{"id":"https://openalex.org/W4391128839","doi":"https://doi.org/10.1109/ictc58733.2023.10392496","title":"RBBA: ResNet - BERT - Bahdanau Attention for Image Caption Generator","display_name":"RBBA: ResNet - BERT - Bahdanau Attention for Image Caption Generator","publication_year":2023,"publication_date":"2023-10-11","ids":{"openalex":"https://openalex.org/W4391128839","doi":"https://doi.org/10.1109/ictc58733.2023.10392496"},"language":"en","primary_location":{"id":"doi:10.1109/ictc58733.2023.10392496","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ictc58733.2023.10392496","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 14th International Conference on Information and Communication Technology Convergence (ICTC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023817822","display_name":"Duc-Hieu Hoang","orcid":null},"institutions":[{"id":"https://openalex.org/I141445968","display_name":"Ton Duc Thang University","ror":"https://ror.org/01drq0835","country_code":"VN","type":"education","lineage":["https://openalex.org/I141445968"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Duc-Hieu Hoang","raw_affiliation_strings":["Ton Duc Thang University,Faculty of Electrical &amp; Electronics Eng.,Ho Chi Minh City,Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ton Duc Thang University,Faculty of Electrical &amp; Electronics Eng.,Ho Chi Minh City,Vietnam","institution_ids":["https://openalex.org/I141445968"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Anh-Khoa Tran","orcid":null},"institutions":[{"id":"https://openalex.org/I141445968","display_name":"Ton Duc Thang University","ror":"https://ror.org/01drq0835","country_code":"VN","type":"education","lineage":["https://openalex.org/I141445968"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Anh-Khoa Tran","raw_affiliation_strings":["Ton Duc Thang University,Faculty of Electrical and Electronics,Ho Chi Minh City,Vietnam","Faculty of Electrical and Electronics, Ton Duc Thang University, Ho Chi Minh City, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ton Duc Thang University,Faculty of Electrical and Electronics,Ho Chi Minh City,Vietnam","institution_ids":["https://openalex.org/I141445968"]},{"raw_affiliation_string":"Faculty of Electrical and Electronics, Ton Duc Thang University, Ho Chi Minh City, Vietnam","institution_ids":["https://openalex.org/I141445968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034169259","display_name":"Duc Ngoc Minh Dang","orcid":"https://orcid.org/0000-0001-9302-3129"},"institutions":[{"id":"https://openalex.org/I109689652","display_name":"FPT University","ror":"https://ror.org/03esj4g97","country_code":"VN","type":"education","lineage":["https://openalex.org/I109689652"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Duc Ngoc Minh Dang","raw_affiliation_strings":["FPT University,Dept. of Computing Fundamental,Ho Chi Minh City,Vietnam","Dept. of Computing Fundamental, FPT University, Ho Chi Minh City, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FPT University,Dept. of Computing Fundamental,Ho Chi Minh City,Vietnam","institution_ids":["https://openalex.org/I109689652"]},{"raw_affiliation_string":"Dept. of Computing Fundamental, FPT University, Ho Chi Minh City, Vietnam","institution_ids":["https://openalex.org/I109689652"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045633892","display_name":"Phuong-Nam Tran","orcid":"https://orcid.org/0009-0009-6551-9106"},"institutions":[{"id":"https://openalex.org/I109689652","display_name":"FPT University","ror":"https://ror.org/03esj4g97","country_code":"VN","type":"education","lineage":["https://openalex.org/I109689652"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Phuong-Nam Tran","raw_affiliation_strings":["FPT University,Dept. of Computing Fundamental,Ho Chi Minh City,Vietnam","Dept. of Computing Fundamental, FPT University, Ho Chi Minh City, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FPT University,Dept. of Computing Fundamental,Ho Chi Minh City,Vietnam","institution_ids":["https://openalex.org/I109689652"]},{"raw_affiliation_string":"Dept. of Computing Fundamental, FPT University, Ho Chi Minh City, Vietnam","institution_ids":["https://openalex.org/I109689652"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036183089","display_name":"Hanh Dang-Ngoc","orcid":"https://orcid.org/0000-0002-5155-5730"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hanh Dang-Ngoc","raw_affiliation_strings":["University of Technology Sydney,School of Electrical and Data Engineering,Sydney,NSW,Australia","School of Electrical and Data Engineering, University of Technology Sydney, Sydney, NSW, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Technology Sydney,School of Electrical and Data Engineering,Sydney,NSW,Australia","institution_ids":["https://openalex.org/I114017466"]},{"raw_affiliation_string":"School of Electrical and Data Engineering, University of Technology Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051858279","display_name":"Cuong Tuan Nguyen","orcid":"https://orcid.org/0000-0003-2556-9191"},"institutions":[{"id":"https://openalex.org/I109689652","display_name":"FPT University","ror":"https://ror.org/03esj4g97","country_code":"VN","type":"education","lineage":["https://openalex.org/I109689652"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Cuong Tuan Nguyen","raw_affiliation_strings":["FPT University,Dept. of Information Technology Specialization,Ho Chi Minh City,Vietnam","Dept. of Information Technology Specialization, FPT University, Ho Chi Minh City, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FPT