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 591–600 of 1149 papers

TitleStatusHype
Dr^2Net: Dynamic Reversible Dual-Residual Networks for Memory-Efficient FinetuningCode0
Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision Language Audio and Action—0
Enhanced Motion-Text Alignment for Image-to-Video Transfer Learning—0
Dr2Net: Dynamic Reversible Dual-Residual Networks for Memory-Efficient Finetuning—0
Compositional Video Understanding with Spatiotemporal Structure-based TransformersCode1
VideoGrounding-DINO: Towards Open-Vocabulary Spatio-Temporal Video Grounding—0
Video-GroundingDINO: Towards Open-Vocabulary Spatio-Temporal Video Grounding—0
Video Understanding with Large Language Models: A SurveyCode4
A Simple LLM Framework for Long-Range Video Question-AnsweringCode1
Open-Vocabulary Video Relation ExtractionCode1
Show:102550
← PrevPage 60 of 115Next →

No leaderboard results yet.