Comparison and improvement of some attention mechanisms in the video field

Yanshi Liu; Jianguang Zhao; Jingjing Fan; Junqiu Zhang

doi:10.1117/12.3021508

19 February 2024 Comparison and improvement of some attention mechanisms in the video field

Yanshi Liu, Jianguang Zhao, Jingjing Fan, Junqiu Zhang

Proceedings Volume 13063, Fourth International Conference on Computer Vision and Data Mining (ICCVDM 2023); 130630D (2024) https://doi.org/10.1117/12.3021508
Event: Fourth International Conference on Computer Vision and Data Mining (ICCVDM 2023), 2023, Changchun, China

Abstract

This paper compares the effects of SE-Net and the improved CBAM attention mechanism, and proposes a CTSA (Channel and Temporal and Spatial Attention) attention mechanism that adds temporal attention for temporal features, and further proposes a TSA (Time-domain and Spatial Attention) attention mechanism that focuses on time-domain on the basis of comparing the effects of multiple attention mechanisms. The experimental results show that in the field of behaviour recognition, the TSA attention mechanism designed in this paper can achieve better recognition results when using a lighter weight network structure.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Yanshi Liu, Jianguang Zhao, Jingjing Fan, and Junqiu Zhang "Comparison and improvement of some attention mechanisms in the video field", Proc. SPIE 13063, Fourth International Conference on Computer Vision and Data Mining (ICCVDM 2023), 130630D (19 February 2024); https://doi.org/10.1117/12.3021508

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available