A new depth residual network combined recurrent with residual structure for human action recognition from videos

Min Wang; Yang Yi; Guixiong Tian

doi:10.1117/12.2631183

18 March 2022 A new depth residual network combined recurrent with residual structure for human action recognition from videos

Min Wang, Yang Yi, Guixiong Tian

Author Affiliations +

Proceedings Volume 12168, International Conference on Computer Graphics, Artificial Intelligence, and Data Processing (ICCAID 2021); 1216808 (2022) https://doi.org/10.1117/12.2631183
Event: International Conference on Computer Graphics, Artificial Intelligence, and Data Processing (ICCAID 2021), 2021, Harbin, China

Abstract

Human action recognition in videos has attracted much attention due to its wide application prospects in research field, such as human-computer interaction, intelligent detection and video search. And deep learning technology has achieved very good results in many fields of the computer vision, especially convolutional networks have achieved the best results in image recognition. However, most convolutional networks are not suitable for dealing with temporal problems. In response to the problems, this paper proposes a new computational framework for the problem of human action recognition from videos, which is presented in this paper by using modified deep residual network. First, the deep residual network is used to obtain features through the fully connected layer, then the recurrent neural network with the residual structure is introduced to improve the efficiency of classification. According to the similar characteristics of adjacent frames in content, the residual structure is introduced into the RNN to increase the depth of the model and obtain better classification effect. Moreover, in order to solve the over-fitting problem, pruning with preference is carried out. According to the proportion of parameters of each node, some parameters are cut off in the training process. Data experiments on some most popular benchmarks as Olympic sports and HMDB51 demonstrate that the presented method could achieve comparable good results to the state of the art.

Citation Download Citation

Min Wang, Yang Yi, and Guixiong Tian "A new depth residual network combined recurrent with residual structure for human action recognition from videos", Proc. SPIE 12168, International Conference on Computer Graphics, Artificial Intelligence, and Data Processing (ICCAID 2021), 1216808 (18 March 2022); https://doi.org/10.1117/12.2631183

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
5 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Video

Neural networks

Remote sensing

Video acceleration

Feature extraction

Performance modeling

Target recognition

Show All Keywords

Keywords/Phrases

Search In:

Publication Years