University,Dept. of Information Technology Specialization,Ho Chi Minh City,Vietnam","institution_ids":["https://openalex.org/I109689652"]},{"raw_affiliation_string":"Dept. of Information Technology Specialization, FPT University, Ho Chi Minh City, Vietnam","institution_ids":["https://openalex.org/I109689652"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"430","last_page":"435"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9955000281333923,"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/T10028","display_name":"Topic Modeling","score":0.9894999861717224,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.863677978515625},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.7063581943511963},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6863934397697449},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5919851660728455},{"id":"https://openalex.org/keywords/bleu","display_name":"BLEU","score":0.5491358637809753},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4992811679840088},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4880589246749878},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.48726120591163635},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48366817831993103},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4539600908756256},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33392179012298584},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3307734429836273},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.3281105160713196},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.09379804134368896},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.05676907300949097}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.863677978515625},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.7063581943511963},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6863934397697449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5919851660728455},{"id":"https://openalex.org/C622187","wikidata":"https://www.wikidata.org/wiki/Q3500773","display_name":"BLEU","level":3,"score":0.5491358637809753},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4992811679840088},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4880589246749878},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.48726120591163635},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48366817831993103},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4539600908756256},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33392179012298584},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3307734429836273},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.3281105160713196},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.09379804134368896},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.05676907300949097},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ictc58733.2023.10392496","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ictc58733.2023.10392496","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 14th International Conference on Information and Communication Technology Convergence (ICTC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1614298861","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2152311353","https://openalex.org/W2157331557","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2531409750","https://openalex.org/W2896457183","https://openalex.org/W2953322005","https://openalex.org/W2962835968","https://openalex.org/W2964350391","https://openalex.org/W3105531629","https://openalex.org/W3175225143","https://openalex.org/W4297734170","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W1925994383","https://openalex.org/W2099607809","https://openalex.org/W2395641992","https://openalex.org/W2807475932","https://openalex.org/W3021126373","https://openalex.org/W4280571180","https://openalex.org/W2903057408","https://openalex.org/W92588874","https://openalex.org/W2426188458","https://openalex.org/W2963991316"],"abstract_inverted_index":{"In":[0,53,92],"recent":[1],"years,":[2],"the":[3,34,46,89,95,105,111],"topic":[4],"of":[5,63,110,114,119],"image":[6],"caption":[7,25],"generators":[8,26],"has":[9],"gained":[10],"significant":[11],"attention.":[12],"Several":[13],"successful":[14],"projects":[15],"have":[16],"emerged":[17],"in":[18,108],"this":[19,54],"field,":[20],"showcasing":[21],"notable":[22],"advancements.":[23],"Image":[24],"automatically":[27],"generate":[28],"descriptive":[29],"captions":[30],"for":[31],"images":[32],"through":[33],"encoder":[35,40],"and":[36,74,82,116],"decoder":[37,47],"mechanisms.":[38],"The":[39],"leverages":[41],"computer":[42],"vision":[43],"models,":[44],"while":[45],"utilizes":[48],"natural":[49],"language":[50],"processing":[51],"models.":[52],"study,":[55],"we":[56],"aim":[57],"to":[58],"assess":[59],"a":[60],"comprehensive":[61],"set":[62],"seven":[64],"distinct":[65],"methodologies,":[66],"including":[67],"six":[68],"existing":[69],"methods":[70,79],"from":[71],"prior":[72],"research":[73],"one":[75],"newly":[76],"proposed.":[77],"These":[78],"are":[80],"trained":[81],"evaluated":[83],"with":[84],"bilingual":[85],"evaluation":[86],"(BLEU)":[87],"on":[88],"Flickr8K":[90],"dataset.":[91],"our":[93],"experiments,":[94],"proposed":[96],"ResNet50":[97],"\u2013":[98,100],"BERT":[99],"Bahdanau":[101],"Attention":[102],"model":[103],"outperforms":[104],"other":[106],"models":[107],"terms":[109],"BLEU-1":[112],"score":[113,118],"0.532143":[115],"BLEU-4":[117],"0.126316.":[120]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
