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 321330 of 369 papers

TitleStatusHype
Action Shuffling for Weakly Supervised Temporal Localization0
What do I Annotate Next? An Empirical Study of Active Learning for Action Localization0
Unified Keypoint-based Action Recognition Framework via Structured Keypoint Pooling0
Unsupervised Action Discovery and Localization in Videos0
Equivalent Classification Mapping for Weakly Supervised Temporal Action Localization0
Enabling Weakly-Supervised Temporal Action Localization from On-Device Learning of the Video Stream0
Exploring Denoised Cross-Video Contrast for Weakly-Supervised Temporal Action Localization0
Exploring Feature Representation and Training strategies in Temporal Action Localization0
Exploring Frame Segmentation Networks for Temporal Action Localization0
Ego-Only: Egocentric Action Detection without Exocentric Transferring0
Show:102550
← PrevPage 33 of 37Next →

No leaderboard results yet.