{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T16:24:28Z","timestamp":1781367868906,"version":"3.54.1"},"reference-count":45,"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-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62271377"],"award-info":[{"award-number":["62271377"]}],"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":["62171347"],"award-info":[{"award-number":["62171347"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Research and Development Program of Shaanxi","award":["2021ZDLGY0106"],"award-info":[{"award-number":["2021ZDLGY0106"]}]},{"name":"Key Research and Development Program of Shaanxi","award":["2022ZDLGY0112"],"award-info":[{"award-number":["2022ZDLGY0112"]}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021ZD0110404"],"award-info":[{"award-number":["2021ZD0110404"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Scientific Technological Innovation Research Project by Ministry of Education"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Geosci. Remote Sensing"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tgrs.2022.3224244","type":"journal-article","created":{"date-parts":[[2022,11,24]],"date-time":"2022-11-24T16:35:09Z","timestamp":1669307709000},"page":"1-16","source":"Crossref","is-referenced-by-count":52,"title":["A Joint-Training Two-Stage Method For Remote Sensing Image Captioning"],"prefix":"10.1109","volume":"60","author":[{"given":"Xiutiao","family":"Ye","sequence":"first","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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 Ministry of Education of China, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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 Ministry of Education of China, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jihui","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruixuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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 Ministry of Education of China, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5903-6150","authenticated-orcid":false,"given":"Fausto","family":"Giunchiglia","sequence":"additional","affiliation":[{"name":"Department of Information Engineering and Computer Science, University of Trento, Trento, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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 Ministry of Education of China, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"arXiv 1409 1556"},{"key":"ref38","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref32","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Proc Assoc Comput Linguistics"},{"key":"ref31","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 2nd Workshop Statist Mach Translat"},{"key":"ref30","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":"ref37","first-page":"1","article-title":"On the variance of the adaptive learning rate and beyond","author":"liu","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3390\/rs11060612"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2959208"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1080\/01431161.2019.1594439"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3044054"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3390\/rs11202349"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3010106"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3390\/rs12060939"},{"key":"ref18","article-title":"Recurrent attention and semantic gate for remote sensing image captioning","volume":"13","author":"li","year":"2021","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3132095"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2677464"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1869790.1869829"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2018.01.016"},{"key":"ref27","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"2013","journal-title":"arXiv 1312 6114"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/0364-0213(90)90002-E"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2014.2357078"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CITS.2016.7546397"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21756"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2776321"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3295748"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3105004"},{"key":"ref45","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","volume":"37","author":"xu","year":"2015","journal-title":"Mach Learn Res"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1099"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3031111"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2951636"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3070383"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2019.2893772"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00486"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3128140"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540039"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/36\/9633014\/09961235.pdf?arnumber=9961235","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:23:24Z","timestamp":1672082604000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9961235\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2022.3224244","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}