{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T15:49:34Z","timestamp":1776440974979,"version":"3.51.2"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"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":["U23A20383"],"award-info":[{"award-number":["U23A20383"]}],"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":["62472109"],"award-info":[{"award-number":["62472109"]}],"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":["62466051"],"award-info":[{"award-number":["62466051"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019370","name":"Project of Guangxi Science and Technology","doi-asserted-by":"publisher","award":["2024GXNSFGA010001"],"award-info":[{"award-number":["2024GXNSFGA010001"]}],"id":[{"id":"10.13039\/501100019370","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019370","name":"Project of Guangxi Science and Technology","doi-asserted-by":"publisher","award":["2025GXNSFAA069676"],"award-info":[{"award-number":["2025GXNSFAA069676"]}],"id":[{"id":"10.13039\/501100019370","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019370","name":"Project of Guangxi Science and Technology","doi-asserted-by":"publisher","award":["2025GXNSFAA069417"],"award-info":[{"award-number":["2025GXNSFAA069417"]}],"id":[{"id":"10.13039\/501100019370","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Research Project of Guangxi Normal University","award":["2024DF001"],"award-info":[{"award-number":["2024DF001"]}]},{"name":"Innovation Project of Guangxi Graduate Education","award":["YCBZ2024083"],"award-info":[{"award-number":["YCBZ2024083"]}]},{"name":"Guangxi Colleges and Universities Key Laboratory of Intelligent Software","award":["2024B01"],"award-info":[{"award-number":["2024B01"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1109\/tcsvt.2025.3557570","type":"journal-article","created":{"date-parts":[[2025,4,3]],"date-time":"2025-04-03T16:08:02Z","timestamp":1743696482000},"page":"9300-9311","source":"Crossref","is-referenced-by-count":10,"title":["Mamba Adapter: Efficient Multi-Modal Fusion for Vision-Language Tracking"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-5934-8837","authenticated-orcid":false,"given":"Liangtao","family":"Shi","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\/0000-0003-3423-1539","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\/0009-0007-1541-1717","authenticated-orcid":false,"given":"Xiantao","family":"Hu","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\/0000-0003-0280-2640","authenticated-orcid":false,"given":"Shuxiang","family":"Song","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"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2024.3402136"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3081254"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2019.07.005"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00579"},{"key":"ref5","first-page":"1","article-title":"Divert more attention to vision-language tracking","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 35th Annu. Conf. Neural Inf. Process. Syst.","author":"Guo"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611803"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28205"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.777"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093425"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3038720"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01355"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475349"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02217"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3301933"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3285441"},{"key":"ref16","article-title":"An empirical investigation of catastrophic forgetting in gradient-based neural networks","author":"Goodfellow","year":"2013","journal-title":"arXiv:1312.6211"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2773081"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539960"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2345390"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.352"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_29"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.733"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00935"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00441"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3289624"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01400"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00935"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28286"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01826"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28591"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3396289"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3486347"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32943"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32372"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2025.3558482"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3288353"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01817"},{"key":"ref45","first-page":"1","article-title":"AdaptFormer: Adapting vision transformers for scalable visual recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 35th Annu. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28243"},{"key":"ref47","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv:2106.09685"},{"key":"ref48","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref49","article-title":"Sparse-tuning: Adapting vision transformers with efficient fine-tuning and inference","author":"Liu","year":"2024","journal-title":"arXiv:2405.14700"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01605"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27852"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.287"},{"key":"ref53","article-title":"SwimVG: Step-wise multimodal fusion and adaption for visual grounding","author":"Shi","year":"2025","journal-title":"arXiv:2502.16786"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547851"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00918"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_22"},{"key":"ref58","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. 9th Int. Conf. Learn. Represent. (ICLR)","author":"Dosovitskiy"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref60","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv:2312.00752"},{"key":"ref61","article-title":"Efficiently modeling long sequences with structured state spaces","author":"Gu","year":"2021","journal-title":"arXiv:2111.00396"},{"key":"ref62","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00552"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01387-y"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01802"},{"key":"ref68","article-title":"Robust visual object tracking with natural language region proposal network","author":"Feng","year":"2019","journal-title":"arXiv:1912.02048"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3232854"},{"key":"ref71","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. ICLR","author":"Loshchilov"},{"key":"ref72","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11154820\/10948517.pdf?arnumber=10948517","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T17:49:25Z","timestamp":1757526565000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10948517\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":72,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3557570","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9]]}}}