{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T21:01:13Z","timestamp":1782507673303,"version":"3.54.5"},"reference-count":34,"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\/501100013129","name":"Ministry of SMEs and Start-ups, South Korea","doi-asserted-by":"publisher","award":["S3010704"],"award-info":[{"award-number":["S3010704"]}],"id":[{"id":"10.13039\/501100013129","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["2020R1A4A101777511"],"award-info":[{"award-number":["2020R1A4A101777511"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["2021R1I1A3056900"],"award-info":[{"award-number":["2021R1I1A3056900"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2022.3161428","type":"journal-article","created":{"date-parts":[[2022,3,22]],"date-time":"2022-03-22T19:42:31Z","timestamp":1647978151000},"page":"33679-33694","source":"Crossref","is-referenced-by-count":56,"title":["Deep Learning Approaches Based on Transformer Architectures for Image Captioning Tasks"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8535-1763","authenticated-orcid":false,"given":"Roberto","family":"Castro","sequence":"first","affiliation":[{"name":"Deep Learning for Autonomous Driving, Robotics, and Computer Vision Research Group (DeepARC Research), School of Mathematical and Computational Sciences, Yachay Tech University, Urcuquí, Ecuador"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3950-2169","authenticated-orcid":false,"given":"Israel","family":"Pineda","sequence":"additional","affiliation":[{"name":"Deep Learning for Autonomous Driving, Robotics, and Computer Vision Research Group (DeepARC Research), School of Mathematical and Computational Sciences, Yachay Tech University, Urcuquí, Ecuador"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2533-3496","authenticated-orcid":false,"given":"Wansu","family":"Lim","sequence":"additional","affiliation":[{"name":"Department of Aeronautics, Mechanical and Electronic Convergence Engineering, Future Communications and Systems Laboratory (FCSL), Kumoh National Institute of Technology, Gumi-si, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4705-7923","authenticated-orcid":false,"given":"Manuel Eugenio","family":"Morocho-Cayamcela","sequence":"additional","affiliation":[{"name":"Deep Learning for Autonomous Driving, Robotics, and Computer Vision Research Group (DeepARC Research), School of Mathematical and Computational Sciences, Yachay Tech University, Urcuquí, Ecuador"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.162"},{"key":"ref3","first-page":"444","article-title":"Corpus-guided sentence generation of natural images","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Yang"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.5772\/4960"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.proeng.2015.01.404"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SPIN.2015.7095350"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113967"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-89941-7_13"},{"key":"ref11","first-page":"1243","article-title":"Learning to combine foveal glimpses with a third-order Boltzmann machine","volume-title":"Advance Neural Information Processing System","volume":"1","author":"Larochelle"},{"key":"ref12","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2016"},{"key":"ref13","first-page":"1","article-title":"Recurrent models of visual attention","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mnih"},{"key":"ref14","article-title":"Multiple object recognition with visual attention","author":"Ba","year":"2015","journal-title":"arXiv:1412.7755"},{"key":"ref15","first-page":"595","article-title":"Multimodal neural language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kiros"},{"key":"ref16","article-title":"Deep captioning with multimodal recurrent neural networks (M-RNN)","author":"Mao","year":"2015","journal-title":"arXiv:1412.6632"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref19","article-title":"Attention is all you need","volume-title":"Advance Neural Information Processing System","volume":"30","author":"Vaswani","year":"2017"},{"key":"ref20","article-title":"Accelerating transformer decoding via a hybrid of self-attention and recurrent neural network","author":"Wang","year":"2019","journal-title":"arXiv:1909.02279"},{"key":"ref21","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref22","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019","journal-title":"arXiv:1810.04805"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3390\/sym12121939"},{"key":"ref24","article-title":"Hyperparameter analysis for image captioning","author":"Patel","year":"2020","journal-title":"arXiv:2006.10923"},{"key":"ref25","article-title":"An image is worth $16\\times16$\n words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"ref26","article-title":"CPTR: Full transformer network for image captioning","author":"Liu","year":"2021","journal-title":"arXiv:2101.10804"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3422668"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2020.2982887"},{"key":"ref34","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Represent.","author":"Kingma"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09739703.pdf?arnumber=9739703","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,18]],"date-time":"2024-01-18T00:48:17Z","timestamp":1705538897000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9739703\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3161428","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}