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 91100 of 369 papers

TitleStatusHype
Boosting Weakly-Supervised Temporal Action Localization with Text InformationCode1
Weakly-Supervised Temporal Action Localization with Bidirectional Semantic Consistency ConstraintCode0
Improving Weakly Supervised Temporal Action Localization by Bridging Train-Test Gap in Pseudo LabelsCode1
DeepSegmenter: Temporal Action Localization for Detecting Anomalies in Untrimmed Naturalistic Driving VideosCode0
WEAR: An Outdoor Sports Dataset for Wearable and Egocentric Activity RecognitionCode1
JCDNet: Joint of Common and Definite phases Network for Weakly Supervised Temporal Action Localization0
Decomposed Cross-modal Distillation for RGB-based Temporal Action Detection0
Structured Video-Language Modeling with Temporal Grouping and Spatial Grounding0
Unified Keypoint-based Action Recognition Framework via Structured Keypoint Pooling0
Weakly-Supervised Temporal Action Localization by Inferring Salient Snippet-FeatureCode0
Show:102550
← PrevPage 10 of 37Next →

No leaderboard results yet.