A computer-implemented method is provided for action localization. The method includes converting one or more video frames into person keypoints and object keypoints. The method further includes embedding position, timestamp, instance, and type information with the person keypoints and object keypoints to obtain keypoint embeddings. The method also includes predicting, by a hierarchical transformer encoder using the keypoint embeddings, human actions and bounding box information of when and where the human actions occur in the one or more video frames.
KEYPOINT BASED ACTION LOCALIZATION
2022-07-28
Patent
Electronic Resource
English
Performance Evaluation of 3D Keypoint Detectors
British Library Online Contents | 2013
|Visual Object Categorization with New Keypoint-based AdaBoost Features
British Library Conference Proceedings | 2009
|Keypoint descriptor matching with context-based orientation estimation
British Library Online Contents | 2014
|