{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T23:57:40Z","timestamp":1775174260317,"version":"3.50.1"},"reference-count":119,"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":[{"DOI":"10.13039\/100000001","name":"Guangxi Natural Science Foundation","doi-asserted-by":"publisher","award":["2024GXNSFAA010484"],"award-info":[{"award-number":["2024GXNSFAA010484"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62466013"],"award-info":[{"award-number":["62466013"]}],"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":["62206123"],"award-info":[{"award-number":["62206123"]}],"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":["62066042"],"award-info":[{"award-number":["62066042"]}],"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":["62176170"],"award-info":[{"award-number":["62176170"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1109\/tcsvt.2025.3599856","type":"journal-article","created":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T19:48:31Z","timestamp":1755546511000},"page":"2403-2418","source":"Crossref","is-referenced-by-count":9,"title":["Learning an Adaptive and View-Invariant Vision Transformer for Real-Time UAV Tracking"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-4230-899X","authenticated-orcid":false,"given":"You","family":"Wu","sequence":"first","affiliation":[{"name":"College of Computer Science and Engineering, Guilin University of Technology, Guilin, China"}]},{"given":"Yongxin","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science and Engineering, Guilin University of Technology, Guilin, China"}]},{"given":"Mengyuan","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Engineering, Guilin University of Technology, Guilin, China"}]},{"given":"Xucheng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3025-0516","authenticated-orcid":false,"given":"Xiangyang","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Engineering, Guilin University of Technology, Guilin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6646-8747","authenticated-orcid":false,"given":"Hengzhou","family":"Ye","sequence":"additional","affiliation":[{"name":"College of Computer Science and Engineering, Guilin University of Technology, Guilin, China"}]},{"given":"Dan","family":"Zeng","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Sun Yat-sen University, Zhuhai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4651-7163","authenticated-orcid":false,"given":"Qijun","family":"Zhao","sequence":"additional","affiliation":[{"name":"College of Computer Science, Sichuan University, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4587-513X","authenticated-orcid":false,"given":"Shuiwang","family":"Li","sequence":"additional","affiliation":[{"name":"Guangxi Key Laboratory of Embedded Technology and Intelligent Information Processing, Guilin, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01286"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01194"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01517"},{"key":"ref4","article-title":"Learning motion blur robust vision transformers with dynamic early exit for real-time UAV tracking","author":"Wu","year":"2024","journal-title":"arXiv:2407.05383"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2345390"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.490"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00298"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3023440"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.129"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00480"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00935"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00670"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01438"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3340372"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3375366"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3326695"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3249468"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3094645"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3370981"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01399"},{"key":"ref25","first-page":"50959","article-title":"ZoomTrack: Target-aware non-uniform resizing for efficient visual tracking","volume-title":"Proc. NIPS","author":"Kou"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01826"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28286"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01822"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00935"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00881"},{"key":"ref31","first-page":"28403","article-title":"Learning adaptive and view-invariant vision transformer for real-time uav tracking","volume-title":"Proc. ICML","volume":"235","author":"Li"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/18.suppl_2.S231"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01073"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3135375"},{"key":"ref35","article-title":"Learning deep representations by mutual information estimation and maximization","volume-title":"arXiv:1808.06670","author":"Hjelm","year":"2018"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3055564"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72933-1_21"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02687"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28207"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3232854"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3083880"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_27"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00131"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560756"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859656"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00303"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00855"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3417400"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3440994"},{"key":"ref52","article-title":"Linformer: Self-attention with linear complexity","author":"Wang","year":"2020","journal-title":"arXiv:2006.04768"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01183"},{"key":"ref54","first-page":"12934","article-title":"EfficientFormer: Vision transformers at MobileNet speed","volume-title":"Proc. NIPS","volume":"35","author":"Li"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3277689"},{"key":"ref56","first-page":"13937","article-title":"DynamicViT: Efficient vision transformers with dynamic token sparsification","volume-title":"Proc. NIPS","volume":"34","author":"Rao"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01054"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-023-01171-8"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2018.07.001"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.3390\/app7030210"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1023\/A:1020350100748"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2012.6239233"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2009.2027608"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.03.070"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3119177"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICB.2016.7550060"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01797"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02067"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098135"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN60899.2024.10650915"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682450"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859961"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3307052"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150464"},{"key":"ref75","first-page":"2654","article-title":"Do deep nets really need to be deep","volume-title":"Proc. NIPS","author":"Ba"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.26615\/978-954-452-072-4_068"},{"key":"ref77","first-page":"1837","article-title":"Collaborative learning for deep neural networks","volume-title":"Proc. NIPS","author":"Song"},{"key":"ref78","volume-title":"Information Theory, Inference and Learning Algorithms","author":"MacKay","year":"2004"},{"key":"ref79","first-page":"5171","article-title":"On variational bounds of mutual information","volume-title":"Proc. ICML","author":"Poole"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/362"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73024-5_1"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11205"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_23"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11021-5_28"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2609928"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.733"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00509"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00515"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108614"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3307174"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161487"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3236584"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00234"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10803050"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610022"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00657"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111439"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3448254"},{"key":"ref101","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"arXiv:2010.11929","author":"Dosovitskiy"},{"key":"ref102","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. ICML","author":"Touvron"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2957464"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00552"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_19"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_46"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00628"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00721"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00162"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01309"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/127"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00859"},{"key":"ref116","article-title":"Unified sequence-to-sequence learning for single{-} and multi-modal visual object tracking","author":"Chen","year":"2023","journal-title":"arXiv:2304.14394"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01793"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00879"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610544"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11392768\/11129088.pdf?arnumber=11129088","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T21:02:27Z","timestamp":1770930147000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11129088\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":119,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3599856","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]}}}