Human Action Recognition Based on 3D Convolution and Multi-Attention Transformer
Applied Sciences · 03.03.2025 · 15 (5) · 2695
DOI: 10.3390/app15052695 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 03.03.2025. Verfasst von Minghua Liu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation, Key Research and Development Foundation of Shandong Province.
Abstract (Originalsprache)
To address the limitations of traditional two-stream networks, such as inadequate spatiotemporal information fusion, limited feature diversity, and insufficient accuracy, we propose an improved two-stream network for human action recognition based on multi-scale attention Transformer and 3D convolutional (C3D) fusion. In the temporal stream, the traditional 2D convolutional is replaced with a C3D network to effectively capture temporal dynamics and spatial features. In the spatial stream, a multi-scale convolutional Transformer encoder is introduced to extract features. Leveraging the multi-scale attention mechanism, the model captures and enhances features at various scales, which are then adaptively fused using a weighted strategy to improve feature representation. Furthermore, through extensive experiments on feature fusion methods, the optimal fusion strategy for the two-stream network is identified. Experimental results on benchmark datasets such as UCF101 and HMDB51 demonstrate that the proposed model achieves superior performance in action recognition tasks.
Förderung
- National Natural Science Foundation
- Key Research and Development Foundation of Shandong Province
Zitieren
APA
Liu, M., Li, W., He, B., Wang, C., & Qu, L. (2025). Human Action Recognition Based on 3D Convolution and Multi-Attention Transformer. Applied Sciences, 15(5), 2695. https://doi.org/10.3390/app15052695
Vancouver
Liu M, Li W, He B, Wang C, Qu L. Human Action Recognition Based on 3D Convolution and Multi-Attention Transformer. Applied Sciences. 2025;15(5):2695. doi:10.3390/app15052695
BibTeX
@article{Liu2025,
author = {Liu, Minghua and Li, Wenjing and He, Bo and Wang, Chuanxu and Qu, Lianen},
title = {Human Action Recognition Based on 3D Convolution and Multi-Attention Transformer},
journal = {Applied Sciences},
year = {2025},
volume = {15},
number = {5},
pages = {2695},
doi = {10.3390/app15052695}
}
EUVIMED