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 691700 of 1149 papers

TitleStatusHype
VideoChat: Chat-Centric Video UnderstandingCode4
MH-DETR: Video Moment and Highlight Detection with Cross-modal TransformerCode1
Event-Free Moving Object Segmentation from Moving Ego VehicleCode1
ChatVideo: A Tracklet-centric Multimodal and Versatile Video Understanding System0
MRSN: Multi-Relation Support Network for Video Action Detection0
Search-Map-Search: A Frame Selection Paradigm for Action Recognition0
LASER: A Neuro-Symbolic Framework for Learning Spatial-Temporal Scene Graphs with Weak Supervision0
Leveraging triplet loss for unsupervised action segmentationCode1
Therbligs in Action: Video Understanding through Motion Primitives0
SVT: Supertoken Video Transformer for Efficient Video Understanding0
Show:102550
← PrevPage 70 of 115Next →

No leaderboard results yet.