550
← PrevPage 78 of 115Next →

No leaderboard results yet.