SOTAVerified

Action Localization

Action Localization is finding the spatial and temporal co ordinates for an action in a video. An action localization model will identify which frame an action start and ends in video and return the x,y coordinates of an action. Further the co ordinates will change when the object performing action undergoes a displacement.

Papers

Showing 8190 of 369 papers

TitleStatusHype
DDG-Net: Discriminability-Driven Graph Network for Weakly-supervised Temporal Action LocalizationCode1
NMS Threshold matters for Ego4D Moment Queries -- 2nd place solution to the Ego4D Moment Queries Challenge 2023Code2
Actionness Inconsistency-guided Contrastive Learning for Weakly-supervised Temporal Action LocalizationCode1
Bullying10K: A Large-Scale Neuromorphic Dataset towards Privacy-Preserving Bullying Recognition0
Multi-Granularity Hand Action DetectionCode1
A Survey on Video Moment Localization0
Proposal-Based Multiple Instance Learning for Weakly-Supervised Temporal Action LocalizationCode1
Action Sensitivity Learning for Temporal Action Localization0
Learning Higher-order Object Interactions for Keypoint-based Video Understanding0
Video-Specific Query-Key Attention Modeling for Weakly-Supervised Temporal Action Localization0
Show:102550
← PrevPage 9 of 37Next →

No leaderboard results yet.