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 281290 of 1149 papers

TitleStatusHype
TemporalMaxer: Maximize Temporal Context with only Max Pooling for Temporal Action LocalizationCode1
Localizing Moments in Long Video Via Multimodal GuidanceCode1
Test of Time: Instilling Video-Language Models with a Sense of TimeCode1
Boosting Single Image Super-Resolution via Partial Channel ShiftingCode1
Modeling Video As Stochastic Processes for Fine-Grained Video Representation LearningCode1
Towards Smooth Video CompositionCode1
MOMA-LRG: Language-Refined Graphs for Multi-Object Multi-Actor Activity ParsingCode1
Contrastive Masked Autoencoders for Self-Supervised Video HashingCode1
EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal TokensCode1
InternVideo-Ego4D: A Pack of Champion Solutions to Ego4D ChallengesCode1
Show:102550
← PrevPage 29 of 115Next →

No leaderboard results yet.