{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:49:45Z","timestamp":1777567785737,"version":"3.51.4"},"reference-count":47,"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"}],"funder":[{"DOI":"10.13039\/100006112","name":"Microsoft Research","doi-asserted-by":"publisher","award":["CORE-16"],"award-info":[{"award-number":["CORE-16"]}],"id":[{"id":"10.13039\/100006112","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["16H02846"],"award-info":[{"award-number":["16H02846"]}],"id":[{"id":"10.13039\/501100001691","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.2021.3131393","type":"journal-article","created":{"date-parts":[[2021,11,30]],"date-time":"2021-11-30T23:36:50Z","timestamp":1638315410000},"page":"162951-162961","source":"Crossref","is-referenced-by-count":16,"title":["Imageability- and Length-Controllable Image Captioning"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9193-5973","authenticated-orcid":false,"given":"Marc A.","family":"Kastner","sequence":"first","affiliation":[{"name":"Digital Content and Media Sciences Research Division, National Institute of Informatics, Chiyoda-ku, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kazuki","family":"Umemura","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Nagoya University, Chikusa-ku, Nagoya, Aichi, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3942-9296","authenticated-orcid":false,"given":"Ichiro","family":"Ide","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Nagoya University, Chikusa-ku, Nagoya, Aichi, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3799-4550","authenticated-orcid":false,"given":"Yasutomo","family":"Kawanishi","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Nagoya University, Chikusa-ku, Nagoya, Aichi, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takatsugu","family":"Hirayama","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Nagoya University, Chikusa-ku, Nagoya, Aichi, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keisuke","family":"Doman","sequence":"additional","affiliation":[{"name":"School of Engineering, Chukyo University, Toyota, Aichi, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daisuke","family":"Deguchi","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Nagoya University, Chikusa-ku, Nagoya, Aichi, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8103-9294","authenticated-orcid":false,"given":"Hiroshi","family":"Murase","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Nagoya University, Chikusa-ku, Nagoya, Aichi, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6995-6447","authenticated-orcid":false,"given":"Shin'Ichi","family":"Satoh","sequence":"additional","affiliation":[{"name":"Digital Content and Media Sciences Research Division, National Institute of Informatics, Chiyoda-ku, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"7371","article-title":"Diverse beam search for improved description of complex scenes","volume":"32","author":"vijayakumar","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3758\/s13428-018-1099-3"},{"key":"ref32","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume":"28","author":"ren","year":"2015","journal-title":"Neural Information Processing Systems"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1080\/03640210709336988"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref37","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-67835-7_6"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1037\/h0065439"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01280"},{"key":"ref10","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume":"1","author":"devlin","year":"2019","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.108"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1633"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00433"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.494"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00902"},{"key":"ref19","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Proc Workshop ACL Text Summarization Branches Out"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00850"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1037\/h0025327"},{"key":"ref3","first-page":"527","article-title":"‘Factual’ or ‘emotional’: Stylized image captioning with adaptive learning and attention","volume":"11214","author":"chen","year":"2018","journal-title":"Computer Vision"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3758\/BF03195585"},{"key":"ref29","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref7","first-page":"712","article-title":"Length-controllable image captioning","volume":"12358","author":"deng","year":"2020","journal-title":"Computer Vision"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00998"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01095"},{"key":"ref1","first-page":"382","article-title":"SPICE: Semantic propositional image caption evaluation","volume":"9909","author":"anderson","year":"2016","journal-title":"Computer Vision"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6998"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00754"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3390\/app8050739"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"217","DOI":"10.18653\/v1\/W18-3028","article-title":"Predicting concreteness and imageability of words within and across languages via word embeddings","author":"ljube\u0161i?","year":"2018","journal-title":"Proc 3rd Workshop Represent Learn"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3758\/BF03202594"},{"key":"ref24","first-page":"3574","article-title":"SentiCap: Generating image descriptions with sentiments","volume":"30","author":"mathews","year":"2016","journal-title":"Proc 30th AAAI Conf Artif Intell"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00432"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-5010"},{"key":"ref44","first-page":"1","article-title":"Equal but not the same: Understanding the implicit relationship between persuasive images and text","author":"zhang","year":"2018","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref43","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","volume":"37","author":"xu","year":"2015","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3372278.3390731"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09628002.pdf?arnumber=9628002","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,8]],"date-time":"2022-09-08T20:50:56Z","timestamp":1662670256000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9628002\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3131393","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}