EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Vision Transformer with hierarchical structure and windows shifting for person re-identification

Yinghua Zhang, Wei Hou iD

PLOS ONE · 2023

DOI: 10.1371/journal.pone.0287979 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, 2023. Verfasst von Yinghua Zhang und 1 weiteren Autor:innen. Beteiligte Einrichtung: College of Science and Engineering, Jiaozuo Normal College, Jiaozuo, Henan, China. Hauptthemen laut MEDLINE: Electric Power Supplies, Endocrinologists. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the National Natural Science Foundation of China, the Science and Technology Key Project of Science and Technology Department of Henan Province, the Academic Degrees & Graduate Education Reform Project of Henan Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Extracting rich feature representations is a key challenge in person re-identification (Re-ID) tasks. However, traditional Convolutional Neural Networks (CNN) based methods could ignore a part of information when processing local regions of person images, which leads to incomplete feature extraction. To this end, this paper proposes a person Re-ID method based on vision Transformer with hierarchical structure and window shifting. When extracting person image features, the hierarchical Transformer model is constructed by introducing the hierarchical construction method commonly used in CNN. Then, considering the importance of local information of person images for complete feature extraction, the self-attention calculation is performed by shifting within the window region. Finally, experiments on three standard datasets demonstrate the effectiveness and superiority of the proposed method.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Electric Power SuppliesEndocrinologistsHumansBasic Reproduction NumberNeural Networks, Computer

Autor:innen und Institutionen

  • College of Science and Engineering, Jiaozuo Normal College, Jiaozuo, Henan, China.
  • College of Artificial Intelligence, Henan University, Zhengzhou, Henan, China.

ORCID-Profile: Wei Hou

Förderung

  • the National Natural Science Foundation of China
  • the Science and Technology Key Project of Science and Technology Department of Henan Province
  • the Academic Degrees & Graduate Education Reform Project of Henan Province
  • the Innovation and Quality Improvement Project for Graduate Education of Henan University

Zitieren

APA

Zhang, Y., & Hou, W. (2023). Vision Transformer with hierarchical structure and windows shifting for person re-identification. PLOS ONE. https://doi.org/10.1371/journal.pone.0287979

Vancouver

Zhang Y, Hou W. Vision Transformer with hierarchical structure and windows shifting for person re-identification. PLOS ONE. 2023. doi:10.1371/journal.pone.0287979

BibTeX
@article{Zhang2023,
  author = {Zhang, Yinghua and Hou, Wei},
  title = {Vision Transformer with hierarchical structure and windows shifting for person re-identification},
  journal = {PLOS ONE},
  year = {2023},
  doi = {10.1371/journal.pone.0287979}
}
Kostenlos starten →