MULTI-VIEW JOINT LEARNING NETWORK FOR PEDESTRIAN GENDER CLASSIFICATION

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review

View graph of relations

Author(s)

  • Lei Cai
  • Huanqiang Zeng
  • Jianqing Zhu
  • Jiuwen Cao
  • Canhui Cai

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publication2017 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS) : Proceedings
PublisherIEEE
Pages23-27
ISBN (Electronic)9781538621592
ISBN (Print)9781538621608
Publication statusPublished - Nov 2017

Publication series

NameInternational Symposium on Intelligent Signal Processing and Communication Systems ISPACS

Conference

Title25th IEEE International Symposium on Intelligent Signal Processing and Communication Systems 2017 (ISPACS 2017)
LocationWanda Realm Xiamen North Bay Hotel
PlaceChina
CityXiamen
Period6 - 9 November 2017

Abstract

Since the object occlusion, view variation, arbitrary shape of pedestrian, etc., are inherited in the pedestrian images, the pedestrian gender classification is an extremely challenging task in the object recognition field. To address this problem, an effective multi-view joint learning network (MJLN) is proposed for pedestrian gender classification. Based on the observation that the view variation of pedestrian will affect the judgment of pedestrian gender, the proposed MJLN simultaneously performs pedestrian gender learning and pedestrian view learning. Consequently, the determination of pedestrian view (i.e., frontal, rear, and left/right profile) obtained by the pedestrian view learning module will effectively assist the pedestrian gender learning module to yield a more robust and distinguishable feature so as to improve the gender classification performance. Extensive experiments on multiple challenging pedestrian datasets, which includes CUHK, VIPeR, GRID, PRID, and MIT, have demonstrated that the proposed MJLN can effectively promote the gender classification performance, and outperforms multiple state-of-the-art methods.

Research Area(s)

  • gender learning module, multiview joint learning network, Pedestrian gender classification, view learning module

Citation Format(s)

MULTI-VIEW JOINT LEARNING NETWORK FOR PEDESTRIAN GENDER CLASSIFICATION. / Cai, Lei; Zeng, Huanqiang; Zhu, Jianqing; Cao, Jiuwen; Hou, Junhui; Cai, Canhui.

2017 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS) : Proceedings. IEEE, 2017. p. 23-27 (International Symposium on Intelligent Signal Processing and Communication Systems ISPACS).

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review