Scholarlink

Person re-identification (ReID) (Zhou et al. 2019; Wang et al. 2018a; Quan et al. 2019) is a significant research area in computer vision, focused on identifying specific individuals across different camera views or video sequences. Recent advancements in deep learning, particularly with convolutional neural networks (CNNs), have led to remarkable progress in this field. These CNN-based models learn unique features for each input image, aiming to minimize the similarity distance between images of the same identity. ReID presents greater challenges than face recognition.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Auto-Scale Single-Branch Architecture Search for Person Re-identification

  • 章节

  • 发表日期：

    2026年

查看全文
  • Hongyang Gu,
  • Yao Ding,
  • Xiaogang Yang,
  • Ruitao Lu,
  • Lei Pu,
  • Siming Han

摘要

Person re-identification (ReID) (Zhou et al. 2019; Wang et al. 2018a; Quan et al. 2019) is a significant research area in computer vision, focused on identifying specific individuals across different camera views or video sequences. Recent advancements in deep learning, particularly with convolutional neural networks (CNNs), have led to remarkable progress in this field. These CNN-based models learn unique features for each input image, aiming to minimize the similarity distance between images of the same identity. ReID presents greater challenges than face recognition.