跳到主要导航 跳到搜索 跳到主要内容

PCNET: PARALLELLY CONQUER THE LARGE VARIANCE OF PERSON RE-IDENTIFICATION

  • Jianyuan Wang
  • , Meiyue You
  • , Biao Leng*
  • , Ming Jiang
  • , Guanglu Song
  • *此作品的通讯作者
  • Beihang University
  • Beijing University of Chemical Technology

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

Person re-identification has a wide range of applications, and many state-of-the-art methods are proposed to solve the problem under specific scenarios. However, it is still a challenging issue because of the large variance in practical applications, such as pose variations, misalignment, and image noises. In this paper, Parallelly Conquer Net (PCNet) is proposed to deal with large variance in a parallel manner. PCNet consists of three module: Pose Adaptation Module (PAM), Global Alignment Module (GAM), and Pixel-Wised Attention Module (PWAM). Each module is designed to deal with a sub-variance independently. Furthermore, the generated features are aggregated by parallel branches to utilize complementary information among them. Extensive experiments on three benchmarks (Market-1501, DukeMTMC-reID, and CUHK03) demonstrate the effectiveness of the method. The results show that PCNet can significantly improve the performance of person re-identification.

源语言英语
主期刊名2021 IEEE International Conference on Image Processing, ICIP 2021 - Proceedings
出版商IEEE Computer Society
2368-2372
页数5
ISBN(电子版)9781665441155
DOI
出版状态已出版 - 2021
活动28th IEEE International Conference on Image Processing, ICIP 2021 - Anchorage, 美国
期限: 19 9月 202122 9月 2021

出版系列

姓名Proceedings - International Conference on Image Processing, ICIP
2021-September
ISSN(印刷版)1522-4880

会议

会议28th IEEE International Conference on Image Processing, ICIP 2021
国家/地区美国
Anchorage
时期19/09/2122/09/21

学术指纹

探究 'PCNET: PARALLELLY CONQUER THE LARGE VARIANCE OF PERSON RE-IDENTIFICATION' 的科研主题。它们共同构成独一无二的学术指纹。

引用此