TEN: temporal excitation network for video action recognition

Dengdi Sun; Zhenhao He; Bin Luo; Zhuanlian Ding

doi:10.1117/12.2683421

26 June 2023 TEN: temporal excitation network for video action recognition

Dengdi Sun, Zhenhao He, Bin Luo, Zhuanlian Ding

Proceedings Volume 12714, International Conference on Computer Network Security and Software Engineering (CNSSE 2023); 127141T (2023) https://doi.org/10.1117/12.2683421
Event: Third International Conference on Computer Network Security and Software Engineering (CNSSE 2023), 2023, Sanya, China

Abstract

Temporal modeling has attracted the attention of a large number of researchers in the past few years. In this work, we propose a new video architecture, termed as Temporal Excitation Network (TEN). The core of TEN is Temporal Excitation Module (TEM) block, which consists of Temporal Convolution Module (TCM) and Temporal Difference Module (TDM). TCM applies a channel-wise convolution to supplements the short-range temporal information. TDM works by computing feature-level long-range temporal differences and then exploiting it to excite motion-sensitive channels. These two-stage modeling scheme can be fused into existing 2D CNNs to model temporal structures flexibly and efficiently. Extensive experiments demonstrate the effectiveness of the proposed TEN on several benchmarks (e.g., UCF101, HMDB51, Something-Something V1 and Jester). The proposed TEN can guarantee high recognition accuracy while maintaining high recognition efficiency on these datasets.

Citation Download Citation

Dengdi Sun, Zhenhao He, Bin Luo, and Zhuanlian Ding "TEN: temporal excitation network for video action recognition", Proc. SPIE 12714, International Conference on Computer Network Security and Software Engineering (CNSSE 2023), 127141T (26 June 2023); https://doi.org/10.1117/12.2683421

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
9 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Video

Action recognition

Convolution

Transmission electron microscopy

Time division multiplexing

Modeling

3D modeling

Show All Keywords

Keywords/Phrases

Search In:

Publication Years