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
App. Res. of Comp. Accepted Paper
Vol. 42, 2025 No. 8

Behavior recognition method based on cross-agent interaction and multi-scale time enhancement

Zhang Junyi1
Zhao Peipei1
Liang Song1
Yang Di1
Sun Aoran1
Xiao Tao2
1. School of Information & Control Engineering, China University of Mining & Technology, Xuzhou 221116, China
2. Changzhou Haitu InformationTechnology Co. , Changzhou 213000, China
DOI: 10.19734/j.issn.1001-3695.2024.11.0508

Abstract

In the behavior recognition algorithm of image/video, there are some problems, such as insufficient utilization of skeletal diagram data, ignoring the interactive semantic information in motion in the model, and insufficient capture of long-term and short-term information in motion, resulting in low recognition accuracy in two-person interaction behavior and similar action scenes. In order to solve these problems, this paper proposed a behavior recognition model that incorporates cross-agent interaction and multi-scale temporal enhancement based on the CTR-GCN(Channel-wise Topology Refinement Graph Convolution Net) network. In order to solve the problem of insufficient utilization of the input skeletal diagram, this paper decomposed the graph data for data augmentation and design an integrated network to process this information. The existing algorithm mainly learns the relationship between the nodes of a single subject, ignores the problem of interaction semantic information when two people interact with each other, this paper designed a Cformer(Cross-Transformer) for cross-agent interaction to learn the interaction features between subjects. In order to solve the problem of insufficient processing of long and short inter-frame information in GCN for time series information, this paper proposed a multi-scale time model to enhance the model's ability to extract long and short-term features. Experimental results show that the model achieves 92.7% and 89.4% accuracy in NTU-RGBD and NTU-RGBD 120 datasets, especially in the scenarios of two-person interaction and similar action behaviors, which verifies the effectiveness of the model.

Foundation Support

国家重点研发计划资助项目(2022YFC3004703)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2024.11.0508
Publish at: Application Research of Computers Accepted Paper, Vol. 42, 2025 No. 8

Publish History

[2025-03-21] Accepted Paper

Cite This Article

张君逸, 赵培培, 梁松, 等. 基于跨主体交互和多尺度时间增强的行为识别方法 [J]. 计算机应用研究, 2025, 42 (8). (2025-04-17). https://doi.org/10.19734/j.issn.1001-3695.2024.11.0508. (Zhang Junyi, Zhao Peipei, Liang Song, et al. Behavior recognition method based on cross-agent interaction and multi-scale time enhancement [J]. Application Research of Computers, 2025, 42 (8). (2025-04-17). https://doi.org/10.19734/j.issn.1001-3695.2024.11.0508. )

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)