{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T07:02:05Z","timestamp":1775890925737,"version":"3.50.1"},"reference-count":472,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Key Scientific Technological Innovation Research Project by Ministry of Education"},{"name":"State Key Program and the Foundation for Innovative Research Groups of the National Natural Science Foundation of China","award":["61836009"],"award-info":[{"award-number":["61836009"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22B2054"],"award-info":[{"award-number":["U22B2054"]}],"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":["62076192"],"award-info":[{"award-number":["62076192"]}],"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":["62006177"],"award-info":[{"award-number":["62006177"]}],"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":["61902298"],"award-info":[{"award-number":["61902298"]}],"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":["61573267"],"award-info":[{"award-number":["61573267"]}],"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":["61906150"],"award-info":[{"award-number":["61906150"]}],"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":["62276199"],"award-info":[{"award-number":["62276199"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013314","name":"Higher Education Discipline Innovation Project","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013314","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Program for Cheung Kong Scholars and Innovative Research Team in University","award":["IRT 15R53"],"award-info":[{"award-number":["IRT 15R53"]}]},{"name":"ST Innovation Project from the Chinese Ministry of Education"},{"name":"Key Research and Development Program in Shaanxi Province of China","award":["2019ZDLGY03-06"],"award-info":[{"award-number":["2019ZDLGY03-06"]}]},{"name":"National Science Basic Research Plan in Shaanxi Province of China","award":["2022JQ-607"],"award-info":[{"award-number":["2022JQ-607"]}]},{"name":"China Postdoctoral Fund","award":["2022T150506"],"award-info":[{"award-number":["2022T150506"]}]},{"name":"Scientific Research Project of Education Department in Shaanxi Province of China","award":["20JY023"],"award-info":[{"award-number":["20JY023"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/jstars.2023.3289293","type":"journal-article","created":{"date-parts":[[2023,6,26]],"date-time":"2023-06-26T18:38:24Z","timestamp":1687804704000},"page":"1-45","source":"Crossref","is-referenced-by-count":54,"title":["Transformer Meets Remote Sensing Video Detection and Tracking: A Comprehensive Survey"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3354-9617","authenticated-orcid":false,"given":"Licheng","family":"Jiao","sequence":"first","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, International Research Center of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0296-0393","authenticated-orcid":false,"given":"Xin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, International Research Center of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8780-5455","authenticated-orcid":false,"given":"Xu","family":"Liu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, International Research Center of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5669-9354","authenticated-orcid":false,"given":"Fang","family":"Liu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, International Research Center of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4796-5737","authenticated-orcid":false,"given":"Shuyuan","family":"Yang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, International Research Center of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8872-2195","authenticated-orcid":false,"given":"Wenping","family":"Ma","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, International Research Center of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6130-2518","authenticated-orcid":false,"given":"Lingling","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, International Research Center of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5472-1426","authenticated-orcid":false,"given":"Puhua","family":"Chen","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, International Research Center of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7372-9180","authenticated-orcid":false,"given":"Zhixi","family":"Feng","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, International Research Center of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6095-8830","authenticated-orcid":false,"given":"Yuwei","family":"Guo","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, International Research Center of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1375-0778","authenticated-orcid":false,"given":"Xu","family":"Tang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, International Research Center of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1996-186X","authenticated-orcid":false,"given":"Biao","family":"Hou","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, International Research Center of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0379-2042","authenticated-orcid":false,"given":"Xiangrong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, International Research Center of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5412-7793","authenticated-orcid":false,"given":"Jing","family":"Bai","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, International Research Center of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6943-4657","authenticated-orcid":false,"given":"Dou","family":"Quan","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, International Research Center of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8068-6767","authenticated-orcid":false,"given":"Junpeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, International Research Center