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 26–50 of 1149 papers

TitleStatusHype
Tarsier2: Advancing Large Vision-Language Models from Detailed Video Description to Comprehensive Video UnderstandingCode4
PVUW 2024 Challenge on Complex Video Understanding: Methods and ResultsCode4
Flamingo: a Visual Language Model for Few-Shot LearningCode4
Video Understanding with Large Language Models: A SurveyCode4
MovieChat+: Question-aware Sparse Memory for Long Video Question AnsweringCode4
Unified Reward Model for Multimodal Understanding and GenerationCode4
MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual TokensCode4
Video-XL: Extra-Long Vision Language Model for Hour-Scale Video UnderstandingCode4
Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language ModelsCode4
LongVU: Spatiotemporal Adaptive Compression for Long Video-Language UnderstandingCode3
Long-VITA: Scaling Large Multi-modal Models to 1 Million Tokens with Leading Short-Context AccurayCode3
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video UnderstandingCode3
VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-TrainingCode3
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language ModelsCode3
LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via a Hybrid ArchitectureCode3
VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-TuningCode3
Valley2: Exploring Multimodal Models with Scalable Vision-Language DesignCode3
MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video UnderstandingCode3
Harnessing Temporal Causality for Advanced Temporal Action DetectionCode3
SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model InferenceCode3
TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming VideosCode3
Hawk: Learning to Understand Open-World Video AnomaliesCode3
SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language ModelsCode3
Flash-VStream: Memory-Based Real-Time Understanding for Long Video StreamsCode3
Towards Universal Soccer Video UnderstandingCode3
Show:102550
← PrevPage 2 of 46Next →

No leaderboard results yet.