Full metadata record

DC FieldValueLanguage
dc.contributor.author김익재-
dc.contributor.authorHanjae Kim-
dc.contributor.authorSunghun Joung-
dc.contributor.authorKwanghoon Sohn-
dc.date.accessioned2021-07-29T15:30:02Z-
dc.date.available2021-07-29T15:30:02Z-
dc.date.issued2021-06-
dc.identifier.issn--
dc.identifier.other57149-
dc.identifier.urihttps://pubs.kist.re.kr/handle/201004/73527-
dc.description.abstractExisting person search methods integrate person detection and re-identification (re-ID) module into a unified system. Though promising results have been achieved, the misalignment problem, which commonly occurs in person search, limits the discriminative feature representation for re-ID. To overcome this limitation, we introduce a novel framework to learn the discriminative representation by utilizing prototype in OIM loss. Unlike conventional methods using prototype as a representation of person identity, we utilize it as guidance to allow the attention network to consistently highlight multiple instances across different poses. Moreover, we propose a new prototype update scheme with adaptive momentum to increase the discriminative ability across different instances. Extensive ablation experiments demonstrate that our method can significantly enhance the feature discriminative power, outperforming the state-ofthe-art results on two person search benchmarks including CUHK-SYSU and PRW.-
dc.publisherCVPR, IEEE conf. on Computer Vision and Pattern Recognition-
dc.subject재식별-
dc.subject사람 추적-
dc.subjectSaliency-
dc.titlePrototype-Guided Saliency Feature Learning for Person Search-
dc.typeConference Paper-
Appears in Collections:
KIST Publication > Conference Paper
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE