2021 IEEE International Conference on Image Processing

19-22 September 2021 • Anchorage, Alaska, USA

Imaging Without Borders

2021 IEEE International Conference on Image Processing

19-22 September 2021 • Anchorage, Alaska, USA

Login Paper Search My Schedule Paper Index Help

My ICIP 2021 Schedule

Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
  1. Create a login based on your email (takes less than one minute)
  2. Perform 'Paper Search'
  3. Select papers that you desire to save in your personalized schedule
  4. Click on 'My Schedule' to see the current list of selected papers
  5. Click on 'Printable Version' to create a separate window suitable for printing (the header and menu will appear, but will not actually print)

Paper Detail

Paper IDARS-4.5
Paper Title PCNet: Parallelly Conquer the Large Variance of Person Re-identification
Authors Jianyuan Wang, Beihang University, China; Meiyue You, Beijing University of Chemical Technology, China; Biao Leng, Ming Jiang, Guanglu Song, Beihang University, China
SessionARS-4: Re-Identification and Retrieval
LocationArea I
Session Time:Wednesday, 22 September, 08:00 - 09:30
Presentation Time:Wednesday, 22 September, 08:00 - 09:30
Presentation Poster
Topic Image and Video Analysis, Synthesis, and Retrieval: Image & Video Storage and Retrieval
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Abstract 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), Globel 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.