In accordance with regulations and requirements, the editorial department's website domain has been changed to arocmag.cn. The original domain (arocmag.com) will be discontinued after Dec. 31st, 2024.
See More
App. Res. of Comp. Accepted Paper
Vol. 42, 2025 No. 3

ASGC-STT: adaptive spatial graph convolution and spatio-temporal Transformer for action recognition

Zhuang Tianming
Qin Zhen
Geng Ji
Zhang Hanwen
Network & Data Security Key Laboratory of Sichuan Province, University of Electronic Science & Technology of China, Chengdu Sichuan 610054, China
DOI: 10.19734/j.issn.1001-3695.2024.07.0255

Abstract

Many recent action recognition studies have modeled the human skeleton as a topology graph and used Graph Convolution Network to extract action features. However, the inherent shared and static features of the topology graph during training limit the performance of the model. To address this issue, an Adaptive Spatial Graph Convolution and Spatio-Temporal Transformer (ASGC-STT) method for human action recognition is proposed. First, an adaptive spatial graph convolution with non-shared graph topology is proposed, where the graph topology is unique in different network layers, enabling the extraction of more diverse features. Additionally, multi-scale temporal convolutions are used to capture high-level temporal features. Second, a spatial-temporal Transformer module is introduced, which accurately captures the correlations between arbitrary joints within and between frames, modeling action representations that include local and global joint relationships. Finally, a multi-scale residual aggregation module is designed, which employs a hierarchical residual structure to effectively expand the receptive field, capturing multi-scale dependencies in both spatial and temporal domains. The proposed ASGC-STT method achieves an accuracy of 92.7% (X-Sub) and 96.9% (X-View) on the large-scale dataset NTU-RGB+D 60, 88.2% (X-Sub) and 89.5% (X-Set) on NTU-RGB+D 120, and 38.6% (Top-1) and 61.4% (Top-5) on Kinetics Skeleton 400. Experimental results demonstrate that, the ASGC-STT method offers superior performance and generalization in human action recognition tasks.

Foundation Support

国家自然科学基金资助项目(62372083,62072074,62070654,62027827,62020447)
四川科技支撑计划项目(2024NSFTD0005,2023YFS0020,2023YFS0197,2023FG0148)
CCF百度开放基金资助项目(202312)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2024.07.0255
Publish at: Application Research of Computers Accepted Paper, Vol. 42, 2025 No. 3

Publish History

[2024-12-10] Accepted Paper

Cite This Article

庄添铭, 秦臻, 耿技, 等. ASGC-STT：基于自适应空间图卷积和时空Transformer的人体行为识别 [J]. 计算机应用研究, 2025, 42 (3). (2024-12-16). https://doi.org/10.19734/j.issn.1001-3695.2024.07.0255. (Zhuang Tianming, Qin Zhen, Geng Ji, et al. ASGC-STT: adaptive spatial graph convolution and spatio-temporal Transformer for action recognition [J]. Application Research of Computers, 2025, 42 (3). (2024-12-16). https://doi.org/10.19734/j.issn.1001-3695.2024.07.0255. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.

Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2022 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)