{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T20:17:55Z","timestamp":1760473075768,"version":"3.37.3"},"reference-count":24,"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-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003725","name":"Basic Science Research Program through the National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100009950","name":"Ministry of Education","doi-asserted-by":"publisher","award":["(2020R1A6A1A03038540)"],"award-info":[{"award-number":["(2020R1A6A1A03038540)"]}],"id":[{"id":"10.13039\/100009950","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014188","name":"Korea government, Ministry of Science and ICT","doi-asserted-by":"publisher","award":["(2021R1F1A1046339)"],"award-info":[{"award-number":["(2021R1F1A1046339)"]}],"id":[{"id":"10.13039\/501100014188","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.2021.3104276","type":"journal-article","created":{"date-parts":[[2021,8,12]],"date-time":"2021-08-12T20:03:59Z","timestamp":1628798639000},"page":"113550-113557","source":"Crossref","is-referenced-by-count":23,"title":["Deep Learning-Based Short Story Generation for an Image Using the Encoder-Decoder Structure"],"prefix":"10.1109","volume":"9","author":[{"given":"Kyungbok","family":"Min","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minh","family":"Dang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7668-3838","authenticated-orcid":false,"given":"Hyeonjoon","family":"Moon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1613\/jair.4900"},{"key":"ref11","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"chen","year":"2015","journal-title":"arXiv 1504 00325"},{"key":"ref12","first-page":"1143","article-title":"Im2text: Describing images using 1 million captioned photographs","author":"ordonez","year":"2011","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref13","first-page":"504","article-title":"Déja image-captions: A corpus of expressive descriptions in repetition","author":"chen","year":"2015","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref14","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref15","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref16","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":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-014-0065-9"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1091"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICDEW.2019.00060"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2018.2794541"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-1505"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3115432"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref8","first-page":"2422","article-title":"Mind’s eye: A recurrent visual representation for image caption generation","author":"chen","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2019.04.005"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/app8122610"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00896"},{"key":"ref22","first-page":"2121","article-title":"Devise: A deep visual-semantic embedding model","author":"frome","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09512087.pdf?arnumber=9512087","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:57:51Z","timestamp":1639771071000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9512087\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3104276","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2021]]}}}