{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T17:04:02Z","timestamp":1783530242837,"version":"3.55.0"},"reference-count":116,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Youth Innovation Promotion Association of CAS"},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306294"],"award-info":[{"award-number":["62306294"]}],"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":["62021001"],"award-info":[{"award-number":["62021001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Graduate School Special Funding Program of the University of Science and Technology of China"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1109\/tpami.2025.3615714","type":"journal-article","created":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T17:40:39Z","timestamp":1760377239000},"page":"1554-1572","source":"Crossref","is-referenced-by-count":1,"title":["UniSOT: A Unified Framework for Multi-Modality Single Object Tracking"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-0506-5217","authenticated-orcid":false,"given":"Yinchao","family":"Ma","sequence":"first","affiliation":[{"name":"School of Information Science, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5292-2873","authenticated-orcid":false,"given":"Yuyang","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Information Science, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3599-7659","authenticated-orcid":false,"given":"Wenfei","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Information Science, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1856-9564","authenticated-orcid":false,"given":"Tianzhu","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Science, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7695-5834","authenticated-orcid":false,"given":"Xu","family":"Zhou","sequence":"additional","affiliation":[{"name":"Sangfor Research Institute, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7266-5579","authenticated-orcid":false,"given":"Feng","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Information Science, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28205"},{"key":"ref2","first-page":"3492","article-title":"Prompting for multi-modal tracking","volume-title":"Proc. ACM Int. Conf. Multimedia","author":"Jinyu","year":"2022"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2022.103508"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-012-0582-z"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2797082"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.777"},{"key":"ref8","first-page":"23151","article-title":"Joint visual grounding and tracking with natural language specification","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Li","year":"2023"},{"key":"ref9","first-page":"4446","article-title":"Divert more attention to vision-language tracking","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Mingzhe","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00579"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"ref12","first-page":"6181","article-title":"Learning discriminative model prediction for tracking","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Zhu","year":"2019"},{"key":"ref13","first-page":"9516","article-title":"Visual prompt multi-modal tracking","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Jiawen","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01280"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3174341"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01055"},{"key":"ref17","first-page":"19156","article-title":"Single-model and any-modality for video object tracking","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Zongwei","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3275034"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref21","first-page":"9082","article-title":"Adalora: Adaptive budget allocation for parameter-efficient fine-tuning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2388226"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00441"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00479"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00670"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01559-4"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01435-1"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.733"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_9"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00540"},{"key":"ref34","first-page":"13763","article-title":"Towards more flexible and accurate object tracking with natural language: Algorithms and benchmark","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Xiao","year":"2021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3038720"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01817"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00480"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_29"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2345390"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.279"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00935"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01356"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_22"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25500"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20187"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2023.3318601"},{"key":"ref47","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford","year":"2021"},{"key":"ref48","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Li","year":"2021"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01136"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01319"},{"key":"ref51","first-page":"20378","article-title":"Movement pruning: Adaptive sparsity by fine-tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Sanh","year":"2020"},{"key":"ref52","first-page":"26809","article-title":"Platon: Pruning large transformer models with upper confidence bound of weight importance","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang","year":"2022"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00552"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2957464"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_19"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref60","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Glorot","year":"2010"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_43"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01808"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3376690"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3289620"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3249468"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00162"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_46"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_13"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6944"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.465"},{"key":"ref71","article-title":"Unified sequence-to-sequence learning for single- and multi-modal visual object tracking","author":"Chen","year":"2024"},{"key":"ref72","first-page":"16743","article-title":"Swintrack: A simple and strong baseline for transformer tracking","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lin","year":"2021"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25085-9_25"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00195"},{"key":"ref75","first-page":"36324","article-title":"Decoupling features in hierarchical propagation for video object segmentation","volume-title":"Proc. 36th Int. Conf. Neural Inf. Process. Syst.","author":"Yang","year":"2022"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00304"},{"key":"ref77","first-page":"2491","article-title":"Associating objects with transformers for video object segmentation","volume-title":"Proc. 35th Adv. Neural Inf. Process. Syst.","author":"Yang","year":"2021"},{"key":"ref78","first-page":"4061","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref79","first-page":"1769","article-title":"Sgdr: Stochastic gradient descent with warm restarts","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ilya","year":"2017"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3130533"},{"key":"ref81","first-page":"1","article-title":"Avist: A benchmark for visual object tracking in adverse visibility","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Noman","year":"2022"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01387-y"},{"key":"ref83","first-page":"1134","article-title":"Need for speed: A benchmark for higher frame rate object tracking","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Kiani","year":"2017"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_27"},{"key":"ref85","article-title":"Robust visual object tracking with natural language region proposal network","author":"Feng","year":"2019"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093425"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00928"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_35"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01506"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16188"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01661"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_23"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00477"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68238-5_39"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00305"},{"key":"ref98","article-title":"Middle fusion and multi-stage, multi-form prompts for robust RGB-T tracking","volume-title":"Neurocomputing","volume":"596","author":"Wang","year":"2024"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00523"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00709"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3060862"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00278"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350928"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_14"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00868"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.3390\/s20020393"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2020.2980735"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00017"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123289"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.106977"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00721"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00937"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00142"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00661"},{"key":"ref115","first-page":"12513","article-title":"LORA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2022"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6758"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11345188\/11202681.pdf?arnumber=11202681","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:00:35Z","timestamp":1768255235000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11202681\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":116,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3615714","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]}}}