{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T02:44:00Z","timestamp":1791945840639,"version":"4.3.4"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"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":["62076192"],"award-info":[{"award-number":["62076192"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Joint Fund Project of National Natural Science Foundation of China","award":["U22B2054"],"award-info":[{"award-number":["U22B2054"]}]},{"name":"Postdoctoral Fellowship Program of China Postdoctoral Science Foundation","award":["GZC20232033"],"award-info":[{"award-number":["GZC20232033"]}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2023M742738"],"award-info":[{"award-number":["2023M742738"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Program for Cheung Kong Scholars and Innovative Research Team in University","award":["IRT_15R53"],"award-info":[{"award-number":["IRT_15R53"]}]},{"name":"Fund for Foreign Scholars in University Research and Teaching Programs through the 111 Project","award":["B07048"],"award-info":[{"award-number":["B07048"]}]},{"name":"Key Scientific Technological Innovation Research Project","award":["B07048"],"award-info":[{"award-number":["B07048"]}]},{"DOI":"10.13039\/501100001809","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","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":[[2024,12]]},"DOI":"10.1109\/tcsvt.2024.3436878","type":"journal-article","created":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T18:36:02Z","timestamp":1722537362000},"page":"12770-12781","source":"Crossref","is-referenced-by-count":30,"title":["Visual and Language Collaborative Learning for RGBT Object Tracking"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0375-9253","authenticated-orcid":false,"given":"Jiahao","family":"Wang","sequence":"first","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, International Research Center for Intelligent Perception and Computation, and the Joint International Research Laboratory of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi’an, Shaanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5669-9354","authenticated-orcid":false,"given":"Fang","family":"Liu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, International Research Center for Intelligent Perception and Computation, and the Joint International Research Laboratory of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi’an, Shaanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3354-9617","authenticated-orcid":false,"given":"Licheng","family":"Jiao","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, International Research Center for Intelligent Perception and Computation, and the Joint International Research Laboratory of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi’an, Shaanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingjia","family":"Gao","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, International Research Center for Intelligent Perception and Computation, and the Joint International Research Laboratory of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi’an, Shaanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, International Research Center for Intelligent Perception and Computation, and the Joint International Research Laboratory of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi’an, Shaanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2002-3894","authenticated-orcid":false,"given":"Shuo","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, International Research Center for Intelligent Perception and Computation, and the Joint International Research Laboratory of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi’an, Shaanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6130-2518","authenticated-orcid":false,"given":"Lingling","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, International Research Center for Intelligent Perception and Computation, and the Joint International Research Laboratory of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi’an, Shaanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5472-1426","authenticated-orcid":false,"given":"Puhua","family":"Chen","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, International Research Center for Intelligent Perception and Computation, and the Joint International Research Laboratory of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi’an, Shaanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8780-5455","authenticated-orcid":false,"given":"Xu","family":"Liu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, International Research Center for Intelligent Perception and Computation, and the Joint International Research Laboratory of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi’an, Shaanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01218"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01493"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00440"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3067997"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3072207"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3288853"},{"key":"ref7","first-page":"1","article-title":"Enhanced target tracking through infrared-visible image fusion","volume-title":"Proc. 14th Int. Conf. Inf. Fusion","author":"Schnelle"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3102886"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.14257\/ijsip.2015.8.3.15"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3023440"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.05.011"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3316990"},{"key":"ref13","article-title":"Multi-focus image fusion: A benchmark","author":"Zhang","year":"2020","journal-title":"arXiv:2005.01116"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.05.002"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1117\/12.918373"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1117\/1.OE.52.1.017004"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101881"},{"key":"ref18","article-title":"Decision-level visible and infrared fusion tracking via Siamese networks","volume-title":"Proc. 9th Chin. Conf. Inf. Fusion","author":"Zhang"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2019.2898618"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2018.10.002"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.01.022"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00279"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350928"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803528"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.23919\/FUSION43075.2019.9011253"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3390\/electronics9122162"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00060"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.02.023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01495-3"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20187"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02080"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.421"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"ref34","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":"ref35","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":"ref36","article-title":"Supervision exists everywhere: A data efficient contrastive language-image pre-training paradigm","author":"Li","year":"2021","journal-title":"arXiv:2110.05208"},{"key":"ref37","first-page":"20450","article-title":"CLOOB: Modern Hopfield networks with InfoLOOB outperform CLIP","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"F\u00fcrst"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01759"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref41","first-page":"1931","article-title":"Unifying vision-and-language tasks via text generation","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Cho"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00695"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_41"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547851"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref49","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02238"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2614135"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123289"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3130533"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_49"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2020.2980735"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00017"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_14"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00278"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.3390\/s20020393"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3157594"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1117\/12.3023347"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101816"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3310295"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10811772\/10620225.pdf?arnumber=10620225","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:39:41Z","timestamp":1734982781000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10620225\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":67,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3436878","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}