{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T21:56:54Z","timestamp":1776981414012,"version":"3.51.4"},"reference-count":54,"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306215"],"award-info":[{"award-number":["62306215"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Jiangsu Key Development Planning Project","award":["BE2023004-2"],"award-info":[{"award-number":["BE2023004-2"]}]},{"DOI":"10.13039\/501100001736","name":"Future Network Scientific Research Fund Project","doi-asserted-by":"publisher","award":["FNSRFP-2021-YB-15"],"award-info":[{"award-number":["FNSRFP-2021-YB-15"]}],"id":[{"id":"10.13039\/501100001736","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans.Inform.Forensic Secur."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tifs.2025.3573185","type":"journal-article","created":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T17:03:38Z","timestamp":1748019818000},"page":"5465-5477","source":"Crossref","is-referenced-by-count":8,"title":["Diverse Co-Saliency Feature Learning for Text-Based Person Retrieval"],"prefix":"10.1109","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8095-8141","authenticated-orcid":false,"given":"Shuai","family":"You","sequence":"first","affiliation":[{"name":"School of Internet of Things, Nanjing University of Posts and Telecommunications (NJUPT), Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4133-0028","authenticated-orcid":false,"given":"Cuiqun","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Anhui University, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1051-7217","authenticated-orcid":false,"given":"Yujian","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Computer Engineering, Jiangsu University of Technology, Changzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4062-4945","authenticated-orcid":false,"given":"Hai","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer, South China Normal University, Guangzhou, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7019-3942","authenticated-orcid":false,"given":"Yimu","family":"Ji","sequence":"additional","affiliation":[{"name":"School of Computer Science, NJUPT, Nanjing, 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":"National Engineering Research Center for Multimedia Software, Hubei Key Laboratory of Multimedia and Network Communication Engineering, Institute of Artificial Intelligence, 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\/TIFS.2024.3417251"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2024.3352408"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3318956"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2024.3465037"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3354575"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01452"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110981"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2984883"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_24"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6777"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3327924"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3344354"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02078"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25072-9_42"},{"key":"ref15","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":"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":"10.1109\/ICASSP43922.2022.9746846"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.04.081"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.551"},{"key":"ref20","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":"ref21","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":"ref22","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":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29789"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02519"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01524"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548166"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547753"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20370"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548028"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00165"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548057"},{"key":"ref32","article-title":"Progressive feature mining and external knowledge-assisted text-pedestrian image retrieval","author":"Li","year":"2023","journal-title":"arXiv:2308.11994"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00273"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i1.27801"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01621"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/62"},{"key":"ref38","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00495"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2973812"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3285426"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611709"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110481"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3372832"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445963"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3410129"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref52","article-title":"Calibrating cross-modal features for text-based person searching","author":"Wei","year":"2023","journal-title":"arXiv:2304.02278"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109636"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"}],"container-title":["IEEE Transactions on Information Forensics and Security"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10206\/10810755\/11014247.pdf?arnumber=11014247","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T05:10:10Z","timestamp":1749532210000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11014247\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/tifs.2025.3573185","relation":{},"ISSN":["1556-6013","1556-6021"],"issn-type":[{"value":"1556-6013","type":"print"},{"value":"1556-6021","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}