{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T04:52:00Z","timestamp":1781931120107,"version":"3.54.5"},"reference-count":74,"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":[{"name":"National Key Research and Development Program of China","award":["2025YFC3811300"],"award-info":[{"award-number":["2025YFC3811300"]}]},{"name":"National Key Research and Development Program of China","award":["2023YFA1008500"],"award-info":[{"award-number":["2023YFA1008500"]}]},{"name":"National Key Research and Development Program of China","award":["2025ZD1601300"],"award-info":[{"award-number":["2025ZD1601300"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376070"],"award-info":[{"award-number":["62376070"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076195"],"award-info":[{"award-number":["62076195"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22B2035"],"award-info":[{"award-number":["U22B2035"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62402138"],"award-info":[{"award-number":["62402138"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Fundamental and Interdisciplinary Disciplines Breakthrough Plan of the Ministry of Education of China","award":["JYB2025XDXM901"],"award-info":[{"award-number":["JYB2025XDXM901"]}]},{"name":"Suzhou Key Core Technology Project","award":["SYG2025118"],"award-info":[{"award-number":["SYG2025118"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3699088","type":"journal-article","created":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T19:54:34Z","timestamp":1780948474000},"page":"6123-6138","source":"Crossref","is-referenced-by-count":0,"title":["Language Supervised Multi-Camera Multi-Object Tracking"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-3757-7114","authenticated-orcid":false,"given":"Kaige","family":"Mao","sequence":"first","affiliation":[{"name":"Faculty of Computing, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0611-0636","authenticated-orcid":false,"given":"Xiaopeng","family":"Hong","sequence":"additional","affiliation":[{"name":"Faculty of Computing, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9660-3636","authenticated-orcid":false,"given":"Xiaopeng","family":"Fan","sequence":"additional","affiliation":[{"name":"Faculty of Computing, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3330-783X","authenticated-orcid":false,"given":"Wangmeng","family":"Zuo","sequence":"additional","affiliation":[{"name":"Faculty of Computing, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/PETS-WINTER.2009.5399556"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.461"},{"key":"ref3","article-title":"MOT16: A benchmark for multi-object tracking","author":"Milan","year":"2016","journal-title":"arXiv:1603.00831"},{"key":"ref4","article-title":"MOT20: A benchmark for multi object tracking in crowded scenes","author":"Dendorfer","year":"2020","journal-title":"arXiv:2003.09003"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11190"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01357"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00866"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00922"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00484"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02108"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02530"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00285"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02765"},{"key":"ref15","article-title":"NEXT: Multi-grained mixture of experts via text-modulation for multi-modal object re-identification","author":"Li","year":"2025","journal-title":"arXiv:2505.20001"},{"key":"ref16","first-page":"570","article-title":"A framework for multiple-instance learning","volume":"10","author":"Maron","year":"1997","journal-title":"Proc. NeurIPS"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01393"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3261752"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00689"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475177"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28553"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijleo.2013.07.089"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0943-0"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01314-1"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2980070"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3572810"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72761-0_16"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3139178"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00900"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3131936"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3078124"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3207223"},{"key":"ref33","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":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01642"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01355"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02217"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3553290"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01406"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01810"},{"key":"ref41","first-page":"3205","article-title":"Type-to-track: Retrieve any object via prompt-based tracking","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kitani"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128553"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447535"},{"key":"ref44","article-title":"MLS-Track: Multilevel semantic interaction in RMOT","author":"Ma","year":"2024","journal-title":"arXiv:2404.12031"},{"key":"ref45","article-title":"Bootstrapping referring multi-object tracking","author":"Zhang","year":"2024","journal-title":"arXiv:2406.05039"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i2.32219"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9780511811685"},{"key":"ref48","first-page":"1263","article-title":"Neural message passing for quantum chemistry","volume-title":"Proc. 34th Int. Conf. Mach. Learning","volume":"70","author":"Gilmer"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/0169-7439(87)80084-9"},{"key":"ref51","volume-title":"Principal Component Analysis","author":"Jolliffe","year":"2002"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00528"},{"key":"ref53","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475310"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1155\/2008\/246309"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_2"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01375-2"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00380"},{"key":"ref59","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. ICLR","author":"Kingma"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"issue":"86","key":"ref61","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00917"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.21"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00163"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00018"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00071"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3034435"},{"key":"ref68","first-page":"107984","article-title":"YOLOv10: Real-time end-to-end object detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3034233"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261659"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3586118"},{"key":"ref72","first-page":"5554","article-title":"Learning clustering-based prototypes for compositional zero-shot learning","volume-title":"Proc. ICLR","author":"Qu"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3629609"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3523802"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11554242.pdf?arnumber=11554242","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T04:34:07Z","timestamp":1781930047000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11554242\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3699088","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}