{"id":"https://openalex.org/W4226156236","doi":"https://doi.org/10.1109/access.2022.3169781","title":"Image Captioning Model Using Part-of-Speech Guidance Module for Description With Diverse Vocabulary","display_name":"Image Captioning Model Using Part-of-Speech Guidance Module for Description With Diverse Vocabulary","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4226156236","doi":"https://doi.org/10.1109/access.2022.3169781"},"language":"en","primary_location":{"id":"doi:10.1109/access.2022.3169781","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3169781","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9668973/09762317.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/9668973/09762317.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058012424","display_name":"Ju-Won Bae","orcid":"https://orcid.org/0000-0001-9150-4850"},"institutions":[{"id":"https://openalex.org/I197867492","display_name":"Korea Maritime and Ocean University","ror":"https://ror.org/01v7y5b55","country_code":"KR","type":"education","lineage":["https://openalex.org/I197867492"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ju-Won Bae","raw_affiliation_strings":["Department of Electronics & Electrical Engineering, Interdisciplinary Major of Maritime AI Convergence, Korea Maritime and Ocean University, Busan, South Korea"],"raw_orcid":"https://orcid.org/0000-0001-9150-4850","affiliations":[{"raw_affiliation_string":"Department of Electronics & Electrical Engineering, Interdisciplinary Major of Maritime AI Convergence, Korea Maritime and Ocean University, Busan, South Korea","institution_ids":["https://openalex.org/I197867492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058266666","display_name":"Soo-Hwan Lee","orcid":"https://orcid.org/0000-0001-6199-6487"},"institutions":[{"id":"https://openalex.org/I197867492","display_name":"Korea Maritime and Ocean University","ror":"https://ror.org/01v7y5b55","country_code":"KR","type":"education","lineage":["https://openalex.org/I197867492"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Soo-Hwan Lee","raw_affiliation_strings":["Department of Electronics & Electrical Engineering, Interdisciplinary Major of Maritime AI Convergence, Korea Maritime and Ocean University, Busan, South Korea"],"raw_orcid":"https://orcid.org/0000-0001-6199-6487","affiliations":[{"raw_affiliation_string":"Department of Electronics & Electrical Engineering, Interdisciplinary Major of Maritime AI Convergence, Korea Maritime and Ocean University, Busan, South Korea","institution_ids":["https://openalex.org/I197867492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084043021","display_name":"Won-Yeol Kim","orcid":"https://orcid.org/0000-0002-3492-6413"},"institutions":[{"id":"https://openalex.org/I197867492","display_name":"Korea Maritime and Ocean University","ror":"https://ror.org/01v7y5b55","country_code":"KR","type":"education","lineage":["https://openalex.org/I197867492"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Won-Yeol Kim","raw_affiliation_strings":["Artificial Intelligence Convergence Research Center for Regional Innovation, Korea Maritime & Ocean University, Busan, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Convergence Research Center for Regional Innovation, Korea Maritime & Ocean University, Busan, South Korea","institution_ids":["https://openalex.org/I197867492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091611912","display_name":"Ju-Hyeon Seong","orcid":"https://orcid.org/0000-0002-8198-0439"},"institutions":[{"id":"https://openalex.org/I197867492","display_name":"Korea Maritime and Ocean University","ror":"https://ror.org/01v7y5b55","country_code":"KR","type":"education","lineage":["https://openalex.org/I197867492"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ju-Hyeon Seong","raw_affiliation_strings":["Department of Liberal Education, Interdisciplinary Major of Maritime AI Convergence, Korea Maritime & Ocean University, Busan, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-8198-0439","affiliations":[{"raw_affiliation_string":"Department of Liberal Education, Interdisciplinary Major of Maritime AI Convergence, Korea Maritime & Ocean University, Busan, South Korea","institution_ids":["https://openalex.org/I197867492"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042128313","display_name":"Dong-Hoan Seo","orcid":"https://orcid.org/0000-0003-3610-0356"},"institutions":[{"id":"https://openalex.org/I197867492","display_name":"Korea Maritime and Ocean University","ror":"https://ror.org/01v7y5b55","country_code":"KR","type":"education","lineage":["https://openalex.org/I197867492"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dong-Hoan Seo","raw_affiliation_strings":["Division of Electronics and Electrical Information Engineering, Interdisciplinary Major of Maritime AI Convergence, Korea Maritime & Ocean University, Busan, South Korea"],"raw_orcid":"https://orcid.org/0000-0003-3610-0356","affiliations":[{"raw_affiliation_string":"Division of Electronics and Electrical Information Engineering, Interdisciplinary Major of Maritime AI Convergence, Korea Maritime & Ocean University, Busan, South Korea","institution_ids":["https://openalex.org/I197867492"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.7261,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.85470319,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"10","issue":null,"first_page":"45219","last_page":"45229"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9889000058174133,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9883999824523926,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8618030548095703},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8574298024177551},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6426270008087158},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6236773133277893},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5890294909477234},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5784654021263123},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.558506190776825},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.506304144859314},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4328203797340393},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1126861572265625}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8618030548095703},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8574298024177551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6426270008087158},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6236773133277893},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5890294909477234},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5784654021263123},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.558506190776825},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.506304144859314},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4328203797340393},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1126861572265625},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2022.3169781","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3169781","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9668973/09762317.