{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T10:19:04Z","timestamp":1773137944486,"version":"3.50.1"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"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":["62121002"],"award-info":[{"award-number":["62121002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Innovation Promotion Association of Chinese Academy of Sciences"},{"DOI":"10.13039\/501100001809","name":"Graduate School Special Funding Program of the University of Science and Technology of China","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":[[2026,3]]},"DOI":"10.1109\/tcsvt.2025.3623281","type":"journal-article","created":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T17:58:24Z","timestamp":1760983104000},"page":"3820-3833","source":"Crossref","is-referenced-by-count":0,"title":["State Space Models for Natural Language Tracking: Exploring Context-Adaptive Language Cues"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5292-2873","authenticated-orcid":false,"given":"Yuyang","family":"Tang","sequence":"first","affiliation":[{"name":"MoE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition and the School of Information Science, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0506-5217","authenticated-orcid":false,"given":"Yinchao","family":"Ma","sequence":"additional","affiliation":[{"name":"MoE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition and the School of Information Science, University of Science and Technology of China, Hefei, China"}]},{"given":"Dengqing","family":"Yang","sequence":"additional","affiliation":[{"name":"MoE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition and the School of Information Science, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9384-8665","authenticated-orcid":false,"given":"Jie","family":"Xiao","sequence":"additional","affiliation":[{"name":"MoE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition and the School of Information Science, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1856-9564","authenticated-orcid":false,"given":"Tianzhu","family":"Zhang","sequence":"additional","affiliation":[{"name":"MoE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition and the School of Information Science, University of Science and Technology of China, Hefei, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3212987"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2987601"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3037947"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3275034"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3533155"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.777"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3038720"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3557570"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3288353"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3395352"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01355"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02217"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28205"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3301933"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3563267"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0476"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01817"},{"key":"ref20","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv:2312.00752"},{"key":"ref21","first-page":"572","article-title":"Combining recurrent, convolutional, and continuous-time models with linear state space layers","volume-title":"Proc. Adv. neural Inf. Process. Syst.","volume":"34","author":"Gu"},{"key":"ref22","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","author":"Zhu","year":"2024","journal-title":"arXiv:2401.09417"},{"key":"ref23","article-title":"LION: Linear group RNN for 3D object detection in point clouds","author":"Liu","year":"2024","journal-title":"arXiv:2407.18232"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72684-2_7"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3266837"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3037518"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00540"},{"key":"ref28","article-title":"Siamese natural language tracker: Tracking by natural language descriptions with Siamese trackers","author":"Feng","year":"2019","journal-title":"arXiv:1912.02048"},{"key":"ref29","article-title":"Efficiently modeling long sequences with structured state spaces","author":"Gu","year":"2021","journal-title":"arXiv:2111.00396"},{"key":"ref30","article-title":"Hungry hungry hippos: Towards language modeling with state space models","author":"Fu","year":"2022","journal-title":"arXiv:2212.14052"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_14"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3557992"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3588533"},{"key":"ref35","article-title":"Transformers are SSMs: Generalized models and efficient algorithms through structured state space duality","author":"Dao","year":"2024","journal-title":"arXiv:2405.21060"},{"key":"ref36","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":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3429508"},{"key":"ref38","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref39","first-page":"12360","article-title":"Root mean square layer normalization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00552"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2388226"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01387-y"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00162"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00928"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00935"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01826"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1241"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00579"},{"key":"ref51","first-page":"4446","article-title":"Divert more attention to vision-language tracking","volume-title":"Proc. NIPS","author":"Guo"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3285441"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611803"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093425"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_35"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00928"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3328185"},{"key":"ref58","article-title":"VastTrack: Vast category visual object tracking","author":"Peng","year":"2024","journal-title":"arXiv:2403.03493"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32440"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i2.32223"},{"key":"ref62","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016","journal-title":"arXiv:1608.03983"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref66","article-title":"Hivit: A simpler and more efficient design of hierarchical vision transformer","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Zhang"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11424237\/11207713.pdf?arnumber=11207713","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T20:01:07Z","timestamp":1773086467000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11207713\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":66,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3623281","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}