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
Video Understanding with Large Language Models: A SurveyCode4
An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language ModelsCode4
A Survey on Video Diffusion ModelsCode4
PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense CaptioningCode4
Unified Reward Model for Multimodal Understanding and GenerationCode4
Video-XL: Extra-Long Vision Language Model for Hour-Scale Video UnderstandingCode4
MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual TokensCode4
Goldfish: Vision-Language Understanding of Arbitrarily Long VideosCode4
Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language ModelsCode4
LongVU: Spatiotemporal Adaptive Compression for Long Video-Language UnderstandingCode3
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video UnderstandingCode3
Long-VITA: Scaling Large Multi-modal Models to 1 Million Tokens with Leading Short-Context AccurayCode3
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
VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-TuningCode3
MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video UnderstandingCode3
LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via a Hybrid ArchitectureCode3
Valley2: Exploring Multimodal Models with Scalable Vision-Language DesignCode3
Harnessing Temporal Causality for Advanced Temporal Action DetectionCode3
Hawk: Learning to Understand Open-World Video AnomaliesCode3
TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming VideosCode3
SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language ModelsCode3
Flash-VStream: Memory-Based Real-Time Understanding for Long Video StreamsCode3
SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model InferenceCode3
Towards Universal Soccer Video UnderstandingCode3
Show:102550
← PrevPage 2 of 46Next →

No leaderboard results yet.