File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/TPAMI.2020.3025062
- PMID: 32946383
- WOS: WOS:000982475600029
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Fashion Retrieval via Graph Reasoning Networks on a Similarity Pyramid
Title | Fashion Retrieval via Graph Reasoning Networks on a Similarity Pyramid |
---|---|
Authors | |
Keywords | Fashion retrieval graph reasoning similarity pyramid |
Issue Date | 2020 |
Publisher | Institute of Electrical and Electronics Engineers. The Journal's web site is located at https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=34 |
Citation | IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, Epub 2020-09-18 How to Cite? |
Abstract | Matching clothing images from customers and online shopping stores has rich applications in E-commerce. Existing algorithms mostly encode an image as a global feature vector and perform retrieval via global representation matching. However, discriminative local information on clothes is submerged in this global representation, resulting in sub-optimal performance. To address this issue, we propose a novel Graph Reasoning Network (GRNet) on a Similarity Pyramid, which learns similarities between a query and a gallery cloth by using both initially pairwise multi-scale feature representations and matching propagation for unaligned ones. The query local representations at each scale are aligned with those of the gallery via a novel adaptive window pooling module. The similarity pyramid is represented by a Graph of similarity, where nodes represent similarities between clothing components at different scales, and the final matching score is obtained by message passing along edges. In GRNet, graph reasoning is solved by training a graph convolutional network, enabling to align salient clothing components to improve clothing retrieval. To facilitate future researches, we introduce a new benchmark FindFashion, containing rich annotations of bounding boxes, views, occlusions, and cropping. Extensive experiments show GRNet obtains new state-of-the-art results on three challenging benchmarks and all settings on FindFashion. |
Persistent Identifier | http://hdl.handle.net/10722/301200 |
ISSN | 2023 Impact Factor: 20.8 2023 SCImago Journal Rankings: 6.158 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | GAO, Y | - |
dc.contributor.author | KUANG, Z | - |
dc.contributor.author | LI, G | - |
dc.contributor.author | Luo, P | - |
dc.contributor.author | LIN, L | - |
dc.contributor.author | ZHANG, W | - |
dc.date.accessioned | 2021-07-27T08:07:36Z | - |
dc.date.available | 2021-07-27T08:07:36Z | - |
dc.date.issued | 2020 | - |
dc.identifier.citation | IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, Epub 2020-09-18 | - |
dc.identifier.issn | 0162-8828 | - |
dc.identifier.uri | http://hdl.handle.net/10722/301200 | - |
dc.description.abstract | Matching clothing images from customers and online shopping stores has rich applications in E-commerce. Existing algorithms mostly encode an image as a global feature vector and perform retrieval via global representation matching. However, discriminative local information on clothes is submerged in this global representation, resulting in sub-optimal performance. To address this issue, we propose a novel Graph Reasoning Network (GRNet) on a Similarity Pyramid, which learns similarities between a query and a gallery cloth by using both initially pairwise multi-scale feature representations and matching propagation for unaligned ones. The query local representations at each scale are aligned with those of the gallery via a novel adaptive window pooling module. The similarity pyramid is represented by a Graph of similarity, where nodes represent similarities between clothing components at different scales, and the final matching score is obtained by message passing along edges. In GRNet, graph reasoning is solved by training a graph convolutional network, enabling to align salient clothing components to improve clothing retrieval. To facilitate future researches, we introduce a new benchmark FindFashion, containing rich annotations of bounding boxes, views, occlusions, and cropping. Extensive experiments show GRNet obtains new state-of-the-art results on three challenging benchmarks and all settings on FindFashion. | - |
dc.language | eng | - |
dc.publisher | Institute of Electrical and Electronics Engineers. The Journal's web site is located at https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=34 | - |
dc.relation.ispartof | IEEE Transactions on Pattern Analysis and Machine Intelligence | - |
dc.rights | IEEE Transactions on Pattern Analysis and Machine Intelligence. Copyright © Institute of Electrical and Electronics Engineers. | - |
dc.rights | ©20xx IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. | - |
dc.subject | Fashion retrieval | - |
dc.subject | graph reasoning | - |
dc.subject | similarity pyramid | - |
dc.title | Fashion Retrieval via Graph Reasoning Networks on a Similarity Pyramid | - |
dc.type | Article | - |
dc.identifier.email | Luo, P: pluo@hku.hk | - |
dc.identifier.authority | Luo, P=rp02575 | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/TPAMI.2020.3025062 | - |
dc.identifier.pmid | 32946383 | - |
dc.identifier.hkuros | 323756 | - |
dc.identifier.volume | Epub 2020-09-18 | - |
dc.identifier.isi | WOS:000982475600029 | - |
dc.publisher.place | United States | - |