{"id":"https://openalex.org/W4401690668","doi":"https://doi.org/10.1016/j.heliyon.2024.e36272","title":"Enhancing image caption generation through context-aware attention mechanism","display_name":"Enhancing image caption generation through context-aware attention mechanism","publication_year":2024,"publication_date":"2024-08-19","ids":{"openalex":"https://openalex.org/W4401690668","doi":"https://doi.org/10.1016/j.heliyon.2024.e36272","pmid":"https://pubmed.ncbi.nlm.nih.gov/39281436","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/11399578"},"language":"en","primary_location":{"id":"doi:10.1016/j.heliyon.2024.e36272","doi":"https://doi.org/10.1016/j.heliyon.2024.e36272","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.heliyon.2024.e36272","pdf_url":null,"source":{"id":"https://openalex.org/S2898612692","display_name":"Heliyon","issn_l":"2405-8440","issn":["2405-8440"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","ki-jl-1","norway-1","poland-40","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Heliyon","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1016/j.heliyon.2024.e36272","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113340014","display_name":"Ahatesham Bhuiyan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I102782458","display_name":"Chittagong University of Engineering & Technology","ror":"https://ror.org/052qsay17","country_code":"BD","type":"education","lineage":["https://openalex.org/I102782458"]}],"countries":["BD"],"is_corresponding":true,"raw_author_name":"Ahatesham Bhuiyan","raw_affiliation_strings":["Department of Electronics and Telecommunication Engineering, Chittagong University of Engineering and Technology, Chittagong, 4349, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics and Telecommunication Engineering, Chittagong University of Engineering and Technology, Chittagong, 4349, Bangladesh","institution_ids":["https://openalex.org/I102782458"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027804851","display_name":"Eftekhar Hossain","orcid":"https://orcid.org/0000-0003-4575-0596","observed_orcids":["https://orcid.org/0000-0003-4575-0596"]},"institutions":[{"id":"https://openalex.org/I102782458","display_name":"Chittagong University of Engineering & Technology","ror":"https://ror.org/052qsay17","country_code":"BD","type":"education","lineage":["https://openalex.org/I102782458"]}],"countries":["BD"],"is_corresponding":true,"raw_author_name":"Eftekhar Hossain","raw_affiliation_strings":["Department of Electronics and Telecommunication Engineering, Chittagong University of Engineering and Technology, Chittagong, 4349, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics and Telecommunication Engineering, Chittagong University of Engineering and Technology, Chittagong, 4349, Bangladesh","institution_ids":["https://openalex.org/I102782458"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091780889","display_name":"Mohammed Moshiul Hoque","orcid":"https://orcid.org/0000-0001-8806-708X","observed_orcids":["https://orcid.org/0000-0001-8806-708X"]},"institutions":[{"id":"https://openalex.org/I102782458","display_name":"Chittagong University of Engineering & Technology","ror":"https://ror.org/052qsay17","country_code":"BD","type":"education","lineage":["https://openalex.org/I102782458"]}],"countries":["BD"],"is_corresponding":true,"raw_author_name":"Mohammed Moshiul Hoque","raw_affiliation_strings":["Department of Computer Science and Engineering, Chittagong University of Engineering and Technology, Chittagong, 4349, Bangladesh"],"raw_orcid":"https://orcid.org/0000-0001-8806-708X","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Chittagong University of Engineering and Technology, Chittagong, 4349, Bangladesh","institution_ids":["https://openalex.org/I102782458"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089476507","display_name":"M. Ali Akber Dewan","orcid":"https://orcid.org/0000-0001-6347-7509","observed_orcids":["https://orcid.org/0000-0001-6347-7509"]},"institutions":[{"id":"https://openalex.org/I86897205","display_name":"Athabasca University","ror":"https://ror.org/01y3xgc52","country_code":"CA","type":"education","lineage":["https://openalex.org/I86897205"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"M. Ali Akber Dewan","raw_affiliation_strings":["School of Computing and Information Systems, Faculty of Science and Technology, Athabasca University, Athabasca, AB T9S 3A3, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, Faculty of Science and Technology, Athabasca University, Athabasca, AB T9S 3A3, Canada","institution_ids":["https://openalex.org/I86897205"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5027804851","https://openalex.org/A5089476507","https://openalex.org/A5091780889","https://openalex.org/A5113340014"],"corresponding_institution_ids":["https://openalex.org/I102782458","https://openalex.org/I86897205"],"apc_list":{"value":2100,"currency":"USD","value_usd":2100},"apc_paid":{"value":2100,"currency":"USD","value_usd":2100},"fwci":1.4927,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.82048376,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":"10","issue":"17","first_page":"e36272","last_page":"e36272"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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":0.9994999766349792,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":9.999999747378752e-05,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/image-captioning","display_name":"image