In accordance with regulations and requirements, the editorial department's website domain has been changed to arocmag.cn. The original domain (arocmag.com) has been redirecting to new domain since Jan. 1st, 2025.
See More
Technology of Graphic & Image
|
App. Res. of Comp. Printed Article
Vol. 42, 2025 No. 2
630-635

Action recognition based on multi-level graph topology comparison and refinement

Tang Yuan
Wei Wei
Zheng Cheng
Li Chen
Jiang Haowen
College of Soft Engineering, Chengdu University of Information Technology, Chengdu 610225, China
DOI: 10.19734/j.issn.1001-3695.2024.04.0167

Abstract

Action recognition represents a cutting-edge exploration in the field of computer vision. Leveraging the advantages of the graph convolutional network(GCN) in handling non-Euclidean data, this method has become a mainstream approach for extracting features from skeleton data. Addressing the current issues where GCN overlooks cross-sequence information and struggles to distinguish samples with high trajectory similarity, this paper proposed a GTCR-Block combined with contrastive learning. Firstly, based on the model's recognition results, it categorized samples into reliable samples and ambiguous samples. Secondly, it established a sample-level memory bank and a global-level memory bank to store cross-batch graph topologies. Using contrastive learning, it ensured the graph topologies exhibited intra-class aggregation and inter-class dispersion characteristics, effectively separating ambiguous samples in the feature space. Lastly, it employed multi-level strategies to learn more discriminative feature representations. Experimental results demonstrate that without adding extra parameters, this approach achieves an accuracy of 93.3% on the X-Sub benchmark and 97.4% on the X-View benchmark of the NTU RGB+D dataset. For the NTU RGB+D 120 dataset, it achieves an accuracy of 89.4% on the X-Sub benchmark and 91.2% on the X-set benchmark. The adoption of the GTCR-Block significantly enhances action recognition performance.

Foundation Support

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

Publish Information

DOI: 10.19734/j.issn.1001-3695.2024.04.0167
Publish at: Application Research of Computers Printed Article, Vol. 42, 2025 No. 2
Section: Technology of Graphic & Image
Pages: 630-635
Serial Number: 1001-3695(2025)02-043-0630-06

Publish History

[2025-02-05] Printed Article

Cite This Article

唐櫞, 魏维, 郑程, 等. 基于多层次图拓扑对比细化的动作识别 [J]. 计算机应用研究, 2025, 42 (2): 630-635. (Tang Yuan, Wei Wei, Zheng Cheng, et al. Action recognition based on multi-level graph topology comparison and refinement [J]. Application Research of Computers, 2025, 42 (2): 630-635. )

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)