{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:13:14Z","timestamp":1778080394134,"version":"3.51.4"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003995","name":"Natural Science Foundation of Anhui Province","doi-asserted-by":"publisher","award":["2308085MF211"],"award-info":[{"award-number":["2308085MF211"]}],"id":[{"id":"10.13039\/501100003995","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Scientific Research Project of National University of Defense Technology","award":["zk19-15"],"award-info":[{"award-number":["zk19-15"]}]},{"DOI":"10.13039\/100012592","name":"Foundation of Army Artillery and Air Defense Academy of PLA","doi-asserted-by":"publisher","award":["PFXY220114001"],"award-info":[{"award-number":["PFXY220114001"]}],"id":[{"id":"10.13039\/100012592","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/tits.2024.3520103","type":"journal-article","created":{"date-parts":[[2024,12,27]],"date-time":"2024-12-27T19:32:10Z","timestamp":1735327930000},"page":"3659-3670","source":"Crossref","is-referenced-by-count":12,"title":["Vision-Language Tracking With CLIP and Interactive Prompt Learning"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2841-7129","authenticated-orcid":false,"given":"Hong","family":"Zhu","sequence":"first","affiliation":[{"name":"College of Electronic Engineering, National University of Defense Technology, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8005-7182","authenticated-orcid":false,"given":"Qingyang","family":"Lu","sequence":"additional","affiliation":[{"name":"Army Artillery and Air Defense Academy of PLA, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7355-9668","authenticated-orcid":false,"given":"Lei","family":"Xue","sequence":"additional","affiliation":[{"name":"College of Electronic Engineering, National University of Defense Technology, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1206-1444","authenticated-orcid":false,"given":"Pingping","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7591-943X","authenticated-orcid":false,"given":"Guanglin","family":"Yuan","sequence":"additional","affiliation":[{"name":"Army Artillery and Air Defense Academy of PLA, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3270969"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3195946"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3122865"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3046478"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3017505"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.777"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3038720"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01355"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02217"},{"key":"ref10","article-title":"Divert more attention to vision-language tracking","author":"Guo","year":"2022","journal-title":"arXiv:2207.01076"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093425"},{"key":"ref12","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"arXiv:2103.00020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00540"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01288"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2023.3324362"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3273547"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3110713"},{"key":"ref19","article-title":"Describe and attend to track: Learning natural language guided structural representation and visual attention for object tracking","author":"Wang","year":"2018","journal-title":"arXiv:1811.10014"},{"key":"ref20","article-title":"Siamese tracking with lingual object constraints","author":"Filtenborg","year":"2020","journal-title":"arXiv:2011.11721"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00579"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00915"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.544"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00271"},{"issue":"14","key":"ref25","first-page":"71","article-title":"Dall-e: Creating images from text","volume":"8","author":"Reddy","year":"2021","journal-title":"UGC Care Group I J."},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref27","article-title":"Scaling open-vocabulary image segmentation with image-level labels","author":"Ghiasi","year":"2021","journal-title":"arXiv:2112.12143"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.410"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3233\/faia240489"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref35","article-title":"MaPLe: Multi-modal prompt learning","author":"Khattak","year":"2022","journal-title":"arXiv:2210.03117"},{"key":"ref36","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. IEEE Int. Conf. Learn. Represent. (ICLR)","author":"Dosovitskiy"},{"issue":"8","key":"ref37","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00552"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.443"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2957464"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref48","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref49","article-title":"Robust visual object tracking with natural language region proposal network","author":"Feng","year":"2019","journal-title":"arXiv:1912.02048"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00162"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01228-7"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6979\/10909032\/10817474.pdf?arnumber=10817474","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,4]],"date-time":"2025-03-04T18:53:40Z","timestamp":1741114420000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10817474\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":52,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tits.2024.3520103","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}