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. 7
2213-2219

Weakly supervised temporal action localization with dual-stream feature enhancement and fusion

Liu Yibin1
Gao Shu1
Chen Liangchen2,3
1. School of Computer Science & Artificial Intelligence, Wuhan University of Technology, Wuhan 430070, China
2. School of Computer, China University of Labor Relations, Beijing 100048, China
3. Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100093, China
DOI: 10.19734/j.issn.1001-3695.2024.09.0373

Abstract

Weakly supervised temporal action localization aims to classify and locate action instances in untrimmed videos using only video-level labels. Existing models typically use pre-trained feature extractors to extract segment-level RGB and optical flow features from videos, but the pre-extracted segment-level video features only cover short time spans and do not consider the complementarity and correlation between RGB and optical flow, which affects the accuracy of localization. To this end, this paper proposed a weakly-supervised temporal action localization model with dual-stream feature enhancement and fusion. Firstly, it expanded the receptive field through a multi-scale dense dilated convolution, allowing the model to cover multiple time spans and capture the temporal dependencies between video segments, resulting in enhanced RGB and optical flow features. Then, it utilized a convolutional network to adaptively extract key features from the enhanced RGB and optical flow features for fusion, achieving complementary correlation between RGB and optical flow features, further enriching the video feature representation and improving the accuracy of the models localization performance. The model achieves detection accuracies of 73.9% and 43.5% on the THUMOS14 and ActivityNet1.3 datasets respectively, outperforming the existing state-of-the-art models, which proves the effectiveness of the proposed model.

Foundation Support

国家自然科学基金项目(52172327)
国家教育部人文社科项目(18YJA630076)
中国劳动关系学院科研项目(23XYJS016)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2024.09.0373
Publish at: Application Research of Computers Printed Article, Vol. 42, 2025 No. 7
Section: Technology of Graphic & Image
Pages: 2213-2219
Serial Number: 1001-3695(2025)07-039-2213-07

Publish History

[2025-03-06] Accepted Paper
[2025-07-05] Printed Article

Cite This Article

刘逸斌, 高曙, 陈良臣. 双流特征增强与融合的弱监督时序动作定位 [J]. 计算机应用研究, 2025, 42 (7): 2213-2219. (Liu Yibin, Gao Shu, Chen Liangchen. Weakly supervised temporal action localization with dual-stream feature enhancement and fusion [J]. Application Research of Computers, 2025, 42 (7): 2213-2219. )

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)