Full metadata record

DC FieldValueLanguage
dc.contributor.author박성기-
dc.contributor.author김창환-
dc.contributor.author이장우-
dc.date.accessioned2021-06-09T04:23:39Z-
dc.date.available2021-06-09T04:23:39Z-
dc.date.issued2019-05-
dc.identifier.citationVOL 25, NO 5-469-
dc.identifier.issn1976-5622-
dc.identifier.other54076-
dc.identifier.urihttps://pubs.kist.re.kr/handle/201004/70678-
dc.description.abstractMost current gait recognition approaches based on convolution neural networks (CNNs) do not learn the discriminative features of separable inter-class differences resulting from cross-view data. To improve this discriminative ability, this paper proposes a network that reduces intra-class variation using a center loss function for view-invariant gait recognition. The proposed method achieved 92% accuracy using OU-MVLP, the largest existing gait recognition dataset. Furthermore, a network trained using the OU-MVLP achieved 95% accuracy with the OU-LP . These results demonstrate that the proposed method offers a good generalization performance.-
dc.publisher제어로봇시스템학회논문지-
dc.titleCross-view Gait Identification based on Convolution Neural Network with Joint Loss Function-
dc.typeArticle-
dc.relation.page463469-
Appears in Collections:
KIST Publication > Article
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