{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T20:30:25Z","timestamp":1771533025749,"version":"3.50.1"},"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\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001871","name":"Fundao para a Cincia e a Tecnologia","doi-asserted-by":"publisher","award":["2020.06106.BD"],"award-info":[{"award-number":["2020.06106.BD"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001871","name":"Fundao para a Cincia e a Tecnologia","doi-asserted-by":"publisher","award":["PTDC\/CCI-CIF\/32607\/2017 (MIMU)"],"award-info":[{"award-number":["PTDC\/CCI-CIF\/32607\/2017 (MIMU)"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]},{"name":"INESCID multiannual funding from the PIDDAC programme","award":["UIDB\/50021\/2020"],"award-info":[{"award-number":["UIDB\/50021\/2020"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2022.3151874","type":"journal-article","created":{"date-parts":[[2022,2,15]],"date-time":"2022-02-15T20:43:44Z","timestamp":1644957824000},"page":"24852-24863","source":"Crossref","is-referenced-by-count":25,"title":["Using Neural Encoder-Decoder Models With Continuous Outputs for Remote Sensing Image Captioning"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8741-8164","authenticated-orcid":false,"given":"Rita","family":"Ramos","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3856-2936","authenticated-orcid":false,"given":"Bruno","family":"Martins","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2988782"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3079918"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/rs12060939"},{"key":"ref4","article-title":"Von Mises\u2013Fisher loss for training sequence to sequence models with continuous outputs","author":"Kumar","year":"2018","journal-title":"arXiv:1812.04616"},{"key":"ref5","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3070872"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2677464"},{"key":"ref8","article-title":"From show to tell: A survey on deep learning-based image captioning","author":"Stefanini","year":"2021","journal-title":"arXiv:2107.06912"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CITS.2016.7546397"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2776321"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/rs11060612"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2962195"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2942154"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3390\/rs11202349"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2020.2980933"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS.2019.8900503"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3010106"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.105920"},{"key":"ref19","article-title":"SD-RSIC: Summarization driven deep remote sensing image captioning","author":"Sumbul","year":"2020","journal-title":"arXiv:2006.08432"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2959208"},{"key":"ref21","article-title":"Evaluation of text generation: A survey","author":"Celikyilmaz","year":"2020","journal-title":"arXiv:2006.14799"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-5626"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K19-1009"},{"key":"ref24","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"arXiv:2103.00020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3390\/info11020125"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref31","first-page":"1","article-title":"Attention is all you need","volume-title":"Proc. Annu. Meeting Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref32","first-page":"794","article-title":"GradNorm: Gradient normalization for adaptive loss balancing in deep multitask networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/1869790.1869829"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2014.2357078"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref37","article-title":"BERTScore: Evaluating text generation with BERT","author":"Zhang","year":"2019","journal-title":"arXiv:1904.09675"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018142"},{"key":"ref39","article-title":"Classical structured prediction losses for sequence to sequence learning","author":"Edunov","year":"2017","journal-title":"arXiv:1711.04956"},{"key":"ref40","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","author":"Bengio","year":"2015","journal-title":"arXiv:1506.03099"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref44","article-title":"Visual transformers: Token-based image representation and processing for computer vision","author":"Wu","year":"2020","journal-title":"arXiv:2006.03677"},{"key":"ref45","article-title":"CPTR: Full transformer network for image captioning","author":"Liu","year":"2021","journal-title":"arXiv:2101.10804"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09714367.pdf?arnumber=9714367","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,17]],"date-time":"2024-01-17T23:36:11Z","timestamp":1705534571000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9714367\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3151874","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}