{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:25:21Z","timestamp":1776882321691,"version":"3.51.2"},"reference-count":69,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tai.2025.3558482","type":"journal-article","created":{"date-parts":[[2025,4,8]],"date-time":"2025-04-08T14:20:46Z","timestamp":1744122046000},"page":"2819-2829","source":"Crossref","is-referenced-by-count":10,"title":["Adaptive Perception for Unified Visual Multimodal Object Tracking"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-1541-1717","authenticated-orcid":false,"given":"Xiantao","family":"Hu","sequence":"first","affiliation":[{"name":"Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and Guangxi Key Laboratory of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4387-407X","authenticated-orcid":false,"given":"Bineng","family":"Zhong","sequence":"additional","affiliation":[{"name":"Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and Guangxi Key Laboratory of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2353-5246","authenticated-orcid":false,"given":"Qihua","family":"Liang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and Guangxi Key Laboratory of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5934-8837","authenticated-orcid":false,"given":"Liangtao","family":"Shi","sequence":"additional","affiliation":[{"name":"Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and Guangxi Key Laboratory of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6123-363X","authenticated-orcid":false,"given":"Zhiyi","family":"Mo","sequence":"additional","affiliation":[{"name":"School of Data Science and Software Engineering, Wuzhou University, Wuzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4665-6852","authenticated-orcid":false,"given":"Ying","family":"Tai","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Suzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4800-832X","authenticated-orcid":false,"given":"Jian","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_22"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01400"},{"key":"ref5","first-page":"16743","article-title":"SwinTrack: A simple and strong baseline for transformer tracking","volume-title":"Proc. NeurIPS","volume":"35","author":"Lin","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00935"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00918"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01812"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32943"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32372"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00560"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2023.3235442"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110806"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27826"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2022.3221128"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102863"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3316068"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32297"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01805"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547851"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02507"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01310"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27852"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00860"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00552"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2957464"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_19"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3130533"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.106977"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01055"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2015.79"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2023.3318601"},{"key":"ref33","article-title":"Unified-IO: A unified model for vision, language, and multi-modal tasks","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Lu","year":"2022"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref35","article-title":"MUTEX: Learning unified policies from multimodal task specifications","author":"Shah","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72630-9_18"},{"key":"ref37","first-page":"25006","article-title":"A unified audio-visual learning framework for localization, separation, and recognition","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mo","year":"2023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_5"},{"key":"ref39","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Loshchilov","year":"2018"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123289"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28325"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_9"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25500"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01055"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3289624"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3336665"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28286"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01826"},{"key":"ref53","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3396289"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25500"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3195759"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106493"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687717"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32938"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32618"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2024.3462973"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2022.3223871"},{"key":"ref63","article-title":"Multi-stage vision token dropping: Towards efficient multimodal large language model","author":"Liu","year":"2024"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3486347"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32528"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01821"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02730"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2025.3586135"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3174341"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9078688\/11186126\/10955486.pdf?arnumber=10955486","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T04:33:55Z","timestamp":1759379635000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10955486\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":69,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tai.2025.3558482","relation":{},"ISSN":["2691-4581"],"issn-type":[{"value":"2691-4581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}