Paper
23 August 2022 A context-action dependency model for spatio-temporal action localization
Junhan Wang, Xu Wang, Nanxi Chen
Author Affiliations +
Proceedings Volume 12330, International Conference on Cyber Security, Artificial Intelligence, and Digital Economy (CSAIDE 2022); 123301U (2022) https://doi.org/10.1117/12.2646770
Event: International Conference on Cyber Security, Artificial Intelligence, and Digital Economy (CSAIDE 2022), 2022, Huzhou, China
Abstract
Understanding the interaction to the context and the co-occurrence of actions is necessary for human action detection. This paper proposes a Context-Action Dependency (CAD) model for spatio-temporal action localization tasks. It leverages context features and action relations through two attention-based modules. A context-dependency module learns the relation between actors and attentive context information. An action-dependency module models each action class separately and explores the relations within co-occurring actions. This paper introduces an action detection framework that integrates the CAD model to improve the precision of action localization. To verify the effectiveness of our solutions, we ran experiments on two datasets AVA and UCF101-24. Our experiment shows that CAD has better performance than the baselines.
© (2022) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Junhan Wang, Xu Wang, and Nanxi Chen "A context-action dependency model for spatio-temporal action localization", Proc. SPIE 12330, International Conference on Cyber Security, Artificial Intelligence, and Digital Economy (CSAIDE 2022), 123301U (23 August 2022); https://doi.org/10.1117/12.2646770
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Video

Computer aided design

Sensors

RGB color model

Visualization

Information visualization

Optical flow

RELATED CONTENT


Back to Top