App. Res. of Comp. Accepted Paper
Vol. 44, 2027 No. 2

Human parsing model with self-gated group attention and pyramid shifted aggregation

Lin Siyuan1,2
Jia Xiaolin1,2
Gu Yajun1,2
1. College of Computer Science and Technology, Southwest University of Science and Technology, Mianyang Sichuan 621010, China
2. Mobile Internet of Things and Radio Frequency Identification Technology Key Laboratory of Mianyang, Mianyang Sichuan 621010, China
DOI: 10.19734/j.issn.1001-3695.2026.05.0192

Abstract

To address the issues of blurred segmentation boundaries and high computational complexity in human body region and clothing segmentation tasks, a human parsing model integrating self‑gated group attention and pyramid shifted aggregation (Pyramid Shifted Aggregation Gated Attention U‑Net, PSAGA‑UNet) was proposed. The proposed model replaced the standard encoder with the EfficientNet backbone to extract deep semantic features. At the longest‑distance skip connection, a Self‑Gated Dual‑input Group Attention (SDGA) module was designed to enhance spatial and channel representation capabilities through attention mechanisms and grouping strategies. Meanwhile, a Pyramid Shifted Aggregation (PSA) module was introduced at the bottleneck to improve the quality of aggregated multi‑scale features via shifted average pooling operations. On the PASCAL‑Person‑Part and Street Tryon datasets, PSAGA‑UNet achieved mean Intersection over Union (mIoU) scores of 71.43% and 69.44%, respectively, outperforming several mainstream segmentation models. Experimental results demonstrate that the proposed algorithm effectively balances segmentation accuracy and computational efficiency in complex scenes.

Foundation Support

国家自然科学基金面上项目(61471306)
四川省自然科学基金面上项目(2022NSFSC0548)
绵阳市移动物联网射频识别技术重点实验室专项(MYZD23032302)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2026.05.0192
Publish at: Application Research of Computers Accepted Paper, Vol. 44, 2027 No. 2

Publish History

[2026-10-24] Accepted Paper

Cite This Article

林思远, 贾小林, 顾娅军. 融合自门控分组注意力与金字塔位移聚合的人体解析算法 [J]. 计算机应用研究, 2027, 44 (2). (2026-10-24). https://doi.org/10.19734/j.issn.1001-3695.2026.05.0192. (Lin Siyuan, Jia Xiaolin, Gu Yajun. Human parsing model with self-gated group attention and pyramid shifted aggregation [J]. Application Research of Computers, 2027, 44 (2). (2026-10-24). https://doi.org/10.19734/j.issn.1001-3695.2026.05.0192. )

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
  • 2020-2025 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)