of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi'an, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2023.3247455"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3119654"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3176858"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3104603"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3146035"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3116798"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2022.3198643"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3154922"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2021.3105440"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2020.3036602"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3169815"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3168465"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3144158"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3163410"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3168697"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2021.3095166"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3183468"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3162964"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3174135"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3160007"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3177235"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2934760"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref27","first-page":"7487","article-title":"Stabilizing transformers for reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Parisotto","year":"2020"},{"key":"ref28","first-page":"15475","article-title":"ResT: An efficient transformer for visual recognition","volume":"34","author":"Zhang","year":"2021","journal-title":"in Proc. Int. Conf. Neural Inf. Process. Syst."},{"key":"ref29","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3152247"},{"key":"ref32","article-title":"Relating transformers to models and neural representations of the hippocampal formation","author":"Whittington","year":"2021"},{"key":"ref33","first-page":"1180","article-title":"Dense associative memory for pattern recognition","author":"Krotov","year":"2016","journal-title":"in Proc. Int. Conf. Neural Inf. Process. Syst."},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2021.3115137"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3130436"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2882926"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2921827"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3101398"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00317"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2868561"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00162"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3154286"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3009034"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3113169"},{"key":"ref46","first-page":"13695","article-title":"Self-supervised multi-object tracking with cross-input consistency","volume":"34","author":"Bastani","year":"2021","journal-title":"in Proc. Int. Conf. Neural Inf. Process. Syst."},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2017.2776899"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3137606"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3045634"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3158652"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS47720.2021.9554763"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1561\/2200000016"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3077257"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS.2019.8900196"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2944097"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00421"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2980419"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2770319"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00699"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.468"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2922648"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2943366"},{"key":"ref63","first-page":"1935","article-title":"Deep attentive tracking via reciprocative learning","author":"Pu","year":"2018","journal-title":"in Proc. Int. Conf. Neural Inf. Process. Syst."},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3055362"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2929034"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00260"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00064"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6828"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3125504"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3060862"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.10.005"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICME46284.2020.9102840"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3050073"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2990089"},{"key":"ref75","first-page":"3056","article-title":"Hierarchical attentive recurrent tracking","volume":"30","author":"Kosiorek","year":"2017","journal-title":"in Proc. Int. Conf. Neural Inf. Process. Syst."},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2869277"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3148876"},{"key":"ref78","first-page":"16743","article-title":"SwinTrack: A simple and strong baseline for transformer tracking","volume-title":"Adv. Neural Inform. Process. Syst.","author":"Lin","year":"2021"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2691769"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01314-1"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2779856"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3139121"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1087-1"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2843129"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2876253"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3115491"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-01147-z"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2018.2878467"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01513-4"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3152250"},{"key":"ref91","first-page":"1192","article-title":"Prototypical cross-attention networks for multiple object tracking and segmentation","volume":"34","author":"Ke","year":"2021","journal-title":"in Proc. Int. Conf. Neural Inf. Process. Syst."