{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T17:07:26Z","timestamp":1778605646511,"version":"3.51.4"},"reference-count":55,"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\/501100003725","name":"National Research Foundation of Korea (NRF) Grant","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"Korea Government [Ministry of Science and ICT (MSIT)]","doi-asserted-by":"publisher","award":["NRF-2021R1A2C1014024"],"award-info":[{"award-number":["NRF-2021R1A2C1014024"]}],"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.2022.3169781","type":"journal-article","created":{"date-parts":[[2022,4,22]],"date-time":"2022-04-22T19:34:23Z","timestamp":1650656063000},"page":"45219-45229","source":"Crossref","is-referenced-by-count":15,"title":["Image Captioning Model Using Part-of-Speech Guidance Module for Description With Diverse Vocabulary"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9150-4850","authenticated-orcid":false,"given":"Ju-Won","family":"Bae","sequence":"first","affiliation":[{"name":"Department of Electronics & Electrical Engineering, Interdisciplinary Major of Maritime AI Convergence, Korea Maritime and Ocean University, Busan, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6199-6487","authenticated-orcid":false,"given":"Soo-Hwan","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Electronics & Electrical Engineering, Interdisciplinary Major of Maritime AI Convergence, Korea Maritime and Ocean University, Busan, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Won-Yeol","family":"Kim","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Convergence Research Center for Regional Innovation, Korea Maritime & Ocean University, Busan, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8198-0439","authenticated-orcid":false,"given":"Ju-Hyeon","family":"Seong","sequence":"additional","affiliation":[{"name":"Department of Liberal Education, Interdisciplinary Major of Maritime AI Convergence, Korea Maritime & Ocean University, Busan, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3610-0356","authenticated-orcid":false,"given":"Dong-Hoan","family":"Seo","sequence":"additional","affiliation":[{"name":"Division of Electronics and Electrical Information Engineering, Interdisciplinary Major of Maritime AI Convergence, Korea Maritime & Ocean University, Busan, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2587640"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2896516"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3131343"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_2"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3994"},{"key":"ref8","first-page":"1143","article-title":"Im2Text: Describing images using 1 million captioned photographs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"24","author":"Ordonez"},{"key":"ref9","first-page":"444","article-title":"Corpus-guided sentence generation of natural images","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Yang"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.162"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2976552"},{"issue":"11","key":"ref12","first-page":"1223","article-title":"Parallel injection method for improving descriptive performance of Bi-GRU image captions","volume":"22","author":"Lee","year":"2019","journal-title":"J. Korea Multimedia Soc."},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3295748"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.494"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018957"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2917979"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3067607"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2017.10.018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref24","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","author":"Banerjee"},{"key":"ref25","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summarization Branches Out","author":"Lin"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref27","first-page":"957","article-title":"From word embeddings to document distances","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kusner"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.5749\/j.ctttv2st"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref31","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Sutskever"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2010-343"},{"key":"ref33","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref34","first-page":"1","article-title":"Deep captioning with multimodal recurrent neural networks (M-RNN)","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Mao"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2018.02.005"},{"key":"ref38","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01034"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00184"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00898"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00435"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.93"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1017\/S1351324918000098"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21236\/ADA273556"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref49","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_31"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00856"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09762317.pdf?arnumber=9762317","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T21:16:31Z","timestamp":1705958191000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9762317\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3169781","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}