Show simple item record

dc.contributor.authorZhao, Yang
dc.contributor.authorShen, Chunhua
dc.contributor.authorYu, Xiaohan
dc.contributor.authorChen, Hao
dc.contributor.authorGao, Yongsheng
dc.contributor.authorXiong, Shengwu
dc.date.accessioned2021-03-15T23:40:42Z
dc.date.available2021-03-15T23:40:42Z
dc.date.issued2021
dc.identifier.issn0031-3203
dc.identifier.doi10.1016/j.patcog.2021.107938
dc.identifier.urihttp://hdl.handle.net/10072/403165
dc.description.abstractPerson retrieval is an important vision task, aiming at matching the images of the same person under various camera views. The key challenge of person retrieval lies in the large intra-class variations among the person images. Therefore, how to learn discriminative feature representations becomes the core problem. In this paper, we propose a deep part-aware representation learning method for person retrieval. First, an improved triplet loss is introduced such that the global feature representations from the same identity are closely clustered. Meanwhile, a localization branch is proposed to automatically localize those discriminative person-wise parts or regions, only using identity labels in a weakly supervised manner. Via the learning simultaneously guided by the global branch and the localization branch, the proposed method can further improve the performance for person retrieval. Through an extensive set of ablation studies, we verify that the localization branch and the improved triplet loss each contributes to the performance boosts of the proposed method. Our model obtains superior (or comparable) performance compared to state-of-the-art methods for person retrieval on the four public person retrieval datasets. On the CUHK03-labeled dataset, for instance, the performance increases from 73.0% mAP and 77.9% rank-1 accuracy to 80.8% (+7.8%) mAP and 83.9% (+6.0%) rank-1 accuracy.
dc.description.peerreviewedYes
dc.languageen
dc.publisherElsevier BV
dc.relation.ispartofjournalPattern Recognition
dc.subject.fieldofresearchArtificial Intelligence and Image Processing
dc.subject.fieldofresearchInformation Systems
dc.subject.fieldofresearchElectrical and Electronic Engineering
dc.subject.fieldofresearchcode0801
dc.subject.fieldofresearchcode0806
dc.subject.fieldofresearchcode0906
dc.titleLearning Deep Part-Aware Embedding for Person Retrieval
dc.typeJournal article
dc.type.descriptionC1 - Articles
dcterms.bibliographicCitationZhao, Y; Shen, C; Yu, X; Chen, H; Gao, Y; Xiong, S, Learning Deep Part-Aware Embedding for Person Retrieval, Pattern Recognition, 2021
dcterms.licensehttps://creativecommons.org/licenses/by-nc-nd/4.0/
dc.date.updated2021-03-15T22:09:49Z
dc.description.versionAccepted Manuscript (AM)
gro.description.notepublicThis publication has been entered in Griffith Research Online as an advanced online version.
gro.rights.copyright© 2021 Elsevier. Licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International Licence (http://creativecommons.org/licenses/by-nc-nd/4.0/) which permits unrestricted, non-commercial use, distribution and reproduction in any medium, providing that the work is properly cited.
gro.hasfulltextFull Text
gro.griffith.authorYu, Xiaohan
gro.griffith.authorZhao, Yang
gro.griffith.authorGao, Yongsheng


Files in this item

This item appears in the following Collection(s)

  • Journal articles
    Contains articles published by Griffith authors in scholarly journals.

Show simple item record