Table of Content

Open Access iconOpen Access

REVIEW

crossmark

Review of GAN-Based Person Re-Identification

Zhiyuan Luo*

School of Computer & Software, Nanjing University of Information Science and Technology, Nanjing, 210044, China

* Corresponding Author: Zhiyuan Luo. Email: email

Journal of New Media 2021, 3(1), 11-17. https://doi.org/10.32604/jnm.2021.018027

Abstract

Person re-ID is becoming increasingly popular in the field of modern surveillance. The purpose of person re-ID is to retrieve person of interests in non-overlapping multi-camera surveillance system. Due to the complexity of the surveillance scene, the person images captured by cameras often have problems such as size variation, rotation, occlusion, illumination difference, etc., which brings great challenges to the study of person re-ID. In recent years, studies based on deep learning have achieved great success in person re-ID. The improvement of basic networks and a large number of studies on the influencing factors have greatly improved the accuracy of person re-ID. Recently, some studies utilize GAN to tackle the domain adaptation task by transferring person images of source domain to the style of target domain and have achieved state of the art result in person re-ID.

Keywords


Cite This Article

APA Style
Luo, Z. (2021). Review of gan-based person re-identification. Journal of New Media, 3(1), 11-17. https://doi.org/10.32604/jnm.2021.018027
Vancouver Style
Luo Z. Review of gan-based person re-identification. J New Media . 2021;3(1):11-17 https://doi.org/10.32604/jnm.2021.018027
IEEE Style
Z. Luo, “Review of GAN-Based Person Re-Identification,” J. New Media , vol. 3, no. 1, pp. 11-17, 2021. https://doi.org/10.32604/jnm.2021.018027



cc Copyright © 2021 The Author(s). Published by Tech Science Press.
This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
  • 1865

    View

  • 1209

    Download

  • 0

    Like

Share Link