{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T18:07:37Z","timestamp":1775326057447,"version":"3.50.1"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"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. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/tcsvt.2024.3510735","type":"journal-article","created":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T14:22:05Z","timestamp":1733322125000},"page":"4384-4396","source":"Crossref","is-referenced-by-count":2,"title":["Multi-Modal Understanding and Generation for Object Tracking"],"prefix":"10.1109","volume":"35","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"}]},{"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"}]},{"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"}]},{"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"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.777"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3038720"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01355"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02217"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00579"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00915"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01288"},{"key":"ref8","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"arXiv:2201.12086","author":"Li","year":"2022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3195759"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3039933"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3178656"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00162"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"ref14","article-title":"TrTr: Visual tracking with transformer","volume-title":"arXiv:2105.03817","author":"Zhao","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3249468"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3376582"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01792"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094971"},{"key":"ref22","article-title":"Describe and attend to track: Learning natural language guided structural representation and visual attention for object tracking","volume-title":"arXiv:1811.10014","author":"Wang","year":"2018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093425"},{"key":"ref24","article-title":"Siamese tracking with lingual object constraints","volume-title":"arXiv:2011.11721","author":"Filtenborg","year":"2020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3301933"},{"key":"ref26","article-title":"Learning transferable visual models from natural language supervision","volume-title":"arXiv:2103.00020","author":"Radford","year":"2021"},{"key":"ref27","article-title":"ViLT: Vision-and-Language transformer without convolution or region supervision","volume-title":"arXiv:2102.03334","author":"Kim","year":"2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref29","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","volume-title":"arXiv:2104.13921","author":"Gu","year":"2021"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref31","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Systems. (NeurIPS)","author":"Li"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28361"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref37","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00552"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.443"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2957464"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref45","article-title":"Siamese natural language tracker: Tracking by natural language descriptions with Siamese trackers","volume-title":"arXiv:1912.02048","author":"Feng","year":"2019"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00540"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01228-7"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10989278\/10777574.pdf?arnumber=10777574","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T18:41:42Z","timestamp":1767638502000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10777574\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":47,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3510735","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}