},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3165376"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01332"},{"key":"ref95","article-title":"VRT: A video restoration transformer","author":"Liang","year":"2022"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01325"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01696"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00932"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20028"},{"key":"ref101","article-title":"Time is MattEr: Temporal self-supervision for video transformers","author":"Yun","year":"2022"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3243465"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3142279"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3187135"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3143368"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3182809"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2020.2971763"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3171551"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3165885"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11205"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2021.3111183"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3140809"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01266-1"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS.2019.8900572"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3124222"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2746262"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2926164"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00739"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2020.3034677"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2843761"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3066675"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS.2016.7729316"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00256"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3109028"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00859"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3211695"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2668278"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01231-y"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3143532"},{"key":"ref131","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2014"},{"key":"ref132","first-page":"577","article-title":"Attention-based models for speech recognition","author":"Chorowski","year":"2015","journal-title":"in Int. Conf. Neural Inf. Process. Syst."},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1176"},{"key":"ref134","first-page":"2793","article-title":"Attention is not all you need: Pure attention loses rank doubly exponentially with depth","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dong"},{"key":"ref135","article-title":"Conditional positional encodings for vision transformers","author":"Chu","year":"2021"},{"key":"ref136","article-title":"Graph-Bert: Only attention is needed for learning graph representations","author":"Zhang","year":"2020"},{"key":"ref137","first-page":"11307","article-title":"Generative video transformer: Can objects be the words?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wu"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00599"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"ref141","first-page":"1243","article-title":"Convolutional sequence to sequence learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gehring","year":"2017"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00983"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3186400"},{"key":"ref144","first-page":"21618","article-title":"Rethinking graph transformers with spectral attention","volume":"34","author":"Kreuzer","year":"2021","journal-title":"in Proc. Int. Conf. Neural Inf. Process. Syst."},{"key":"ref145","article-title":"UniFormer: Unified transformer for efficient spatiotemporal representation learning","author":"Li","year":"2022"},{"key":"ref146","article-title":"A mathematical framework for transformer circuits","volume-title":"Transformer Circuits Thread","author":"Elhage","year":"2021"},{"key":"ref147","article-title":"In-context learning and induction heads","volume-title":"Transformer Circuits Thread","author":"Olsson","year":"2022"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_18"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1145\/3530811"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3093977"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20142"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3186634"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3063381"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1167"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2020.10.004"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3109061"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00069"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87589-3_28"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00259"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_17"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3026051"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3130716"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3144894"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3152425"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451652"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"ref171","first-page":"12559","article-title":"Self-supervised graph transformer on large-scale molecular data","volume":"33","author":"Rong","year":"2020","journal-title":"in Proc. Int. Conf. Neural Inf. Process. Syst."},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2022.3198244"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3185088"},{"key":"ref175","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref176","article-title":"How do vision transformers work?","author":"Park","year":"2022"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3185640"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3115699"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3151353"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2020.3009352"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3172410"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3095505"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3058049"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2020.3026587"},{"key":"ref185","article-title":"Competitive inner-imaging squeeze and excitation for residual network","author":"Hu","year":"2018"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2020.2968550"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3144017"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3043267"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2021.3058549"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3066432"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2997200"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2020.2997081"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1807.06521"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3127232"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3178479"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2020.2988294"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3144165"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3189044"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2020.3037893"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS46834.2022.9883686"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3085870"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3159544"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3091758"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.19"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3154390"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3169479"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3137967"},{"key":"ref209","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3132027"},{"key":"ref210","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref212","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"ref213","first-page":"18590","article-title":"All