Person Re-identification Method Using Text Description Through CLIP
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, K. | - |
dc.contributor.author | Kim, M.-J. | - |
dc.contributor.author | Kim, H. | - |
dc.contributor.author | Park, S. | - |
dc.contributor.author | Paik, Joon Ki | - |
dc.date.accessioned | 2023-09-15T02:49:17Z | - |
dc.date.available | 2023-09-15T02:49:17Z | - |
dc.date.issued | 2023 | - |
dc.identifier.issn | 0000-0000 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/67636 | - |
dc.description.abstract | A typical person re-identification (Re-ID) system works by taking person image as a query to find the most similar person among the images inside the gallery. From this, the system's performance depends heavily on the quality of the query image. We see the hint to overcome this limitation in recent surprising progress in multi-modal learning between vision and language. In this context, this paper proposes a person re-identification method that utilizes text guidance via the Contrastive Language-Image Pre-training (CLIP). To fully utilize CLIP, we show how to transfer their knowledge to person Re-ID network. Experimental results prove the superior performance of our method on person Re-ID. © 2023 IEEE. | - |
dc.language | 영어 | - |
dc.language.iso | ENG | - |
dc.publisher | Institute of Electrical and Electronics Engineers Inc. | - |
dc.title | Person Re-identification Method Using Text Description Through CLIP | - |
dc.type | Article | - |
dc.identifier.doi | 10.1109/ICEIC57457.2023.10049924 | - |
dc.identifier.bibliographicCitation | 2023 International Conference on Electronics, Information, and Communication, ICEIC 2023 | - |
dc.description.isOpenAccess | N | - |
dc.identifier.scopusid | 2-s2.0-85150426713 | - |
dc.citation.title | 2023 International Conference on Electronics, Information, and Communication, ICEIC 2023 | - |
dc.type.docType | Conference Paper | - |
dc.subject.keywordAuthor | Multi-modal learning | - |
dc.subject.keywordAuthor | Person Re-identification | - |
dc.subject.keywordAuthor | Text based person search | - |
dc.description.journalRegisteredClass | scopus | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
84, Heukseok-ro, Dongjak-gu, Seoul, Republic of Korea (06974)02-820-6194
COPYRIGHT 2019 Chung-Ang University All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.