EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A local-global transformer-based model for person re-identification

Guangjie Liu, Ke Xu iD, Jinlong Zhu, Yu Ge, Xiaoyang Chen

PLOS One · 13.11.2025 · 20 (11) · e0335848

DOI: 10.1371/journal.pone.0335848 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 13.11.2025. Verfasst von Guangjie Liu und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer Science and Technology, Changchun Normal University, Changchun, Jinlin, China. Hauptthemen laut MEDLINE: Biometric Identification, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Jilin Provincial Department of science and technology.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Person re-identification (ReID) aims to recognize a specific individual across various camera views. State-of-the-art methods have shown that both Transformer-based and CNN-based methods deliver competitive performance. However, Transformer-based methods tend to overlook local features, as they primarily process input sequences holistically, rather than focusing on individual elements or small groups within the sequence. To address this limitation, we introduce an innovative Transformer-based person ReID model that effectively integrates local and global features. The Local Attention Module is added to capture fine-grained features, which are then combined with global features to enhance the model’s recognition accuracy. Given the importance of positional information in image data, relative position encoding is incorporated within the Local Attention Module. This encoding method better captures the relative positional relationships between different tokens in an image, thereby improving the model’s comprehension of the structural information of the image. Experimental results indicate that the Rank-1 of our model respectively improves by 0.7% and 0.9% on the Market-1501 and DukeMTMC-reID benchmark datasets for person ReID.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Biometric IdentificationImage Processing, Computer-AssistedHumansAlgorithmsNeural Networks, Computer

Autor:innen und Institutionen

  • College of Computer Science and Technology, Changchun Normal University, Changchun, Jinlin, China.
  • Jilin Open University, Changchun, Jinlin, China.

ORCID-Profile: Ke Xu

Förderung

  • Jilin Provincial Department of science and technology

Zitieren

APA

Liu, G., Xu, K., Zhu, J., Ge, Y., & Chen, X. (2025). A local-global transformer-based model for person re-identification. PLOS One, 20(11), e0335848. https://doi.org/10.1371/journal.pone.0335848

Vancouver

Liu G, Xu K, Zhu J, Ge Y, Chen X. A local-global transformer-based model for person re-identification. PLOS One. 2025;20(11):e0335848. doi:10.1371/journal.pone.0335848

BibTeX
@article{Liu2025,
  author = {Liu, Guangjie and Xu, Ke and Zhu, Jinlong and Ge, Yu and Chen, Xiaoyang},
  title = {A local-global transformer-based model for person re-identification},
  journal = {PLOS One},
  year = {2025},
  volume = {20},
  number = {11},
  pages = {e0335848},
  doi = {10.1371/journal.pone.0335848}
}
Kostenlos starten →