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

Showing 226250 of 1149 papers

TitleStatusHype
Slot State Space ModelsCode1
VideoVista: A Versatile Benchmark for Video Understanding and ReasoningCode1
MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in VideosCode1
Differentiable Task Graph Learning: Procedural Activity Representation and Online Mistake Detection from Egocentric VideosCode1
EgoSurgery-Phase: A Dataset of Surgical Phase Recognition from Egocentric Open Surgery VideosCode1
TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-AlignmentCode1
No Time to Waste: Squeeze Time into Channel for Mobile Video UnderstandingCode1
SFMViT: SlowFast Meet ViT in Chaotic WorldCode1
Task-Driven Exploration: Decoupling and Inter-Task Feedback for Joint Moment Retrieval and Highlight DetectionCode1
Enhancing Traffic Safety with Parallel Dense Video Captioning for End-to-End Event AnalysisCode1
SportsHHI: A Dataset for Human-Human Interaction Detection in Sports VideosCode1
Language Repository for Long Video UnderstandingCode1
Exploring Pre-trained Text-to-Video Diffusion Models for Referring Video Object SegmentationCode1
Towards Neuro-Symbolic Video UnderstandingCode1
Spatio-temporal Prompting Network for Robust Video Feature ExtractionCode1
BehAVE: Behaviour Alignment of Video Game EncodingsCode1
Compositional Video Understanding with Spatiotemporal Structure-based TransformersCode1
A Simple LLM Framework for Long-Range Video Question-AnsweringCode1
Open-Vocabulary Video Relation ExtractionCode1
Shot2Story20K: A New Benchmark for Comprehensive Understanding of Multi-shot VideosCode1
SMILE: Multimodal Dataset for Understanding Laughter in Video with Language ModelsCode1
How Well Does GPT-4V(ision) Adapt to Distribution Shifts? A Preliminary InvestigationCode1
Grounded Question-Answering in Long Egocentric VideosCode1
Action Scene Graphs for Long-Form Understanding of Egocentric VideosCode1
DEVIAS: Learning Disentangled Video Representations of Action and SceneCode1
Show:102550
← PrevPage 10 of 46Next →

No leaderboard results yet.