Cui Haifeng, Hou Zhihong, Zhang Tianyu, Duan Daxin, Yao Mingkai, Liu Taoran, Shang Mingwei, Qu Yang, Wang Yafei, Wang Hongbo, Yao Tianming, Tian Baofeng
{"title":"RSTNet: A Spatio-Temporal Attention Framework for Human Action Recognition","authors":"Cui Haifeng, Hou Zhihong, Zhang Tianyu, Duan Daxin, Yao Mingkai, Liu Taoran, Shang Mingwei, Qu Yang, Wang Yafei, Wang Hongbo, Yao Tianming, Tian Baofeng","doi":"10.1049/ell2.70191","DOIUrl":null,"url":null,"abstract":"<p>This paper introduces RSTNet, a neural network model based on spatio-temporal attention (STA), designed to improve the accuracy of human action recognition. The model uses heatmaps as input, employs 3D-ResNet as its backbone network, and incorporates STA modules and squeeze-and-excitation (SE) modules. Experiments on the UCF101 dataset demonstrate that RSTNet outperforms other classic methods in key metrics such as Top1 accuracy, Top5 accuracy and average accuracy. Ablation studies further validate the contribution of each module to the model's performance, proving the effectiveness of this approach in capturing spatio-temporal features and enhancing action recognition precision.</p>","PeriodicalId":11556,"journal":{"name":"Electronics Letters","volume":"61 1","pages":""},"PeriodicalIF":0.7000,"publicationDate":"2025-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/ell2.70191","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Electronics Letters","FirstCategoryId":"5","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1049/ell2.70191","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 0
Abstract
This paper introduces RSTNet, a neural network model based on spatio-temporal attention (STA), designed to improve the accuracy of human action recognition. The model uses heatmaps as input, employs 3D-ResNet as its backbone network, and incorporates STA modules and squeeze-and-excitation (SE) modules. Experiments on the UCF101 dataset demonstrate that RSTNet outperforms other classic methods in key metrics such as Top1 accuracy, Top5 accuracy and average accuracy. Ablation studies further validate the contribution of each module to the model's performance, proving the effectiveness of this approach in capturing spatio-temporal features and enhancing action recognition precision.
期刊介绍:
Electronics Letters is an internationally renowned peer-reviewed rapid-communication journal that publishes short original research papers every two weeks. Its broad and interdisciplinary scope covers the latest developments in all electronic engineering related fields including communication, biomedical, optical and device technologies. Electronics Letters also provides further insight into some of the latest developments through special features and interviews.
Scope
As a journal at the forefront of its field, Electronics Letters publishes papers covering all themes of electronic and electrical engineering. The major themes of the journal are listed below.
Antennas and Propagation
Biomedical and Bioinspired Technologies, Signal Processing and Applications
Control Engineering
Electromagnetism: Theory, Materials and Devices
Electronic Circuits and Systems
Image, Video and Vision Processing and Applications
Information, Computing and Communications
Instrumentation and Measurement
Microwave Technology
Optical Communications
Photonics and Opto-Electronics
Power Electronics, Energy and Sustainability
Radar, Sonar and Navigation
Semiconductor Technology
Signal Processing
MIMO