tokens matter: Token labeling for training better vision transformers","volume":"34","author":"Jiang","year":"2021","journal-title":"in Proc. Int. Conf. Neural Inf. Process. Syst."},{"key":"ref214","article-title":"Focal self-attention for local-global interactions in vision transformers","author":"Yang","year":"2021"},{"key":"ref215","article-title":"ELSA: Enhanced local self-attention for vision transformer","author":"Zhou","year":"2021"},{"key":"ref216","article-title":"BOAT: Bilateral local attention vision transformer","author":"Yu","year":"2022"},{"key":"ref217","first-page":"15908","article-title":"Transformer in transformer","volume":"34","author":"Han","year":"2021","journal-title":"in Proc. Int. Conf. Neural Inf. Process. Syst."},{"key":"ref218","article-title":"PyramidTNT: Improved transformer-in-transformer baselines with pyramid architecture","author":"Han","year":"2022"},{"key":"ref219","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00165"},{"key":"ref220","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume":"34","author":"Chu","year":"2021","journal-title":"in Proc. Int. Conf. Neural Inf. Process. Syst."},{"key":"ref221","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref222","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-023-0364-2"},{"key":"ref223","article-title":"On the connection between local attention and dynamic depth-wise convolution","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Han","year":"2021"},{"key":"ref224","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00089"},{"key":"ref225","article-title":"TRT-ViT: TensorRT-oriented vision transformer","author":"Xia","year":"2022"},{"key":"ref226","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00042"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00518"},{"key":"ref228","first-page":"28522","article-title":"ViTAE: Vision transformer advanced by exploring intrinsic inductive bias","volume":"34","author":"Xu","year":"2021","journal-title":"in Proc. Int. Conf. Neural Inf. Process. Syst."},{"key":"ref229","article-title":"HRViT: Multi-scale high-resolution vision transformer","author":"Gu","year":"2021"},{"key":"ref230","first-page":"7281","article-title":"HRFormer: High-resolution vision transformer for dense predict","volume":"34","author":"Yuan","year":"2021","journal-title":"in Proc. Int. Conf. Neural Inf. Process. Syst."},{"key":"ref231","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"ref232","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02007"},{"key":"ref233","article-title":"Adaptive transformers in RL","author":"Kumar","year":"2020"},{"key":"ref234","article-title":"CoBERL: Contrastive BERT for reinforcement learning","author":"Banino","year":"2021"},{"key":"ref235","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475272"},{"key":"ref236","first-page":"12493","article-title":"Keeping your eye on the ball: Trajectory attention in video transformers","volume":"34","author":"Patrick","year":"2021","journal-title":"in Proc. Int. Conf. Neural Inf. Process. Syst."},{"key":"ref237","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref238","first-page":"19594","article-title":"Space-time mixing attention for video transformer","volume":"34","author":"Bulat","year":"2021","journal-title":"in Proc. Int. Conf. Neural Inf. Process. Syst."},{"key":"ref239","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00560"},{"key":"ref240","first-page":"2491","article-title":"Associating objects with transformers for video object segmentation","volume":"34","author":"Yang","year":"2021","journal-title":"in Proc. Int. Conf. Neural Inf. Process. Syst."},{"key":"ref241","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00352"},{"key":"ref242","first-page":"3965","article-title":"CoAtNet: Marrying convolution and attention for all data sizes","volume":"34","author":"Dai","year":"2021","journal-title":"in Proc. Int. Conf. Neural Inf. Process. Syst."},{"key":"ref243","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3355890"},{"key":"ref244","article-title":"Next-ViT: Next generation vision transformer for efficient deployment in realistic industrial scenarios","author":"Li","year":"2022"},{"key":"ref245","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref246","article-title":"Lite transformer with long-short range attention","author":"Wu","year":"2020"},{"key":"ref247","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref248","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01166"},{"key":"ref249","first-page":"2204","article-title":"Recurrent models of visual attention","author":"Mnih","year":"2014","journal-title":"in Proc. Int. Conf. Neural Inf. Process. Syst."},{"key":"ref250","article-title":"Multiple object recognition with visual attention","author":"Ba","year":"2014"},{"key":"ref251","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume":"34","author":"Chen","year":"2021","journal-title":"in Proc. Int. Conf. Neural Inf. Process. Syst."},{"key":"ref252","first-page":"1273","article-title":"Offline reinforcement learning as one big sequence modeling problem","volume":"34","author":"Janner","year":"2021","journal-title":"in Proc. Int. Conf. Neural Inf. Process. Syst."