{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T16:24:29Z","timestamp":1781367869314,"version":"3.54.1"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Basic Research Program of China","doi-asserted-by":"publisher","award":["2017YFB0502900"],"award-info":[{"award-number":["2017YFB0502900"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61806193"],"award-info":[{"award-number":["61806193"]}],"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":["61702498"],"award-info":[{"award-number":["61702498"]}],"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":["61772510"],"award-info":[{"award-number":["61772510"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["QYZDB-SSW-JSC015"],"award-info":[{"award-number":["QYZDB-SSW-JSC015"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["SKLST2017010"],"award-info":[{"award-number":["SKLST2017010"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["XAB2017B26"],"award-info":[{"award-number":["XAB2017B26"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["XAB2017B15"],"award-info":[{"award-number":["XAB2017B15"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Xi\u2019an Postdoctoral Innovation Base Scientific Research Project"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Geosci. Remote Sensing"],"published-print":{"date-parts":[[2020,3]]},"DOI":"10.1109\/tgrs.2019.2951636","type":"journal-article","created":{"date-parts":[[2019,12,12]],"date-time":"2019-12-12T20:37:36Z","timestamp":1576183056000},"page":"1985-2000","source":"Crossref","is-referenced-by-count":90,"title":["Sound Active Attention Framework for Remote Sensing Image Captioning"],"prefix":"10.1109","volume":"58","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7037-5188","authenticated-orcid":false,"given":"Xiaoqiang","family":"Lu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9406-167X","authenticated-orcid":false,"given":"Binqiang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8398-6324","authenticated-orcid":false,"given":"Xiangtao","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.235"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540009"},{"key":"ref33","first-page":"1","article-title":"You said that?","author":"chung","year":"2017","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.5121\/csit.2012.2337"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_48"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_3"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238663"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/BF02943243"},{"key":"ref34","first-page":"1","article-title":"Deep cross-modal retrieval for remote sensing image and audio","author":"guo","year":"2018","journal-title":"Proc IAPR Workshop Pattern Recognit Remote Sens"},{"key":"ref28","first-page":"772","article-title":"Learning joint statistical models for audio-visual fusion and segregation","author":"fisher","year":"2001","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.264"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_27"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2677464"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CITS.2016.7546397"},{"key":"ref20","first-page":"4133","article-title":"Image caption with global-local attention","author":"li","year":"2017","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref22","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s00221-006-0578-4"},{"key":"ref26","first-page":"5167","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","author":"wang","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178347"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2014.2357078"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-018-5856-1"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.07.001"},{"key":"ref58","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref55","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","author":"banerjee","year":"2005","journal-title":"Proc ACL Workshop Intrinsic Extrinsic Eval Measures Mach Transl Summarization"},{"key":"ref54","first-page":"10","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Proceedings of the workshop on text summarization branches"},{"key":"ref53","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref10","first-page":"6214","article-title":"Low-shot learning for the semantic segmentation of remote sensing imagery","volume":"56","author":"ronald","year":"2018","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1080\/2150704X.2017.1410291"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2702596"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2756851"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2783902"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/rs10020290"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3390\/rs10020243"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2773199"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3390\/rs10030443"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3390\/rs10030400"},{"key":"ref4","first-page":"4798","article-title":"Natural language description of remote sensing images based on deep learning","author":"gao","year":"2017","journal-title":"Proc Int Geosci Remote Sens Symp"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2776321"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2531179"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1080\/2150704X.2017.1415473"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2018.04.014"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.08.015"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/1869790.1869829"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2018.2810320"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1047"},{"key":"ref48","first-page":"1","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014","journal-title":"Proc Neural Inf Process Syst Deep Learn Workshop"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-02698-1_49"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00583"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268967"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3390\/rs11060612"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/36\/9014411\/08931249.pdf?arnumber=8931249","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:11:24Z","timestamp":1651068684000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8931249\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3]]},"references-count":59,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tgrs.2019.2951636","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,3]]}}}