{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T11:37:50Z","timestamp":1759837070887,"version":"build-2065373602"},"reference-count":55,"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":"\u201cRegional Innovation System and Education (RISE)\u201d through the Ulsan RISE Center"},{"name":"Ministry of Education"},{"name":"Ulsan Metropolitan City, Republic of Korea","award":["2025-RISE-07-001"],"award-info":[{"award-number":["2025-RISE-07-001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3584377","type":"journal-article","created":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T13:39:16Z","timestamp":1751290756000},"page":"114911-114922","source":"Crossref","is-referenced-by-count":2,"title":["Text-Guided Visual Representation Learning via Cross-Modal Fusion for Person Re-Identification"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9135-3888","authenticated-orcid":false,"given":"Ge","family":"Cao","sequence":"first","affiliation":[{"name":"Department of Electrical, Electronic and Computer Engineering, University of Ulsan, Ulsan, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4194-8597","authenticated-orcid":false,"given":"Qing","family":"Tang","sequence":"additional","affiliation":[{"name":"Data Science Group, INTERX, Ulsan, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7411-0697","authenticated-orcid":false,"given":"Xuan-Thuy","family":"Vo","sequence":"additional","affiliation":[{"name":"Department of Electrical, Electronic and Computer Engineering, University of Ulsan, Ulsan, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1553-7631","authenticated-orcid":false,"given":"Adri","family":"Priadana","sequence":"additional","affiliation":[{"name":"Department of Electrical, Electronic and Computer Engineering, University of Ulsan, Ulsan, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8266-0536","authenticated-orcid":false,"given":"Tien-Dat","family":"Tran","sequence":"additional","affiliation":[{"name":"Department of Electrical, Electronic and Computer Engineering, University of Ulsan, Ulsan, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4937-7082","authenticated-orcid":false,"given":"Kang-Hyun","family":"Jo","sequence":"additional","affiliation":[{"name":"Department of Electrical, Electronic and Computer Engineering, University of Ulsan, Ulsan, South Korea"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3203397"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2020.3040881"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3059250"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3318007"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2019.2923653"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00380"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00325"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00666"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01844"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25225"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00016"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.133"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.405"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00063"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01474"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20155"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00471"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00715"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01358"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25180"},{"key":"ref22","article-title":"Learning transferable visual models from natural language supervision","volume-title":"arXiv:2103.00020","author":"Radford","year":"2021"},{"key":"ref23","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":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3134181"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_21"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"1","key":"ref29","first-page":"307","article-title":"Noise-contrastive estimation of unnormalized statistical models, with applications to natural image statistics","volume":"13","author":"Gutmann","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"ref30","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref31","article-title":"SimVLM: Simple visual language model pretraining with weak supervision","volume-title":"arXiv:2108.10904","author":"Wang","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01642"},{"key":"ref34","article-title":"Multimodal alignment and fusion: A survey","volume-title":"arXiv:2411.17040","author":"Li","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2189550"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403182"},{"key":"ref38","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":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3297391"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3300582"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1703.07737"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3496673"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26351-4_20"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref46","article-title":"Contrastive learning with hard negative samples","volume-title":"arXiv:2010.04592","author":"Robinson","year":"2020"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613460"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.389"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00106"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01886"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2024.3520304"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3379577"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00069"},{"key":"ref54","article-title":"MLLMReID: Multimodal large language model-based person re-identification","volume-title":"arXiv:2401.13201","author":"Yang","year":"2024"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00084"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11059954.pdf?arnumber=11059954","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T13:05:16Z","timestamp":1759237516000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11059954\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3584377","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}