Item request has been placed! ×
Item request cannot be made. ×
loading  Processing Request

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

Item request has been placed! ×
Item request cannot be made. ×
loading   Processing Request
  • المؤلفون: Zhang, Yinghua; Hou, Wei
  • المصدر:
    PLOS ONE ; volume 18, issue 6, page e0287979 ; ISSN 1932-6203
  • نوع التسجيلة:
    article in journal/newspaper
  • اللغة:
    English
  • معلومة اضافية
    • Contributors:
      Xu, Chenchu; 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
    • بيانات النشر:
      Public Library of Science (PLoS)
    • الموضوع:
      2023
    • Collection:
      PLOS Publications (via CrossRef)
    • نبذة مختصرة :
      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.
    • الرقم المعرف:
      10.1371/journal.pone.0287979
    • الدخول الالكتروني :
      http://dx.doi.org/10.1371/journal.pone.0287979
      https://dx.plos.org/10.1371/journal.pone.0287979
    • Rights:
      http://creativecommons.org/licenses/by/4.0/
    • الرقم المعرف:
      edsbas.9B3BD0BB