Show simple item record

dc.contributor.authorKınlı, Osman Furkan
dc.contributor.authorÖzcan, Barış
dc.contributor.authorKıraç, Mustafa Furkan
dc.date.accessioned2020-09-11T08:40:24Z
dc.date.available2020-09-11T08:40:24Z
dc.date.issued2019
dc.identifier.isbn978-1-7281-5023-9
dc.identifier.issn2473-9936en_US
dc.identifier.urihttp://hdl.handle.net/10679/6940
dc.identifier.urihttps://ieeexplore.ieee.org/document/9022050
dc.description.abstractIn this study, we investigate in-shop clothing retrieval performance of densely-connected Capsule Networks with dynamic routing. To achieve this, we propose Triplet-based design of Capsule Network architecture with two different feature extraction methods. In our design, Stacked-convolutional (SC) and Residual-connected (RC) blocks are used to form the input of capsule layers. Experimental results show that both of our designs outperform all variants of the baseline study, namely FashionNet, without relying on the landmark information. Moreover, when compared to the SOTA architectures on clothing retrieval, our proposed Triplet Capsule Networks achieve comparable recall rates only with half of parameters used in the SOTA architectures.en_US
dc.language.isoengen_US
dc.publisherIEEEen_US
dc.relation.ispartof2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)
dc.rightsrestrictedAccess
dc.titleFashion image retrieval with capsule networksen_US
dc.typeConference paperen_US
dc.publicationstatusPublisheden_US
dc.contributor.departmentÖzyeğin University
dc.contributor.authorID(ORCID 0000-0002-9192-6583 & YÖK ID 283852) Kınlı, Furkan
dc.contributor.authorID(ORCID 0000-0001-9177-0489 & YÖK ID 124619) Kıraç, Furkan
dc.contributor.ozuauthorKınlı, Osman Furkan
dc.contributor.ozuauthorKıraç, Mustafa Furkan
dc.identifier.startpage3109en_US
dc.identifier.endpage3112en_US
dc.identifier.wosWOS:000554591603026
dc.identifier.doi10.1109/ICCVW.2019.00376en_US
dc.identifier.scopusSCOPUS:2-s2.0-85081642041
dc.contributor.ozugradstudentÖzcan, Barış
dc.relation.publicationcategoryConference Paper - International - Institutional Academic Staff and PhD Student


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record


Share this page