{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T16:18:04Z","timestamp":1778948284428,"version":"3.51.4"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"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":["U23B2013"],"award-info":[{"award-number":["U23B2013"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shaanxi Provincial Key Research and Development Program","award":["2021KWZ-03"],"award-info":[{"award-number":["2021KWZ-03"]}]},{"name":"Shaanxi Provincial Key Research and Development Program","award":["2024GX-YBXM-117"],"award-info":[{"award-number":["2024GX-YBXM-117"]}]},{"DOI":"10.13039\/501100017596","name":"Natural Science Basic Research Program of Shaanxi","doi-asserted-by":"publisher","award":["2021JCW-03"],"award-info":[{"award-number":["2021JCW-03"]}],"id":[{"id":"10.13039\/501100017596","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1109\/tcsvt.2024.3392831","type":"journal-article","created":{"date-parts":[[2024,4,23]],"date-time":"2024-04-23T20:07:31Z","timestamp":1713902851000},"page":"8242-8252","source":"Crossref","is-referenced-by-count":15,"title":["Fine-Granularity Alignment for Text-Based Person Retrieval Via Semantics-Centric Visual Division"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9489-5199","authenticated-orcid":false,"given":"Zhimin","family":"Wei","sequence":"first","affiliation":[{"name":"School of Computer Science and Ningbo Institute, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0607-8605","authenticated-orcid":false,"given":"Zhipeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Ningbo Institute, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2938-6798","authenticated-orcid":false,"given":"Peng","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Ningbo Institute, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7077-3402","authenticated-orcid":false,"given":"Ji","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Ningbo Institute, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9218-9132","authenticated-orcid":false,"given":"Peng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Ningbo Institute, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2977-8057","authenticated-orcid":false,"given":"Yanning","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Ningbo Institute, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102201"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3339167"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3236636"},{"key":"ref4","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":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01180"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093640"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.551"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00225"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"issue":"1","key":"ref11","first-page":"1","article-title":"A system for video surveillance and monitoring","volume-title":"VSAM Final Rep.","volume":"2000","author":"Collins","year":"2000"},{"key":"ref12","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":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475369"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00648"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"},{"key":"ref16","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":"ref17","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/148"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_24"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413864"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00591"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00208"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.04.081"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.209"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2984883"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3068825"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548028"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547753"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108891"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548166"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00016"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref33","article-title":"Image as a foreign language: BEiT pretraining for all vision and vision-language tasks","author":"Wang","year":"2022","journal-title":"arXiv:2208.10442"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_42"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3310118"},{"issue":"8","key":"ref36","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2873599"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3043026"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3273719"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3037661"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2916167"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3073718"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3327924"},{"key":"ref45","article-title":"Exploiting the textual potential from vision-language pre-training for text-based person search","author":"Wang","year":"2023","journal-title":"arXiv:2303.04497"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25072-9_42"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6777"},{"key":"ref48","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics, Hum. Lang. Technol","volume":"1","author":"Devlin"},{"key":"ref49","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Jia"},{"key":"ref50","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","volume":"162","author":"Li"},{"key":"ref51","article-title":"Text-based person search with limited data","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Han"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3276167"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10700029\/10507050.pdf?arnumber=10507050","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T05:53:27Z","timestamp":1727762007000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10507050\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":53,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3392831","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9]]}}}