App. Res. of Comp. Accepted Paper
Vol. 43, 2026 No. 10

Action recognition based on graph convolutional networks with dual-dimensional dynamic topology modeling

Zhu Fuling
Wei Wei
Ren Xiang
Wang Teng
Tang Xucheng
School of Software Engineering, Chengdu University of Information Technology, Chengdu 610225, China
DOI: 10.19734/j.issn.1001-3695.2025.12.0543

Abstract

Graph Convolutional Networks (GCN) often suffer from insufficient capture of long-range spatial dependencies in skeleton-based action recognition due to static graph topologies. This study proposed a Double-dimensional Dynamic Topology Graph Convolutional Network (DDT-GCN) to address this limitation. The proposed architecture integrated a Dual-stream Synergistic Graph Convolutional Module (DSG-GCM) . This module expanded the spatial receptive field. It synergistically processed local motion features from physical connections and global semantic associations via adaptive learning. An interactive attention mechanism enhanced the feature representation. A Temporal Topology Self-Attention (TTSA) module utilized a self-attention mechanism. It independently learned joint spatial relationships for each frame to achieve precise modeling of spatial features under specific poses. The model achieved recognition accuracies of 93.5% (X-Sub) and 97.2% (X-View) on the NTU RGB+D dataset. It reached 89.7% (X-Sub) and 91.3% (X-Set) on the NTU RGB+D 120 dataset. The model yielded Top-1 and Top-5 accuracies of 51.5% and 75.3% on the Kinetics-Skeleton dataset. The accuracy on the NW-UCLA dataset reached 97.3%. Experimental results demonstrate that dual-dimension dynamic topology modeling effectively improves the accuracy of action recognition. The proposed method provides a robust solution for capturing complex spatial dependencies in skeletal sequences.

Foundation Support

四川省科技创新苗子项目(MZGC20230105)
科技厅重点研发(2021YFG0299)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2025.12.0543
Publish at: Application Research of Computers Accepted Paper, Vol. 43, 2026 No. 10

Publish History

[2026-07-03] Accepted Paper

Cite This Article

朱福玲, 魏维, 任湘, 等. 基于双维动态拓扑建模的图卷积网络动作识别方法 [J]. 计算机应用研究, 2026, 43 (10). (2026-07-30). https://doi.org/10.19734/j.issn.1001-3695.2025.12.0543. (Zhu Fuling, Wei Wei, Ren Xiang, et al. Action recognition based on graph convolutional networks with dual-dimensional dynamic topology modeling [J]. Application Research of Computers, 2026, 43 (10). (2026-07-30). https://doi.org/10.19734/j.issn.1001-3695.2025.12.0543. )

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)