{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T15:17:10Z","timestamp":1780586230681,"version":"3.54.1"},"reference-count":98,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Scientific Research Fund of the Criminal Investigation Police University of China","award":["D2020032"],"award-info":[{"award-number":["D2020032"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["D2019023"],"award-info":[{"award-number":["D2019023"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3128140","type":"journal-article","created":{"date-parts":[[2021,11,15]],"date-time":"2021-11-15T22:16:34Z","timestamp":1637014594000},"page":"154086-154111","source":"Crossref","is-referenced-by-count":32,"title":["A Systematic Survey of Remote Sensing Image Captioning"],"prefix":"10.1109","volume":"9","author":[{"given":"Beigeng","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref33","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref31","first-page":"1995","article-title":"Convolutional networks for images, speech, and time series","volume":"3361","author":"lecun","year":"1995","journal-title":"The Handbook of Brain Theory and Neural Networks"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3070383"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.235"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540009"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238663"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS39084.2020.9323213"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS39084.2020.9323651"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.2112\/SI102-018.1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/M2GARSS47143.2020.9105191"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3390\/rs12060939"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3390\/rs12111874"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3031111"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207381"},{"key":"ref26","article-title":"Word-sentence framework for remote sensing image captioning","author":"wang","year":"2020","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2020.3009243"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/1869790.1869829"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3994"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1111\/j.1365-2451.2006.00546.x"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1177\/0163443712468776"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2019.11.023"},{"key":"ref55","author":"graff","year":"2003","journal-title":"English Gigaword LDC2003T05"},{"key":"ref54","year":"2018","journal-title":"Drone Manufacture in INDIA&#x2014;Team Dhaksha"},{"key":"ref53","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"chen","year":"2015","journal-title":"arXiv 1504 00325"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS.2017.8128075"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2776321"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2019.2893772"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-02698-1_49"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2951636"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2014.2357078"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3390\/rs11060612"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2942154"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref48","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"arXiv 1506 01497"},{"key":"ref47","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref41","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume":"25","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref43","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref73","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2016","journal-title":"arXiv 1609 02907"},{"key":"ref72","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":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref70","article-title":"Generating sequences with recurrent neural networks","author":"graves","year":"2013","journal-title":"arXiv 1308 0850 [cs]"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref77","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"arXiv 1706 03762"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref75","article-title":"Actor-critic sequence training for image captioning","author":"zhang","year":"2017","journal-title":"arXiv 1706 09601"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.681"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.21512\/comtech.v7i4.3746"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2675998"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref63","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Proc Text Summarization Branches Out"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1108\/00220410410560582"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.21236\/ADA164453"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2677464"},{"key":"ref69","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"arXiv 1409 3215 [cs]"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CITS.2016.7546397"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1264"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.3390\/rs12091444"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2019.04.015"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.3233\/HIS-170246"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1613\/jair.4900"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.05.080"},{"key":"ref98","doi-asserted-by":"crossref","DOI":"10.7326\/0003-4819-151-4-200908180-00135","article-title":"Preferred reporting items for systematic reviews and meta-analyses: The PRISMA statement","volume":"151","author":"moher","year":"2009","journal-title":"Ann Internal Med"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1080\/20964471.2019.1657720"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2016.03.014"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS.2019.8900503"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2962195"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3390\/rs11202349"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2020.01.067"},{"key":"ref14","article-title":"A novel actor dual-critic model for remote sensing image captioning","author":"chavhan","year":"2020","journal-title":"arXiv 2010 01999"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09294-7"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.105920"},{"key":"ref82","author":"cormen","year":"2009","journal-title":"Introduction to Algorithms"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3010106"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1099"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2959208"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijleo.2013.12.003"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2020.2980933"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2016.2572736"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.2307\/1942603"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1145\/3295748"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2014.2374218"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2015.2513898"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2015.2469138"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.108"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09615088.pdf?arnumber=9615088","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,7]],"date-time":"2022-03-07T20:56:29Z","timestamp":1646686589000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9615088\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":98,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3128140","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}