{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T16:20:45Z","timestamp":1775665245443,"version":"3.50.1"},"reference-count":76,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development (R&D) Program of China","doi-asserted-by":"publisher","award":["2020YFB2103900"],"award-info":[{"award-number":["2020YFB2103900"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014219","name":"National Science Fund for Distinguished Young Scholars","doi-asserted-by":"publisher","award":["61825603"],"award-info":[{"award-number":["61825603"]}],"id":[{"id":"10.13039\/501100014219","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Geosci. Remote Sensing"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tgrs.2023.3250471","type":"journal-article","created":{"date-parts":[[2023,2,28]],"date-time":"2023-02-28T18:34:46Z","timestamp":1677609286000},"page":"1-13","source":"Crossref","is-referenced-by-count":120,"title":["RSVG: Exploring Data and Models for Visual Grounding on Remote Sensing Data"],"prefix":"10.1109","volume":"61","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7849-634X","authenticated-orcid":false,"given":"Yang","family":"Zhan","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi&#x2019;an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3953-585X","authenticated-orcid":false,"given":"Zhitong","family":"Xiong","sequence":"additional","affiliation":[{"name":"Chair of Data Science in Earth Observation, Technical University of Munich (TUM), Munich, Germany"}]},{"given":"Yuan","family":"Yuan","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi&#x2019;an, China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"EarthNets: Empowering AI in Earth observation","author":"Xiong","year":"2022","journal-title":"arXiv:2210.04936"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3127851"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3060705"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2776321"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3102590"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3132095"},{"key":"ref7","article-title":"Deep unsupervised contrastive hashing for large-scale cross-modal text-image retrieval in remote sensing","author":"Mikriukov","year":"2022","journal-title":"arXiv:2201.08125"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3124252"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3078451"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2988782"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3173811"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3203314"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00405"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3053459"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3199160"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2019.11.023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_26"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.493"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00437"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.470"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00205"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_49"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00447"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/155"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.95"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00477"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2911066"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00474"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00206"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2973983"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1044"},{"key":"ref34","article-title":"Real-time referring expression comprehension by single-stage grounding network","author":"Chen","year":"2018","journal-title":"arXiv:1812.03426"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00479"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00478"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01089"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_23"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01661"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3181516"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859880"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref43","first-page":"19652","article-title":"Referring transformer: A one-step approach to multi-task visual grounding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Li"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3147385"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00928"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01506"},{"key":"ref47","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_8"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01507"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548316"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2014.x.041"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.475"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00316"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00431"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1215"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413905"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00997"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01010"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01023"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00597"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.3115\/1613715.1613751"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/2858036.2858115"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref69","first-page":"1","article-title":"Universal transformers","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dehghani"},{"key":"ref70","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Assoc. Comput. Linguistics","author":"Kenton"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref74","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Loshchilov"},{"key":"ref75","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Statist.","author":"Glorot"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/36\/10006360\/10056343.pdf?arnumber=10056343","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T23:30:41Z","timestamp":1709422241000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10056343\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":76,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2023.3250471","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}