},{"key":"ref253","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3072381"},{"key":"ref254","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2953181"},{"key":"ref255","article-title":"Detecting tiny moving vehicles in satellite videos","author":"Ao","year":"2018"},{"key":"ref256","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3023175"},{"key":"ref257","first-page":"33","article-title":"GoDec: Randomized low-rank & sparse matrix decomposition in noisy case","volume-title":"Proc. 28th Int. Conf. Mach. Learn.","author":"Zhou","year":"2011"},{"key":"ref258","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3066696"},{"key":"ref259","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3117054"},{"key":"ref260","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3150760"},{"key":"ref261","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.132"},{"key":"ref262","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2828606"},{"key":"ref263","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2630731"},{"key":"ref264","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2976855"},{"key":"ref265","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3004696"},{"key":"ref266","doi-asserted-by":"publisher","DOI":"10.3390\/rs11202372"},{"key":"ref267","doi-asserted-by":"publisher","DOI":"10.1109\/RTEICT.2016.7808064"},{"key":"ref268","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS47720.2021.9554146"},{"key":"ref269","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2998782"},{"key":"ref270","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00097"},{"key":"ref271","doi-asserted-by":"publisher","DOI":"10.1109\/ICFSP55781.2022.9924854"},{"key":"ref272","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2345390"},{"key":"ref273","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2917703"},{"key":"ref274","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2965302"},{"key":"ref275","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2978512"},{"key":"ref276","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2020.2988165"},{"key":"ref277","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2933488"},{"key":"ref278","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3179770"},{"key":"ref279","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3063144"},{"key":"ref280","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.513"},{"key":"ref281","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01438"},{"key":"ref282","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS47720.2021.9554131"},{"key":"ref283","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.465"},{"key":"ref284","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3077640"},{"key":"ref285","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2020.2971657"},{"key":"ref286","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3063001"},{"key":"ref287","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3096809"},{"key":"ref288","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33765-9_50"},{"key":"ref289","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00515"},{"key":"ref290","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.129"},{"key":"ref291","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.531"},{"key":"ref292","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.733"},{"key":"ref293","doi-asserted-by":"publisher","DOI":"10.1023\/b:visi.0000029664.99615.94"},{"key":"ref294","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_6"},{"key":"ref295","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3041332"},{"key":"ref296","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.105526"},{"key":"ref297","article-title":"TAda! Temporally-adaptive convolutions for video understanding","author":"Huang","year":"2021"},{"key":"ref298","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00687"},{"key":"ref299","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00441"},{"key":"ref300","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00628"},{"key":"ref301","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00942"},{"key":"ref302","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00630"},{"key":"ref303","doi-asserted-by":"publisher","DOI":"10.1145\/3488933.3488934"},{"key":"ref304","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107071"},{"key":"ref305","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3056684"},{"key":"ref306","first-page":"293","article-title":"Tracking holistic object representations","volume-title":"Proc. IEEE 30th British Mach. Vis. Conf. Trans. Antennas Propag.","author":"Sauer","year":"2019"},{"key":"ref307","article-title":"TrTr: Visual tracking with transformer","author":"Zhao","year":"2021"},{"key":"ref308","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"ref309","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00303"},{"key":"ref310","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01517"},{"key":"ref311","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"ref312","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_9"},{"key":"ref313","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"ref314","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3162599"},{"key":"ref315","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00479"},{"key":"ref316","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00196"},{"key":"ref317","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-03352-3"},{"key":"ref318","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981248"},{"key":"ref319","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00935"},{"key":"ref320","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108502"},{"key":"ref321","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3234372"},{"key":"ref322","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS47720.2021.9553779"},{"key":"ref323","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_27"},{"key":"ref324","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.312"},{"key":"ref325","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2388226"},{"key":"ref326","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2866955"},{"key":"ref327","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS.2018.8518302"},{"key":"ref328","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS.2018.8518431"},{"key":"ref329","first-page":"23703","article-title":"Tracking people with 3D representations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Rajasegaran","year":"2021"},{"key":"ref330","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_16"},{"key":"ref331","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2849374"},{"key":"ref332","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3087898"},{"key":"ref333","first-page":"652","article-title":"PointNet: Deep learning on point sets for 3D classification and