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 51–75 of 1149 papers

TitleStatusHype
Long-VITA: Scaling Large Multi-modal Models to 1 Million Tokens with Leading Short-Context AccurayCode3
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language ModelsCode3
Towards Universal Soccer Video UnderstandingCode3
Valley2: Exploring Multimodal Models with Scalable Vision-Language DesignCode3
VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-TuningCode3
SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model InferenceCode3
SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language ModelsCode3
Flash-VStream: Efficient Real-Time Understanding for Long Video StreamsCode3
Harnessing Temporal Causality for Advanced Temporal Action DetectionCode3
Flash-VStream: Memory-Based Real-Time Understanding for Long Video StreamsCode3
MLVU: Benchmarking Multi-task Long Video UnderstandingCode3
Video-RAG: Visually-aligned Retrieval-Augmented Long Video ComprehensionCode3
PG-Video-LLaVA: Pixel Grounding Large Video-Language ModelsCode2
A Survey on Open-Vocabulary Detection and Segmentation: Past, Present, and FutureCode2
PPLLaVA: Varied Video Sequence Understanding With Prompt GuidanceCode2
Online Video Understanding: OVBench and VideoChat-OnlineCode2
One Trajectory, One Token: Grounded Video Tokenization via Panoptic Sub-object TrajectoryCode2
OmniVid: A Generative Framework for Universal Video UnderstandingCode2
Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person PerspectivesCode2
Omni-Video: Democratizing Unified Video Understanding and GenerationCode2
OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?Code2
PruneVid: Visual Token Pruning for Efficient Video Large Language ModelsCode2
Needle In A Video Haystack: A Scalable Synthetic Evaluator for Video MLLMsCode2
MVBench: A Comprehensive Multi-modal Video Understanding BenchmarkCode2
Neptune: The Long Orbit to Benchmarking Long Video UnderstandingCode2
Show:102550
← PrevPage 3 of 46Next →

No leaderboard results yet.