{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T12:36:03Z","timestamp":1762432563068,"version":"3.44.0"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3565984","type":"journal-article","created":{"date-parts":[[2025,4,30]],"date-time":"2025-04-30T19:19:33Z","timestamp":1746040773000},"page":"5857-5865","source":"Crossref","is-referenced-by-count":1,"title":["Multi-Modal Hybrid Interaction Vision-Language Tracking"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-2120-4854","authenticated-orcid":false,"given":"Lei","family":"Lei","sequence":"first","affiliation":[{"name":"Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University, Guilin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7083-3847","authenticated-orcid":false,"given":"Xianxian","family":"Li","sequence":"additional","affiliation":[{"name":"Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University, Guilin, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02217"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00630"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3195759"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref8","first-page":"4446","article-title":"Divert more attention to vision-language tracking","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Guo","year":"2022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680657"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00915"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01817"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01400"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3301933"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3038720"},{"key":"ref16","first-page":"5552","article-title":"All in one: Exploring unified vision-language tracking with multi-modal alignment","volume-title":"Proc. 31st ACM Int. Conf. Multimedia","author":"Chunhui","year":"2023"},{"key":"ref17","article-title":"Describe and Attend to Track: Learning Natural Language guided Structural Representation and Visual Attention for Object Tracking","volume-title":"CoRR","author":"Wang","year":"2018"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.777"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093425"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00579"},{"key":"ref21","first-page":"5374","article-title":"LaSOT: A high-quality benchmark for large-scale single object tracking","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Heng","year":"2018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2957464"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.789"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3232854"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01355"},{"key":"ref29","first-page":"300","article-title":"TrackingNet: A large-scale dataset and benchmark for object tracking in the wild","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Mller","year":"2018"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3395352"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref32","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","volume-title":"CoRR","author":"Liu","year":"2019"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00540"},{"key":"ref34","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3321497"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3285441"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2875360"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28205"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01805"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3396289"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3289624"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3486347"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2345390"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00935"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3285441"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10980446.pdf?arnumber=10980446","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T04:26:06Z","timestamp":1756355166000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10980446\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3565984","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2025]]}}}