segmentation","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Qi","year":"2017"},{"key":"ref334","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2687462"},{"key":"ref335","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298832"},{"key":"ref336","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3019915"},{"key":"ref337","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3044219"},{"key":"ref338","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2881123"},{"key":"ref339","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2928123"},{"key":"ref340","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298718"},{"key":"ref341","doi-asserted-by":"publisher","DOI":"10.1109\/34.969114"},{"key":"ref342","doi-asserted-by":"publisher","DOI":"10.1121\/1.398863"},{"key":"ref343","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_7"},{"key":"ref344","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2929520"},{"key":"ref345","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01460-0"},{"key":"ref346","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01527-y"},{"key":"ref347","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611972788.20"},{"key":"ref348","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref349","article-title":"Objects as points","author":"Zhou","year":"2019"},{"key":"ref350","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.164"},{"key":"ref351","article-title":"Vision meets drones: A challenge","author":"Zhu","year":"2018"},{"key":"ref352","article-title":"Vision meets drones: Past, present and future","author":"Zhu","year":"2020"},{"key":"ref353","doi-asserted-by":"publisher","DOI":"10.1016\/j.imed.2022.07.002"},{"key":"ref354","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00493"},{"key":"ref355","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_38"},{"key":"ref356","article-title":"A generalization of transformer networks to graphs","author":"Dwivedi","year":"2020"},{"key":"ref357","first-page":"13266","article-title":"Representing long-range context for graph neural networks with global attention","volume":"34","author":"Wu","year":"2021","journal-title":"in Proc. Int. Conf. Neural Inf. Process. Syst."},{"key":"ref358","first-page":"3469","article-title":"Structure-aware transformer for graph representation learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref359","doi-asserted-by":"publisher","DOI":"10.1038\/s42003-022-03557-9"},{"key":"ref360","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-021-00376-1"},{"key":"ref361","doi-asserted-by":"publisher","DOI":"10.1038\/s41562-021-01194-6"},{"key":"ref362","doi-asserted-by":"publisher","DOI":"10.1038\/s41583-021-00473-5"},{"key":"ref363","doi-asserted-by":"publisher","DOI":"10.1038\/s41593-020-0653-3"},{"key":"ref364","doi-asserted-by":"publisher","DOI":"10.1038\/s42254-021-00314-5"},{"key":"ref365","article-title":"Physics-informed machine learning: A survey on problems, methods and applications","author":"Hao","year":"2022"},{"key":"ref366","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2012.02.008"},{"key":"ref367","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2015.7257269"},{"key":"ref368","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-015-1702-9"},{"key":"ref369","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2016.04.021"},{"key":"ref370","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2016.03.009"},{"key":"ref371","doi-asserted-by":"publisher","DOI":"10.1016\/j.cnsns.2016.08.001"},{"key":"ref372","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.09.013"},{"key":"ref373","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2018.10.045"},{"key":"ref374","first-page":"887","article-title":"Dynamic visual reasoning by learning differentiable physics models from video and language","volume":"34","author":"Ding","year":"2021","journal-title":"in Proc. Int. Conf. Neural Inf. Process. Syst."},{"key":"ref375","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01066"},{"key":"ref376","doi-asserted-by":"publisher","DOI":"10.4135\/9781412952637.n77"},{"key":"ref377","first-page":"3020","article-title":"Learning representations for counterfactual inference","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Johansson","year":"2016"},{"key":"ref378","article-title":"From unstructured text to causal knowledge graphs: A transformer-based approach","author":"Friedman","year":"2022"},{"key":"ref379","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539472"},{"key":"ref380","article-title":"A survey on graph neural networks and graph transformers in computer vision: A task-oriented perspective","author":"Chen","year":"2022"},{"key":"ref381","article-title":"Neural architecture search with reinforcement learning","author":"Zoph","year":"2016"},{"key":"ref382","article-title":"Designing neural network architectures using reinforcement learning","author":"Baker","year":"2016"},{"key":"ref383","first-page":"2902","article-title":"Large-scale evolution of image classifiers","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Real","year":"2017"},{"key":"ref384","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"},{"key":"ref385","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_2"},{"key":"ref386","first-page":"4095","article-title":"Efficient neural architecture search via parameters sharing","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pham","year":"2018"},{"key":"ref387","article-title":"ProxylessNAS: Direct neural architecture search on target task and hardware","author":"Cai","year":"2018"},{"key":"ref388","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00138"},{"key":"ref389","article-title":"A survey on neural architecture search","author":"Wistuba","year":"2019"},{"key":"ref390","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-05318-5_3"},{"key":"ref391","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01489"},{"key":"ref392","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00017"},{"key":"ref393","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00720"},{"key":"ref394","first-page":"5877","article-title":"The evolved transformer","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"So","year":"2019"},{"key":"ref395","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_9"},{"key":"ref396","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01206"},{"key":"ref397","article-title":"Searching for efficient multi-stage vision transformers","author":"Liao","year":"2021"},{"key":"ref398","article-title":"Lightweight vision transformer with cross feature attention","author":"Zhao","year":"2022"},{"key":"ref399","article-title":"MobileViT: Light-weight, general-purpose, and mobile-friendly vision transformer","author":"Mehta","year":"2021"},{"key":"ref400","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/121"},{"key":"ref401","article-title":"EdgeFormer: Improving light-weight ConvNets by learning from vision