{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T02:43:43Z","timestamp":1783737823431,"version":"3.55.0"},"reference-count":62,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Natural Science Foundation of the Jiangsu Higher Education Institutions of China"},{"name":"Key Laboratory of New Generation Artificial Intelligence Technology & Its Interdisciplinary Applications (Southeast University), Ministry of Education, China"},{"name":"National Natural Science Foundation of China under Grants","award":["62176188"],"award-info":[{"award-number":["62176188"]}]},{"name":"National Natural Science Foundation of China under Grants","award":["62476188"],"award-info":[{"award-number":["62476188"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tip.2025.3607637","type":"journal-article","created":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T17:36:12Z","timestamp":1758044172000},"page":"5888-5903","source":"Crossref","is-referenced-by-count":4,"title":["Semi-Supervised Text-Based Person Search"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2627-9201","authenticated-orcid":false,"given":"Daming","family":"Gao","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Soochow University, Suzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Bai","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6628-0370","authenticated-orcid":false,"given":"Min","family":"Cao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Soochow University, Suzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Dou","sequence":"additional","affiliation":[{"name":"Meituan, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3895-5510","authenticated-orcid":false,"given":"Min","family":"Zhang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.551"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3376373"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3054775"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2898940"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/759"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612285"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00273"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i1.27801"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746846"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_24"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01069"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01120"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093394"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2897684"},{"key":"ref17","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":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3069908"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/62"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.04.081"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2984883"},{"key":"ref23","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":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6777"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00165"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.454"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3243316"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.11.025"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2891895"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2983600"},{"key":"ref31","first-page":"29406","article-title":"Learning with noisy correspondence for cross-modal matching","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Huang"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547922"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00726"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02568"},{"key":"ref35","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref36","first-page":"353","article-title":"GLUE: A multi-task benchmark and analysis platform for natural language understanding","volume-title":"Proc. EMNLP Workshop BlackboxNLP, Analyzing Interpreting Neural Netw. NLP","author":"Wang"},{"key":"ref37","first-page":"2383","article-title":"SQuAD: 100,000+ questions for machine comprehension of text","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Rajpurkar"},{"key":"ref38","first-page":"93","article-title":"SWAG: A large-scale adversarial dataset for grounded commonsense inference","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Zellers"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02240"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref42","first-page":"2304","article-title":"MentorNet: Learning data-driven curriculum for very deep neural networks on corrupted labels","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Jiang"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_9"},{"key":"ref44","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","volume-title":"Proc. 32nd Int. Conf. Mach. Learn. (ICML)","author":"Xu"},{"key":"ref45","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. 40th Int. Conf. Mach. Learn. (ICML)","author":"Li"},{"key":"ref46","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref47","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":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475369"},{"key":"ref49","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Kingma"},{"key":"ref50","first-page":"1162","article-title":"Competence-based curriculum learning for neural machine translation","volume-title":"Proc. Conf. North","author":"Platanios"},{"key":"ref51","first-page":"7514","article-title":"CLIPScore: A reference-free evaluation metric for image captioning","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Hessel"},{"key":"ref52","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":"ref53","first-page":"751","article-title":"From baby steps to leapfrog: How \u2019less is more\u2019 in unsupervised dependency parsing","volume-title":"Proc. Human Lang. Technol., Annu. Conf. North Amer. Chapter Assoc. Comput. Linguistics","author":"Spitkovsky"},{"key":"ref54","first-page":"3679","article-title":"The curious case of neural text degeneration","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Holtzman"},{"key":"ref55","first-page":"56","article-title":"Beam search strategies for neural machine translation","volume-title":"Proc. 1st Workshop Neural Mach. Transl.","author":"Freitag"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548028"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3327924"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02078"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611709"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01621"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/11165023.pdf?arnumber=11165023","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T12:29:46Z","timestamp":1759235386000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11165023\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3607637","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}