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:2ee00626c77b486aa0830d8d206a9f6a","is_oa":false,"landing_page_url":"https://doaj.org/article/2ee00626c77b486aa0830d8d206a9f6a","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 10, Pp 45219-45229 (2022)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2022.3169781","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3169781","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9668973/09762317.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8199999928474426}],"awards":[{"id":"https://openalex.org/G2192947683","display_name":null,"funder_award_id":"NRF-2021R1A2C1014024","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320321325","display_name":"Korea Maritime and Ocean University","ror":"https://ror.org/01v7y5b55"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4226156236.pdf","grobid_xml":"https://content.openalex.org/works/W4226156236.grobid-xml"},"referenced_works_count":56,"referenced_works":["https://openalex.org/W52410547","https://openalex.org/W68733909","https://openalex.org/W179875071","https://openalex.org/W1522301498","https://openalex.org/W1632114991","https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1897761818","https://openalex.org/W1905882502","https://openalex.org/W1969616664","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2131774270","https://openalex.org/W2302086703","https://openalex.org/W2463955103","https://openalex.org/W2506483933","https://openalex.org/W2552161745","https://openalex.org/W2745461083","https://openalex.org/W2766261529","https://openalex.org/W2789930422","https://openalex.org/W2885013662","https://openalex.org/W2890531016","https://openalex.org/W2896348597","https://openalex.org/W2896457183","https://openalex.org/W2904551248","https://openalex.org/W2913618459","https://openalex.org/W2946450307","https://openalex.org/W2953322005","https://openalex.org/W2963037989","https://openalex.org/W2963101956","https://openalex.org/W2963150697","https://openalex.org/W2963758027","https://openalex.org/W2964350391","https://openalex.org/W2965697393","https://openalex.org/W2982151481","https://openalex.org/W2984138079","https://openalex.org/W2986670728","https://openalex.org/W2990069284","https://openalex.org/W3009270862","https://openalex.org/W3034417909","https://openalex.org/W3034655362","https://openalex.org/W3035160838","https://openalex.org/W3035284526","https://openalex.org/W3105531629","https://openalex.org/W3137069976","https://openalex.org/W3217070527","https://openalex.org/W6621906925","https://openalex.org/W6631190155","https://openalex.org/W6638742206","https://openalex.org/W6639118148","https://openalex.org/W6676497082","https://openalex.org/W6678262379","https://openalex.org/W6679436768","https://openalex.org/W6682631176","https://openalex.org/W6739901393","https://openalex.org/W6755207826"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W2963177403","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2330246314","https://openalex.org/W3217195652","https://openalex.org/W1997182898"],"abstract_inverted_index":{"Image":[0],"captions":[1],"aim":[2],"to":[3,22,67,101,130,149],"generate":[4],"human-like":[5],"sentences":[6,43,55,98,202],"that":[7,87,197],"describe":[8],"the":[9,35,50,89,103,118,126,134,146,151,155,162,166,183,187,191,198],"image\u2019s":[10],"content.":[11],"Recent":[12],"developments":[13],"in":[14,49,71],"deep":[15],"learning":[16],"(DL)":[17],"have":[18,60],"made":[19],"it":[20,41],"possible":[21],"caption":[23,188],"images":[24,38,92,121],"for":[25],"accurate":[26],"descriptions":[27],"and":[28,39,81,93,96,122,140,160,169,173,195],"detailed":[29],"expressions.":[30],"However,":[31],"since":[32],"DL":[33],"learns":[34],"relationship":[36],"between":[37],"captions,":[40],"constructs":[42],"based":[44,124],"on":[45,125,165],"commonly":[46],"frequented":[47],"words":[48],"dataset.":[51],"Although":[52],"these":[53],"generated":[54],"are":[56],"highly":[57],"accurate,":[58],"they":[59],"low":[61],"lexical":[62,104,184],"diversity,":[63],"unlike":[64],"humans":[65],"due":[66],"limited":[68],"vocabulary.":[69],"Therefore,":[70],"this":[72],"paper,":[73],"we":[74,181],"propose":[75],"a":[76,82],"Part-Of-Speech":[77],"(POS)":[78],"guidance":[79,111,129],"module":[80,112],"multimodal-based":[83],"image":[84],"captioning":[85],"model":[86,164,189,200],"determines":[88],"intensity":[90],"of":[91,106,120,143,186],"word":[94],"sequences":[95,123],"generates":[97,201],"through":[99,190],"POS":[100,110,128,135,139],"enhance":[102],"diversity":[105,185],"DL.":[107],"The":[108],"proposed":[109,163,199],"enables":[113],"rich":[114],"expression":[115],"by":[116],"controlling":[117],"information":[119],"predicted":[127],"predict":[131,150],"words.":[132,205],"Then,":[133],"multimodal":[136,147],"layer":[137,148],"adds":[138],"output":[141],"vector":[142],"Bi-LSTM":[144],"using":[145,203],"next":[152],"caption,":[153],"considering":[154],"grammatical":[156],"structure.":[157],"We":[158],"trained":[159],"tested":[161],"Flicker":[167],"30K":[168],"MS":[170],"COCO":[171],"datasets":[172],"compared":[174],"them":[175],"with":[176],"current":[177],"state-of-the-art":[178],"studies.":[179],"Also,":[180],"analyzed":[182],"Type-Token":[192],"Ratio":[193],"(TTR)":[194],"confirmed":[196],"several":[204]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}