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 11261149 of 1149 papers

TitleStatusHype
MOFO: MOtion FOcused Self-Supervision for Video UnderstandingCode0
MOD: A Deep Mixture Model with Online Knowledge Distillation for Large Scale Video Temporal Concept LocalizationCode0
Detection-Fusion for Knowledge Graph Extraction from VideosCode0
Vamos: Versatile Action Models for Video UnderstandingCode0
Are current long-term video understanding datasets long-term?Code0
Audio Caption in a Car Setting with a Sentence-Level LossCode0
VCRBench: Exploring Long-form Causal Reasoning Capabilities of Large Video Language ModelsCode0
VideoDG: Generalizing Temporal Relations in Videos to Novel DomainsCode0
Detect-and-Track: Efficient Pose Estimation in VideosCode0
MINOTAUR: Multi-task Video Grounding From Multimodal QueriesCode0
AdaVideoRAG: Omni-Contextual Adaptive Retrieval-Augmented Efficient Long Video UnderstandingCode0
Deep Learning Methods for Efficient Large Scale Video LabelingCode0
Creative Flow+ DatasetCode0
Contextual Explainable Video Representation: Human Perception-based UnderstandingCode0
A Challenge to Build Neuro-Symbolic Video AgentsCode0
METok: Multi-Stage Event-based Token Compression for Efficient Long Video UnderstandingCode0
Constrained-size Tensorflow Models for YouTube-8M Video Understanding ChallengeCode0
Masked Autoencoders for Egocentric Video Understanding @ Ego4D Challenge 2022Code0
Context R-CNN: Long Term Temporal Context for Per-Camera Object DetectionCode0
SoccerDB: A Large-Scale Database for Comprehensive Video UnderstandingCode0
Video Action UnderstandingCode0
VURF: A General-purpose Reasoning and Self-refinement Framework for Video UnderstandingCode0
Long-Term Feature Banks for Detailed Video UnderstandingCode0
Localizing Moments in Video with Temporal LanguageCode0
Show:102550
← PrevPage 46 of 46Next →

No leaderboard results yet.