{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T18:54:16Z","timestamp":1784055256419,"version":"3.55.0"},"reference-count":85,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"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"}]},{"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62475288"],"award-info":[{"award-number":["62475288"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangxi \u201cYoung Bagui Scholar\u201d Teams for Innovation and Research Project"},{"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":[[2025,8]]},"DOI":"10.1109\/tcsvt.2025.3549953","type":"journal-article","created":{"date-parts":[[2025,3,17]],"date-time":"2025-03-17T13:49:48Z","timestamp":1742219388000},"page":"7554-7567","source":"Crossref","is-referenced-by-count":54,"title":["AVLTrack: Dynamic Sparse Learning for Aerial Vision-Language Tracking"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8753-4990","authenticated-orcid":false,"given":"Yuanliang","family":"Xue","sequence":"first","affiliation":[{"name":"Xi’an Research Institute of Hi-Tech, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1125-2759","authenticated-orcid":false,"given":"Guodong","family":"Jin","sequence":"additional","affiliation":[{"name":"Xi’an Research Institute of Hi-Tech, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8798-5129","authenticated-orcid":false,"given":"Tao","family":"Shen","sequence":"additional","affiliation":[{"name":"Xi’an Research Institute of Hi-Tech, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1650-2585","authenticated-orcid":false,"given":"Lining","family":"Tan","sequence":"additional","affiliation":[{"name":"Xi’an Research Institute of Hi-Tech, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3867-6753","authenticated-orcid":false,"given":"Ning","family":"Li","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"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2664-0574","authenticated-orcid":false,"given":"Yaozong","family":"Zheng","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"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01517"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00196"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3307174"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636309"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01438"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.1109\/TGRS.2023.3305728","article-title":"SmallTrack: Wavelet pooling and graph enhanced classification for UAV small object tracking","volume":"61","author":"Xue","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560756"},{"key":"ref8","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. ICLR","author":"Dosovitskiy"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01286"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02217"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3301933"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3395352"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3232854"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01817"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28205"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01054"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3212594"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-023-10558-5"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2022.10.001"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00298"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01194"},{"key":"ref22","article-title":"Light Siamese network for long-term onboard aerial tracking","volume":"62","author":"Yang","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.777"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00579"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01355"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3409078"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00915"},{"key":"ref28","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Mach. Learn. Res. (ICML)","author":"Radford"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611803"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3285441"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2023.02.023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3436878"},{"key":"ref33","article-title":"Generating long sequences with sparse transformers","author":"Child","year":"2019","journal-title":"arXiv:1904.10509"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00333"},{"key":"ref35","article-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020","journal-title":"arXiv:2004.05150"},{"key":"ref36","first-page":"1450","article-title":"Big bird: Transformers for longer sequences","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Zaheer"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00995"},{"key":"ref38","article-title":"Reformer: The efficient transformer","volume-title":"Proc. ICLR","author":"Kitaev"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/127"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3411301"},{"key":"ref41","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","author":"Devlin"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00564"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00441"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref47","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01387-y"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2957464"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_19"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3409078"},{"key":"ref54","article-title":"Decoupled weight decay regularization","volume-title":"Proc. ICLR","author":"Loshchilov"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2388226"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01319"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00162"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00935"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00668"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01493"},{"key":"ref61","article-title":"Mobile vision transformer-based visual object tracking","volume-title":"Proc. BMVC","author":"Gopal"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00918"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10803050"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801335"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICARM62033.2024.10715901"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802714"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11205"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_27"},{"key":"ref69","article-title":"MixFormerV2: Efficient fully transformer tracking","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Cui"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01400"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00657"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610022"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161487"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00234"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610544"},{"key":"ref77","article-title":"Learning adaptive and view-invariant vision transformer for real-time UAV tracking","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01792"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3400873"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00881"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2024.3440378"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802294"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01310"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3396289"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25359"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11114024\/10922151.pdf?arnumber=10922151","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T05:19:59Z","timestamp":1754457599000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10922151\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":85,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3549953","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}