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 101–125 of 1149 papers

TitleStatusHype
AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and PruningCode2
StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video UnderstandingCode2
A Survey on Open-Vocabulary Detection and Segmentation: Past, Present, and FutureCode2
Omni-Video: Democratizing Unified Video Understanding and GenerationCode2
OmAgent: A Multi-modal Agent Framework for Complex Video Understanding with Task Divide-and-ConquerCode2
Neptune: The Long Orbit to Benchmarking Long Video UnderstandingCode2
TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video UnderstandingCode2
MVBench: A Comprehensive Multi-modal Video Understanding BenchmarkCode2
Foundation Models for Video Understanding: A SurveyCode2
TimeSuite: Improving MLLMs for Long Video Understanding via Grounded TuningCode2
Multi-granularity Correspondence Learning from Long-term Noisy VideosCode2
Needle In A Video Haystack: A Scalable Synthetic Evaluator for Video MLLMsCode2
TSM: Temporal Shift Module for Efficient and Scalable Video Understanding on Edge DeviceCode2
Understanding Long Videos with Multimodal Language ModelsCode2
OmniVid: A Generative Framework for Universal Video UnderstandingCode2
OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?Code2
Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language ModelsCode2
Beyond MOT: Semantic Multi-Object TrackingCode2
Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data EfficiencyCode2
DeMamba: AI-Generated Video Detection on Million-Scale GenVideo BenchmarkCode2
A Content-Driven Micro-Video Recommendation Dataset at ScaleCode2
Video-CCAM: Enhancing Video-Language Understanding with Causal Cross-Attention Masks for Short and Long VideosCode2
Dense Connector for MLLMsCode2
AdaReTaKe: Adaptive Redundancy Reduction to Perceive Longer for Video-language UnderstandingCode2
MMVU: Measuring Expert-Level Multi-Discipline Video UnderstandingCode2
Show:102550
← PrevPage 5 of 46Next →

No leaderboard results yet.