App. Res. of Comp. Accepted Paper
Vol. 43, 2026 No. 9

Multi-level feature spatial-temporal cross-fusion for group activity recognition‌

Tu Hongbin
Xu Kunlin
He Cheng
Gao Erhan
School of Electrical and Automation Engineering, East China Jiaotong University, Nanchang 330013, China
DOI: 10.19734/j.issn.1001-3695.2026.01.0017

Abstract

In the domain of computer vision, group activity recognition algorithms still face persistent challenges: inadequately exploit scene context, insufficiently model individual spatial distributions and interactive relationships explicitly, and easily suffer from noise intrusion and low-level feature degradation during spatial-temporal feature fusion. To mitigate these limitations, this paper presents a multi-level feature spatial-temporal cross-fusion network MlffNet. To bridge the gap between human-centric features and global scene semantics, we design a feature enhancement module that injects contextual scene information into individual feature representations, thereby strengthening the model’s sensitivity to critical targets. To address the under-modeling of spatial disparities and inter-person interactions, we leverage a convolution-guided attention mechanism to generate high-quality global visual tokens, and explicitly encode the impact of individual spatial layouts on group dynamics via a spatial position encoder paired with a spatial-temporal cross transformer. Furthermore, to alleviate noise contamination and preserve fine-grained low-level features during spatiotemporal fusion, this paper refines the cross-entropy loss function to suppress redundant interference while retaining discriminative detailed cues. Extensive experimental evaluations demonstrate that our approach attains MCA of 95.4% and 96.0% on the Volleyball and Collective Activity datasets, respectively. Notably, it exhibits superior performance in complex group interaction scenarios, which validates the efficacy and robustness of the proposed model.

Foundation Support

赣鄱俊才支持计划-江西省主要学科学术和技术带头人培养项目-领军人才(20243BCE51051)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2026.01.0017
Publish at: Application Research of Computers Accepted Paper, Vol. 43, 2026 No. 9

Publish History

[2026-05-25] Accepted Paper

Cite This Article

涂宏斌, 许坤林, 何城, 等. 多层次特征时空交叉融合的群体行为识别方法 [J]. 计算机应用研究, 2026, 43 (9). (2026-06-02). https://doi.org/10.19734/j.issn.1001-3695.2026.01.0017. (Tu Hongbin, Xu Kunlin, He Cheng, et al. Multi-level feature spatial-temporal cross-fusion for group activity recognition‌ [J]. Application Research of Computers, 2026, 43 (9). (2026-06-02). https://doi.org/10.19734/j.issn.1001-3695.2026.01.0017. )

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)