transformers","author":"Zhang","year":"2022"},{"key":"ref402","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"ref403","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00520"},{"key":"ref404","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01169"},{"key":"ref405","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref406","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref407","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref408","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"ref409","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01204"},{"key":"ref410","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-31880-4_2"},{"key":"ref411","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-70928-2_53"},{"key":"ref412","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2016.07.051"},{"key":"ref413","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2013.10.008"},{"key":"ref414","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2018.03.005"},{"key":"ref415","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2459137"},{"key":"ref416","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2014.2350987"},{"key":"ref417","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-49774-5_8"},{"key":"ref418","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-49774-5_5"},{"key":"ref419","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2006.1688293"},{"key":"ref420","volume-title":"Multi-objective Optim. Using Evol. Algorithms","author":"Deb","year":"2001"},{"key":"ref421","doi-asserted-by":"publisher","DOI":"10.1109\/4235.996017"},{"key":"ref422","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2007.892759"},{"key":"ref423","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2403849"},{"key":"ref424","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-014-0625-y"},{"key":"ref425","doi-asserted-by":"publisher","DOI":"10.1162\/evco_a_00289"},{"key":"ref426","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2004.831456"},{"key":"ref427","doi-asserted-by":"publisher","DOI":"10.1162\/106365600568202"},{"key":"ref428","first-page":"573","article-title":"A dynamic multi-objective evolutionary algorithm based on an orthogonal design","volume-title":"Proc. IEEE Int. Conf. Evol. Comput.","author":"Zeng","year":"2006"},{"key":"ref429","doi-asserted-by":"publisher","DOI":"10.1016\/j.amc.2008.05.151"},{"key":"ref430","doi-asserted-by":"publisher","DOI":"10.1109\/34.192463"},{"key":"ref431","doi-asserted-by":"publisher","DOI":"10.1109\/72.165591"},{"key":"ref432","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3118221"},{"key":"ref433","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3007412"},{"key":"ref434","article-title":"How framelets enhance graph neural networks","author":"Zheng","year":"2021"},{"key":"ref435","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3218735"},{"key":"ref436","article-title":"MWQ: Multiscale wavelet quantized neural networks","author":"Sun","year":"2021"},{"key":"ref437","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3181486"},{"key":"ref438","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2881482"},{"key":"ref439","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.11.015"},{"key":"ref440","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00856"},{"key":"ref441","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS47720.2021.9554705"},{"key":"ref442","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3149947"},{"key":"ref443","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3032958"},{"key":"ref444","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2022.3191783"},{"key":"ref445","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00891"},{"key":"ref446","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00862"},{"key":"ref447","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00525"},{"key":"ref448","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3275156"},{"key":"ref449","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref450","first-page":"1298","article-title":"data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Baevski","year":"2022"},{"key":"ref451","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3542634"},{"key":"ref452","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2014.09.027"},{"key":"ref453","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2016.2547638"},{"key":"ref454","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-10-3614-9_47"},{"key":"ref455","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2021.3088865"},{"key":"ref456","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2909781"},{"key":"ref457","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.11.077"},{"key":"ref458","doi-asserted-by":"publisher","DOI":"10.1117\/1.JRS.14.036501"},{"key":"ref459","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3001584"},{"key":"ref460","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3167830"},{"key":"ref461","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS.2015.7326597"},{"key":"ref462","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3184789"},{"key":"ref463","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2012.01.004"},{"key":"ref464","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2018.2872590"},{"key":"ref465","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3066508"},{"key":"ref466","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3073176"},{"key":"ref467","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3180548"},{"key":"ref468","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3046727"},{"key":"ref469","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2020.2990457"},{"key":"ref470","first-page":"3621","article-title":"Deep variational graph convolutional recurrent network for multivariate time series anomaly detection","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref471","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS52988.2021.9663810"},{"key":"ref472","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548199"}],"container-title":["IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4609443\/9973430\/10163641.pdf?arnumber=10163641","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T11:54:16Z","timestamp":1709294056000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10163641\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":472,"URL":"https:\/\/doi.org\/10.1109\/jstars.2023.3289293","relation":{},"ISSN":["1939-1404","2151-1535"],"issn-type":[{"value":"1939-1404","type":"print"},{"value":"2151-1535","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}