RSTNet: A Spatio‐Temporal Attention Framework for Human Action Recognition
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.
Authors
- Baofeng Tian (ORCID: https://orcid.org/0000-0002-1944-6649)
- Zhihong Huang (ORCID: https://orcid.org/0000-0003-1395-2652)
- Hongbo Wang (ORCID: https://orcid.org/0000-0002-0205-6441)
- Yafei Wang (ORCID: https://orcid.org/0000-0003-4880-5054)
- Yang Qu (ORCID: https://orcid.org/0000-0002-3714-1814)
- Cui Haifeng
- Yao Tianming
- Zhang Tianyu (ORCID: https://orcid.org/0009-0007-5221-7614)
- Duan Daxin
- Yao Mingkai
- Liu Taoran
- Shang Mingwei
Institutions
- Jilin University (CN)
- Changchun 208 Hospital (CN)
Publication Details
- Journal
- Electronics Letters
- Published
- 2025-01-01
- DOI
- https://doi.org/10.1049/ell2.70191
- Primary Topic
- Human Pose and Action Recognition
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- People's Government of Jilin Province
- Education Department of Jilin Province
- National Key Research and Development Program of China
- Jilin Scientific and Technological Development Program