{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T16:06:02Z","timestamp":1770739562632,"version":"3.49.0"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62407018"],"award-info":[{"award-number":["62407018"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2023M741305"],"award-info":[{"award-number":["2023M741305"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Fujian Province of China","award":["2025J01177"],"award-info":[{"award-number":["2025J01177"]}]},{"DOI":"10.13039\/501100012559","name":"Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning","doi-asserted-by":"publisher","award":["2025AISL004"],"award-info":[{"award-number":["2025AISL004"]}],"id":[{"id":"10.13039\/501100012559","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans.Inform.Forensic Secur."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tifs.2026.3658987","type":"journal-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T20:58:37Z","timestamp":1769633917000},"page":"1829-1841","source":"Crossref","is-referenced-by-count":0,"title":["Consensus Labeling: Prompt-Guided Clustering Refinement for Weakly Supervised Text-Based Person Re-Identification"],"prefix":"10.1109","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3770-8892","authenticated-orcid":false,"given":"Chengji","family":"Wang","sequence":"first","affiliation":[{"name":"Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning and the National Language Resources Monitoring and Research Center for Network Media, School of Computer Science, Central China Normal University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2829-8672","authenticated-orcid":false,"given":"Weizhi","family":"Nie","sequence":"additional","affiliation":[{"name":"Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning and the National Language Resources Monitoring and Research Center for Network Media, School of Computer Science, Central China Normal University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5536-5224","authenticated-orcid":false,"given":"Hongbo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Huaqiao University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1314-4957","authenticated-orcid":false,"given":"Hao","family":"Sun","sequence":"additional","affiliation":[{"name":"Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning and the National Language Resources Monitoring and Research Center for Network Media, School of Computer Science, Central China Normal University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3989-7655","authenticated-orcid":false,"given":"Mang","family":"Ye","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.551"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2025.3565392"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2025.3574970"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2025.3586488"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2025.3573185"},{"key":"ref6","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":"ref7","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2025.3536608"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00273"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10688072"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3337653"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3327924"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3285426"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-021-06734-9"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01120"},{"key":"ref16","article-title":"CPCL: Cross-modal prototypical contrastive learning for weakly supervised text-based person retrieval","author":"Zhao","year":"2024","journal-title":"arXiv:2401.10011"},{"key":"ref17","first-page":"17612","article-title":"Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liang"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00402"},{"key":"ref19","article-title":"Cross the gap: Exposing the intra-modal misalignment in CLIP via modality inversion","author":"Mistretta","year":"2025","journal-title":"arXiv:2502.04263"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548028"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02078"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-8858-3_33"},{"key":"ref23","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2022","journal-title":"arXiv:2208.01618"},{"key":"ref24","first-page":"18661","article-title":"Supervised contrastive learning","volume-title":"Proc. NIPS","author":"Khosla"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3054775"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.08.058"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/148"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3449222"},{"key":"ref29","article-title":"Semantically self-aligned network for text-to-image part-aware person re-identification","author":"Ding","year":"2021","journal-title":"arXiv:2107.12666"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475369"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref32","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref33","first-page":"1047","article-title":"Cross-modal generation and alignment via attribute-guided prompt for unsupervised text-based person retrieval","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Li"},{"key":"ref34","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":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28298"},{"key":"ref36","article-title":"An empirical study of validating synthetic data for text-based person retrieval","author":"Cao","year":"2025","journal-title":"arXiv:2503.22171"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714788"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00324"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1250"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.346"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25225"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01407"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01850"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01642"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.5555\/3001460.3001507"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413807"},{"key":"ref50","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1703.07737"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3329220"},{"key":"ref53","article-title":"Prompt decoupling for text-to-image person re-identification","author":"Li","year":"2024","journal-title":"arXiv:2401.02173"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i1.27801"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2024.3417251"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3410129"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3652583.3658054"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548057"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02568"},{"issue":"86","key":"ref60","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Information Forensics and Security"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10206\/11313711\/11366996.pdf?arnumber=11366996","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T21:03:57Z","timestamp":1770671037000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11366996\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/tifs.2026.3658987","relation":{},"ISSN":["1556-6013","1556-6021"],"issn-type":[{"value":"1556-6013","type":"print"},{"value":"1556-6021","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}