{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:42:16Z","timestamp":1777657336590,"version":"3.51.4"},"reference-count":96,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"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":["62101351"],"award-info":[{"award-number":["62101351"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2020A1515110376"],"award-info":[{"award-number":["2020A1515110376"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Outstanding Scientific and Technological Innovation Talents Ph.D. Startup Project","award":["RCBS20210609104447108"],"award-info":[{"award-number":["RCBS20210609104447108"]}]},{"name":"Key-Area Research and Development Program of Guangdong Province","award":["2020B0101350001"],"award-info":[{"award-number":["2020B0101350001"]}]},{"DOI":"10.13039\/501100004853","name":"Chinese University of Hong Kong","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004853","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,7,1]]},"DOI":"10.1109\/tpami.2022.3232854","type":"journal-article","created":{"date-parts":[[2022,12,30]],"date-time":"2022-12-30T18:59:54Z","timestamp":1672426794000},"page":"9186-9205","source":"Crossref","is-referenced-by-count":38,"title":["WebUAV-3M: A Benchmark for Unveiling the Power of Million-Scale Deep UAV Tracking"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9017-1828","authenticated-orcid":false,"given":"Chunhui","family":"Zhang","sequence":"first","affiliation":[{"name":"Cooperative Medianet Innovation Center, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1977-3647","authenticated-orcid":false,"given":"Guanjie","family":"Huang","sequence":"additional","affiliation":[{"name":"Shenzhen Research Institute of Big Data, Chinese University of Hong Kong, Shenzhen, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4497-0135","authenticated-orcid":false,"given":"Li","family":"Liu","sequence":"additional","affiliation":[{"name":"Shenzhen Research Institute of Big Data, Chinese University of Hong Kong, Shenzhen, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0231-9392","authenticated-orcid":false,"given":"Shan","family":"Huang","sequence":"additional","affiliation":[{"name":"Shenzhen Research Institute of Big Data, Chinese University of Hong Kong, Shenzhen, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0919-289X","authenticated-orcid":false,"given":"Yinan","family":"Yang","sequence":"additional","affiliation":[{"name":"Shenzhen Research Institute of Big Data, Chinese University of Hong Kong, Shenzhen, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2324-6527","authenticated-orcid":false,"given":"Xiang","family":"Wan","sequence":"additional","affiliation":[{"name":"Shenzhen Research Institute of Big Data, Chinese University of Hong Kong, Shenzhen, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5293-310X","authenticated-orcid":false,"given":"Shiming","family":"Ge","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5979-578X","authenticated-orcid":false,"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[{"name":"JD Explore Academy, JD.com, Beijing, China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.493"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00628"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01600"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01194"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01355"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01319"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00182"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00721"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.733"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_29"},{"key":"ref96","article-title":"Divert more attention to vision-language tracking","author":"guo","year":"2022","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00552"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2919201"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2957464"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00515"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00715"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00579"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2516982"},{"key":"ref18","first-page":"6495","article-title":"Tracking by natural language specification","author":"feng","year":"2017","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref93","first-page":"1106","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref92","first-page":"784","article-title":"Acquisition of localization confidence for accurate object detection","author":"jiang","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2015.84"},{"key":"ref95","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.352"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6999"},{"key":"ref90","article-title":"Anti-UAV: A large multi-modal benchmark for UAV tracking","author":"jiang","year":"2021"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1364\/AO.21.002569"},{"key":"ref45","article-title":"Pix2seq: A language modeling framework for object detection","author":"chen","year":"2022","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00298"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01415"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00935"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2016.7738055"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.152"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-007-0090-8"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2345390"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01013"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00509"},{"key":"ref43","article-title":"Crowdsourcing annotations for visual object detection","author":"su","year":"2012","journal-title":"Proc AAAI Conf Artif Intell Workshop"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.129"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00664"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6758"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00479"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00441"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11205"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3119563"},{"key":"ref6","first-page":"370","article-title":"The unmanned aerial vehicle benchmark: Object detection and tracking","author":"yu","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3162892"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"ref81","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01517"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00162"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01493"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_3"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00525"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_5"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_20"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.789"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2003.1206512"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_45"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"1442","DOI":"10.1109\/TPAMI.2013.230","article-title":"Visual tracking: An experimental survey","volume":"36","author":"smeulders","year":"2014","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.465"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197528"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_35"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2648793"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00937"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413959"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_27"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.267"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_33"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68238-5_43"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_46"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01309"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00942"},{"key":"ref24","first-page":"191","article-title":"The visual object tracking VOT2014 challenge results","author":"hadfield","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00630"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2482905"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6944"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68238-5_39"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.230"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00670"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_41"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00472"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00142"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2388226"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00140"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.312"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00411"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.128"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2417577"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_19"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_7"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.196"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10144448\/10004511.pdf?arnumber=10004511","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,18]],"date-time":"2024-11-18T18:54:51Z","timestamp":1731956091000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10004511\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,1]]},"references-count":96,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3232854","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,1]]}}}