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 331340 of 369 papers

TitleStatusHype
HACS: Human Action Clips and Segments Dataset for Recognition and Temporal LocalizationCode0
Guided Attention for Interpretable Motion CaptioningCode0
A flexible model for training action localization with varying levels of supervisionCode0
SADA: Semantic adversarial unsupervised domain adaptation for Temporal Action LocalizationCode0
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised ActivationsCode0
Contextualized Spatio-Temporal Contrastive Learning with Self-SupervisionCode0
Weakly-Supervised Temporal Action Localization by Inferring Salient Snippet-FeatureCode0
SoccerDB: A Large-Scale Database for Comprehensive Video UnderstandingCode0
Towards Improving Spatiotemporal Action Recognition in VideosCode0
Weakly-Supervised Temporal Action Localization with Bidirectional Semantic Consistency ConstraintCode0
Show:102550
← PrevPage 34 of 37Next →

No leaderboard results yet.