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 701–725 of 1149 papers

TitleStatusHype
Extending Video Masked Autoencoders to 128 frames—0
Extensible Hierarchical Method of Detecting Interactive Actions for Video Understanding—0
Real-Time Segmentation Networks should be Latency Aware—0
Fast Retinomorphic Event Stream for Video Recognition and Reinforcement Learning—0
FaVChat: Unlocking Fine-Grained Facail Video Understanding with Multimodal Large Language Models—0
FAVOR-Bench: A Comprehensive Benchmark for Fine-Grained Video Motion Understanding—0
Fewer Tokens and Fewer Videos: Extending Video Understanding Abilities in Large Vision-Language Models—0
Fill-in-the-Blank: A Challenging Video Understanding Evaluation Framework—0
Fine-Grain Annotation of Cricket Videos—0
Fine-Grained Video Captioning through Scene Graph Consolidation—0
CaReBench: A Fine-Grained Benchmark for Video Captioning and Retrieval—0
First Place Solution to the Multiple-choice Video QA Track of The Second Perception Test Challenge—0
Flatten: Video Action Recognition is an Image Classification task—0
Flexible Frame Selection for Efficient Video Reasoning—0
FlexSelect: Flexible Token Selection for Efficient Long Video Understanding—0
FocusChat: Text-guided Long Video Understanding via Spatiotemporal Information Filtering—0
Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions—0
Four Eyes Are Better Than Two: Harnessing the Collaborative Potential of Large Models via Differentiated Thinking and Complementary Ensembles—0
Frame-Voyager: Learning to Query Frames for Video Large Language Models—0
From 128K to 4M: Efficient Training of Ultra-Long Context Large Language Models—0
From Broadcast to Minimap: Achieving State-of-the-Art SoccerNet Game State Reconstruction—0
From Image to Video, what do we need in multimodal LLMs?—0
From Shots to Stories: LLM-Assisted Video Editing with Unified Language Representations—0
From Trial to Triumph: Advancing Long Video Understanding via Visual Context Sample Scaling and Self-reward Alignment—0
Fully Automated Hand Hygiene Monitoring\ Operating Room using 3D Convolutional Neural Network—0
Show:102550
← PrevPage 29 of 46Next →

No leaderboard results yet.