{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T15:17:40Z","timestamp":1780586260748,"version":"3.54.1"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"National Key R&D Program of China","award":["2022ZD0118402"],"award-info":[{"award-number":["2022ZD0118402"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/jstars.2023.3305889","type":"journal-article","created":{"date-parts":[[2023,8,16]],"date-time":"2023-08-16T17:29:09Z","timestamp":1692206949000},"page":"7704-7717","source":"Crossref","is-referenced-by-count":35,"title":["From Plane to Hierarchy: Deformable Transformer for Remote Sensing Image Captioning"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8207-4462","authenticated-orcid":false,"given":"Runyan","family":"Du","sequence":"first","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4291-4970","authenticated-orcid":false,"given":"Wei","family":"Cao","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8903-2708","authenticated-orcid":false,"given":"Wenkai","family":"Zhang","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5083-3578","authenticated-orcid":false,"given":"Guo","family":"Zhi","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0038-9816","authenticated-orcid":false,"given":"Xian","family":"Sun","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6071-8014","authenticated-orcid":false,"given":"Shuoke","family":"Li","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8277-4223","authenticated-orcid":false,"given":"Jihao","family":"Li","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Description generation for remote sensing images using attribute attention mechanism","volume":"11","author":"zhang","year":"2019","journal-title":"Remote Sens"},{"key":"ref12","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"0","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3102590"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3031111"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.105076"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2959208"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2776321"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS.2017.8128075"},{"key":"ref54","article-title":"Transforming remote sensing images to textual descriptions","volume":"108","author":"zia","year":"2022","journal-title":"Int J Appl Earth Observ Geoinf"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3070383"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3132095"},{"key":"ref19","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Neural Inf Process Syst"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00583"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-018-5856-1"},{"key":"ref46","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"lin","year":"0","journal-title":"Proc ACL Text Summarization Workshop"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/1869790.1869829"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2014.2357078"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2675998"},{"key":"ref49","article-title":"microsoft COCO captions: Data collection and evaluation Server","author":"chen","year":"2015"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CITS.2016.7546397"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref5","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014"},{"key":"ref40","first-page":"28","article-title":"iSAID: A large-scale dataset for instance segmentation in aerial images","author":"waqas","year":"0","journal-title":"Proc IEEE\/CVF Conf Comput Vis Pattern Recognit Workshops"},{"key":"ref35","first-page":"8778","article-title":"Generalized cross entropy loss for training deep neural networks with noisy labels","author":"zhang","year":"0","journal-title":"Proc 32 Int Conf Neural Inf Process Syst"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/0146-664X(79)90046-7"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref36","first-page":"4694","article-title":"When does label smoothing help ?","author":"m\u00fcller","year":"0","journal-title":"Proc 33rd Int Conf Neural Inf Process Syst"},{"key":"ref31","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"chen","year":"2017"},{"key":"ref30","first-page":"2333","article-title":"Generating multisentence lingual descriptions of indoor scenes","author":"lin","year":"2015","journal-title":"Computer Sci"},{"key":"ref33","article-title":"Layer normalization","author":"ba","year":"2016"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2677464"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2019.2893772"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref38","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3010106"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3044054"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3390\/app8050739"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3201474"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2951636"},{"key":"ref22","first-page":"156","author":"vapnik","year":"1998","journal-title":"Statistical Learning Theory"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3105004"},{"key":"ref28","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"0","journal-title":"Proc NAACL-HLT"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.68"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2947482"}],"container-title":["IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4609443\/9973430\/10221707.pdf?arnumber=10221707","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,7]],"date-time":"2024-02-07T05:06:52Z","timestamp":1707282412000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10221707\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/jstars.2023.3305889","relation":{},"ISSN":["1939-1404","2151-1535"],"issn-type":[{"value":"1939-1404","type":"print"},{"value":"2151-1535","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}