{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T19:08:37Z","timestamp":1783105717197,"version":"3.54.6"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/jstars.2019.2959208","type":"journal-article","created":{"date-parts":[[2020,2,12]],"date-time":"2020-02-12T16:17:22Z","timestamp":1581524242000},"page":"256-270","source":"Crossref","is-referenced-by-count":75,"title":["Retrieval Topic Recurrent Memory Network for Remote Sensing Image Captioning"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9406-167X","authenticated-orcid":false,"given":"Binqiang","family":"Wang","sequence":"first","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"}]},{"given":"Bo","family":"Qu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7037-5188","authenticated-orcid":false,"given":"Xiaoqiang","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00433"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01275"},{"key":"ref33","article-title":"CNN+CNN: Convolutional decoders for image captioning","author":"wang","year":"2018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00583"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.138"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00896"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00146"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-02698-1_49"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.681"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3390\/rs11060612"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2018.2840738"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CITS.2016.7546397"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2019.2893772"},{"key":"ref22","first-page":"2121","article-title":"Devise: A deep visual-semantic embedding model","author":"frome","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3994"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1036"},{"key":"ref23","first-page":"4233","article-title":"Text-guided attention model for image captioning","author":"mun","year":"0","journal-title":"Proc Assoc Adv Artif Intell"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.301"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1301"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-018-5856-1"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref52","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"lin","year":"0","journal-title":"Proc Assoc Comput Linguistics Workshop"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2878958"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS.2017.8128075"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00643"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2677464"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2776321"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21756"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2018.01.016"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICUAS.2018.8453310"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s40899-018-0244-6"},{"key":"ref18","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_21"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2018.2805923"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2018.2875304"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2019.2936652"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2810806"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2917161"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2893115"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2016.2616355"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1147"},{"key":"ref45","first-page":"1378","article-title":"Ask me anything: Dynamic memory networks for natural language processing","author":"kumar","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21512\/comtech.v7i4.3746"},{"key":"ref47","first-page":"1347","article-title":"VIP-CNN: A visual phrase reasoning convolutional neural network for visual relationship detection","author":"li","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref42","article-title":"Memory networks","author":"weston","year":"2014"},{"key":"ref41","article-title":"Neural turing machines","author":"graves","year":"2014"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1038\/nature20101"},{"key":"ref43","first-page":"2440","article-title":"End-to-end memory networks","author":"sukhbaatar","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"}],"container-title":["IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4609443\/8994817\/08995813.pdf?arnumber=8995813","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:30:10Z","timestamp":1641987010000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8995813\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/jstars.2019.2959208","relation":{},"ISSN":["1939-1404","2151-1535"],"issn-type":[{"value":"1939-1404","type":"print"},{"value":"2151-1535","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}