{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T05:47:15Z","timestamp":1763704035603,"version":"3.45.0"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"BK21 FOUR Program"},{"name":"Ministry of Education, South Korea","award":["4120240214912"],"award-info":[{"award-number":["4120240214912"]}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Korean Government","award":["2021R1A2C2093785"],"award-info":[{"award-number":["2021R1A2C2093785"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3630632","type":"journal-article","created":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T18:49:34Z","timestamp":1762800574000},"page":"192403-192415","source":"Crossref","is-referenced-by-count":0,"title":["Fashion Image Retrieval With Vision\u2013Language Model Guided Fine-Grained Textual Attributes and Cross-Domain Contrastive Optimization"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8322-5819","authenticated-orcid":false,"given":"Eojin","family":"Kim","sequence":"first","affiliation":[{"name":"Department of Industrial Engineering, Seoul National University, Gwanak-gu, Seoul, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7584-1061","authenticated-orcid":false,"given":"Sangyeop","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Industrial Engineering, Seoul National University, Gwanak-gu, Seoul, Republic of Korea"}]},{"given":"Cholhwan","family":"Jung","sequence":"additional","affiliation":[{"name":"Department of Industrial Engineering, Seoul National University, Gwanak-gu, Seoul, Republic of Korea"}]},{"given":"Youngseok","family":"Hahm","sequence":"additional","affiliation":[{"name":"Department of Industrial Engineering, Seoul National University, Gwanak-gu, Seoul, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1695-1973","authenticated-orcid":false,"given":"Sungzoon","family":"Cho","sequence":"additional","affiliation":[{"name":"Department of Industrial Engineering, Seoul National University, Gwanak-gu, Seoul, Republic of Korea"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2022.104568"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/access.2024.3368612"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.104899"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.105097"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2025.107552"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2023.103540"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/access.2019.2922554"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2021.104097"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3057892"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2023.103434"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.180"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.124"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2958756"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-63820-7_33"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-92273-3_18"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.382"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.163"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00804"},{"key":"ref20","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-23052-9"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01065"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00185"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.125688"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref29","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia"},{"key":"ref30","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh"},{"key":"ref31","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Li"},{"key":"ref32","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref33","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Alayrac"},{"key":"ref34","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Liu"},{"key":"ref35","article-title":"EVA-CLIP-18B: Scaling CLIP to 18 billion parameters","author":"Sun","year":"2024","journal-title":"arXiv:2402.04252"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2024.103968"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248101"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP.2017.8305144"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_44"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00316"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s42979-023-02351-6"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00398"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_19"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-022-00750-5"},{"key":"ref45","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017","journal-title":"arXiv:1708.07747"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11235935.pdf?arnumber=11235935","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T05:39:00Z","timestamp":1763703540000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11235935\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3630632","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}