Optimizing action segmentation with linear self-attention and pyramidal pooling

Jiamin Fu; Zhihong Chen; Haiwei Zhang; Yuxuan Gao

doi:10.1117/12.3051722

18 November 2024 Optimizing action segmentation with linear self-attention and pyramidal pooling

Jiamin Fu, Zhihong Chen, Haiwei Zhang, Yuxuan Gao

Author Affiliations +

Proceedings Volume 13403, International Conference on Algorithms, High Performance Computing, and Artificial Intelligence (AHPCAI 2024) ; 134032H (2024) https://doi.org/10.1117/12.3051722
Event: International Conference on Algorithms, High Performance Computing, and Artificial Intelligence, 2024, Zhengzhou, China

Abstract

Continuous action segmentation is a challenging task in video semantic understanding, aims to temporally segment unedited long videos. Current state-of-the-art methods combine time-domain convolution with self-attention mechanisms to capture temporal correlations, achieving high-accuracy frame-level classification and reducing over-segmentation during prediction. However, these models rely on multiple decoding modules and complex self-attention mechanisms, which, while improving frame accuracy, incur high computational costs, particularly when dealing with long video sequences. To address this issue, we propose a novel hybrid model that optimizes the temporal convolutional model with a simplified extended linear self-attention layer. This design enables the model to focus more effectively on action changes at key moments in a video sequence while significantly reducing computational complexity. Furthermore, we introduce an attention enhancement module with a pyramidal pooling structure to improve the model's ability to capture actions at multiple scales. By leveraging these innovations, our hybrid model achieves a better balance between accuracy and computational efficiency, making it more suitable for real-world applications involving long video sequences. The experimental results demonstrate that our model achieves an accuracy of 86.0% on the 50Salads dataset and 84.6% on the GTEA dataset, outperforming existing techniques such as MS-TCN++ and ASFormer in terms of both accuracy and computational efficiency. Notably, our model requires only 0.98M parameters, a significant reduction compared to ASFormer's parameter count. These advantages make our model particularly well-suited for practical applications involving long video sequences, where computational efficiency and accuracy are crucial.

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

Citation Download Citation

Jiamin Fu, Zhihong Chen, Haiwei Zhang, and Yuxuan Gao "Optimizing action segmentation with linear self-attention and pyramidal pooling", Proc. SPIE 13403, International Conference on Algorithms, High Performance Computing, and Artificial Intelligence (AHPCAI 2024) , 134032H (18 November 2024); https://doi.org/10.1117/12.3051722

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

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
6 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Video

Convolution

Video surveillance

Performance modeling

Data modeling

Mathematical optimization

Image segmentation

Show All Keywords

Keywords/Phrases

Search In:

Publication Years