{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T19:04:03Z","timestamp":1773255843855,"version":"3.50.1"},"reference-count":64,"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"}]},{"DOI":"10.13039\/100017938","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\/100017938","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2025.3648582","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:04:36Z","timestamp":1768255476000},"page":"317-331","source":"Crossref","is-referenced-by-count":1,"title":["P-CLIP: Progressive Discrepancy Learning for One-Shot Text-to-Image Person Re-Identification"],"prefix":"10.1109","volume":"35","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, 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\/0000-0003-3700-0154","authenticated-orcid":false,"given":"Ming","family":"Dong","sequence":"additional","affiliation":[{"name":"School of Computer Science and Artificial Intelligence, Wuhan University of Technology, 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"}]},{"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, 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"}]},{"given":"Xingpeng","family":"Jiang","sequence":"additional","affiliation":[{"name":"Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning, 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"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.551"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3068825"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3337653"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3285426"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3327924"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00273"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02078"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3587575"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3574918"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01342"},{"key":"ref11","first-page":"27197","article-title":"Noisy-correspondence learning for text-to-image person re-identification","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Yang"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.113"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3504252"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.171"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2940684"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2891895"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3026625"},{"key":"ref18","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":"ref19","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alayrac"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/62"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.389"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.594"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00212"},{"key":"ref24","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-8858-3_33"},{"key":"ref28","article-title":"Contextual non-local alignment over full-scale representation for text-based person search","author":"Gao","year":"2021","journal-title":"arXiv:2101.03036"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/148"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_24"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548028"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3205216"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.08.058"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6777"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2972168"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-021-06734-9"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10688072"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i1.27801"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33091"},{"key":"ref40","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":"ref41","article-title":"Semi-supervised text-based person search","author":"Gao","year":"2024","journal-title":"arXiv:2404.18106"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28298"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714788"},{"key":"ref44","article-title":"An empirical study of validating synthetic data for text-based person retrieval","author":"Cao","year":"2025","journal-title":"arXiv:2503.22171"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58583-9_16"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.110060"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3340923"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3293130"},{"key":"ref49","article-title":"Corrections meet explanations: A unified framework for explainable grammatical error correction","author":"Ye","year":"2025","journal-title":"arXiv:2502.15261"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.711"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1080\/10447318.2024.2352932"},{"key":"ref52","first-page":"1","article-title":"Mask-enhanced autoregressive prediction: Pay less attention to learn more","volume-title":"Proc. 42nd Int. Conf. Mach. Learn.","author":"Zhuang"},{"key":"ref53","first-page":"1","article-title":"ExLM: Rethinking the impact of [MASK] tokens in masked language models","volume-title":"Proc. 42nd Int. Conf. Mach. Learn.","author":"Zheng"},{"key":"ref54","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"1","author":"Chen"},{"key":"ref55","first-page":"6827","article-title":"What makes for good views for contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Tian"},{"key":"ref56","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":"ref57","first-page":"10944","article-title":"What makes multi-modal learning better than single (provably)","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Huang"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ITW.2015.7133169"},{"key":"ref59","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":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475369"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3310118"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_42"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746846"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28433"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11333948.pdf?arnumber=11333948","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T21:10:20Z","timestamp":1770671420000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11333948\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3648582","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}