Technology of Graphic & Image
|
2192-2197,2216

Spatial temporal enhancement interaction network for compositional action recognition

Cui Yafei
School of Computer Science & Engineering, Nanjing University of Science & Technology, Nanjing 210094, China

Abstract

Compositional action recognition is a new challenge in the field of computer vision. It aims to identify unseen combinations of actions and objects. Traditional action recognition models tend to establish a connection between the appearance of objects and the action category, introducing false bias and dramatically deteriorating performance when face unseen combinations of actions and objects. Existing methods ignore the appearance information, take the coordinates and identity information of the object as input, and build an object-centric model. Inspired by these, this paper proposed a spatial-temporal enhancement interaction network(STEIN). Firstly, STEIN extracted and fused multi-level object features from different depths of the backbone network. Then it built an object branch, which used spatial-temporal enhancement module and object interaction module to enhance object features and model the motion and interaction pattern of objects. Finally, it fused the output from the object branch and the backbone network for action classification, making the model took both appearance information and object interaction information into account. Extensive experiments on multiple datasets demonstrate the effectiveness of the proposed model.

Publish Information

DOI: 10.19734/j.issn.1001-3695.2022.10.0526
Publish at: Application Research of Computers Printed Article, Vol. 40, 2023 No. 7
Section: Technology of Graphic & Image
Pages: 2192-2197,2216
Serial Number: 1001-3695(2023)07-041-2192-06

Publish History

[2023-01-05] Accepted Paper
[2023-07-05] Printed Article

Cite This Article

崔亚飞. 基于时空增强式交互网络的组合动作识别 [J]. 计算机应用研究, 2023, 40 (7): 2192-2197,2216. (Cui Yafei. Spatial temporal enhancement interaction network for compositional action recognition [J]. Application Research of Computers, 2023, 40 (7): 2192-2197,2216. )

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)