{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T13:05:54Z","timestamp":1769519154868,"version":"3.49.0"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Key Research and Development Program of Shaanxi","award":["2021ZDLGY01-06"],"award-info":[{"award-number":["2021ZDLGY01-06"]}]},{"name":"Key Research and Development Program of Shaanxi","award":["2022ZDLGY01-12"],"award-info":[{"award-number":["2022ZDLGY01-12"]}]},{"name":"National Key Research and Development Program of China","award":["2021ZD0110404"],"award-info":[{"award-number":["2021ZD0110404"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62171347"],"award-info":[{"award-number":["62171347"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010449","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010449","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/jstars.2022.3194076","type":"journal-article","created":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T21:55:44Z","timestamp":1659477344000},"page":"6220-6235","source":"Crossref","is-referenced-by-count":24,"title":["Multimodal Fusion Remote Sensing Image\u2013Audio Retrieval"],"prefix":"10.1109","volume":"15","author":[{"given":"Rui","family":"Yang","sequence":"first","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, Xidian University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4940-1211","authenticated-orcid":false,"given":"Shuang","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, Xidian University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingzhi","family":"Sun","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, Xidian University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, Xidian University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Liao","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, Xidian University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3634-2275","authenticated-orcid":false,"given":"Yu","family":"Gu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, Xidian University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"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, Xidian University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3354-9617","authenticated-orcid":false,"given":"Licheng","family":"Jiao","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, Xidian University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1873987"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.142"},{"key":"ref3","first-page":"1247","article-title":"Deep canonical correlation analysis","volume-title":"Proc. 30th Int. Conf. Mach. Learn.","author":"Andrew","year":"2013"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/138"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00359"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654902"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01064"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00831"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00183"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2756911"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2015.2469138"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2949220"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3070872"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/PRRS.2018.8486338"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2020.02.006"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2979273"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3390\/rs12010084"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3060705"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2008.925367"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2013.2268736"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2012.2205158"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/d14-1179"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref28","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Krizhevsky","year":"2012"},{"key":"ref29","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ren","year":"2015"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00311"},{"key":"ref33","first-page":"1657","article-title":"Enhanced LSTM for natural language inference","volume-title":"Proc. 55th Annu. Meeting Assoc. Comput. Linguistics","author":"Chen","year":"2016"},{"key":"ref34","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref36","first-page":"1","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018","journal-title":"Open AI Tech. Rep."},{"key":"ref37","first-page":"13063","article-title":"Unified language model pre-training for natural language understanding and generation","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Dong","year":"2019"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2961634"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2760909"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3016020"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2019.2896948"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2984703"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3390\/rs12030405"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3078451"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3163706"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3155283"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-85099-1_8"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1020"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-44415-3_16"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459169"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/1452392.1452442"},{"key":"ref53","first-page":"2296","article-title":"Are you talking to a machine? Dataset and methods for multilingual image question","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Gao","year":"2015"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2461544"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s12193-015-0195-2"},{"key":"ref56","first-page":"14200","article-title":"Attention bottlenecks for multimodal fusion","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Nagrani","year":"2021"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475188"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2951820"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2017.2651056"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref65","first-page":"1866","article-title":"Unsupervised learning of spoken language with visual context","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Harwath","year":"2017"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.17706\/jsw.13.2.103-116"}],"container-title":["IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4609443\/9656571\/09847567.pdf?arnumber=9847567","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T11:19:53Z","timestamp":1706786393000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9847567\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/jstars.2022.3194076","relation":{},"ISSN":["1939-1404","2151-1535"],"issn-type":[{"value":"1939-1404","type":"print"},{"value":"2151-1535","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}