captioning","score":0.9739999771118164},{"id":"https://openalex.org/keywords/bengali-language","display_name":"Bengali language","score":0.8040000200271606},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.8379999995231628},{"id":"https://openalex.org/keywords/context-aware-attention","display_name":"context-aware attention","score":0.9539999961853027},{"id":"https://openalex.org/keywords/semantic-attention","display_name":"semantic attention","score":0.9660000205039978},{"id":"https://openalex.org/keywords/bidirectional-gru","display_name":"bidirectional GRU","score":0.8339999914169312},{"id":"https://openalex.org/keywords/cross-domain-knowledge-transfer","display_name":"cross-domain knowledge transfer","score":0.722000002861023}],"concepts":[{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6787298917770386},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.6642640829086304},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4194387197494507},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4041927754878998},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.35690227150917053},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.26987224817276},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.18047267198562622},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.14015448093414307},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.08439978957176208},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1016/j.heliyon.2024.e36272","doi":"https://doi.org/10.1016/j.heliyon.2024.e36272","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.heliyon.2024.e36272","pdf_url":null,"source":{"id":"https://openalex.org/S2898612692","display_name":"Heliyon","issn_l":"2405-8440","issn":["2405-8440"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","ki-jl-1","norway-1","poland-40","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Heliyon","raw_type":"journal-article"},{"id":"pmh:oai:pubmedcentral.nih.gov:11399578","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11399578","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11399578/pdf/main.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Heliyon","raw_type":"Text"},{"id":"pmid:39281436","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39281436","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Heliyon","raw_type":"Journal Article"},{"id":"pmh:oai:doaj.org/article:00396d46f6044518bb1b43e908280e93","doi":null,"is_oa":true,"landing_page_url":"https://doaj.org/article/00396d46f6044518bb1b43e908280e93","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,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Heliyon, Vol 10, Iss 17, Pp e36272- (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1016/j.heliyon.2024.e36272","doi":"https://doi.org/10.1016/j.heliyon.2024.e36272","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.heliyon.2024.e36272","pdf_url":null,"source":{"id":"https://openalex.org/S2898612692","display_name":"Heliyon","issn_l":"2405-8440","issn":["2405-8440"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","ki-jl-1","norway-1","poland-40","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Heliyon","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2271590008","display_name":null,"funder_award_id":"RGPIN 2020","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G8798599808","display_name":"Detecting student engagement and designing pedagogical intervention in online learning","funder_award_id":"rgpin-2020-06080","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401690668.pdf","grobid_xml":"https://content.openalex.org/works/W4401690668.grobid-xml"},"referenced_works_count":58,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W1514535095","https://openalex.org/W1593271688","https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W2027018831","https://openalex.org/W2069143585","https://openalex.org/W2090849497","https://openalex.org/W2097117768","https://openalex.org/W2103666701","https://openalex.org/W2123301721","https://openalex.org/W2149557440","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2302086703","https://openalex.org/W2343171314","https://openalex.org/W2481240925","https://openalex.org/W2508429489","https://openalex.org/W2600463316","https://openalex.org/W2885138528","https://openalex.org/W2886641317","https://openalex.org/W2891768291","https://openalex.org/W2899575547","https://openalex.org/W2904565150","https://openalex.org/W2950626540","https://openalex.org/W2963815651","https://openalex.org/W2965558087","https://openalex.org/W3046370984","https://openalex.org/W3091320486","https://openalex.org/W3093143956","https://openalex.org/W3097413439","https://openalex.org/W3132423244","https://openalex.org/W3134450428","https://openalex.org/W3155399358","https://openalex.org/W3196350734","https://openalex.org/W3209417397","https://openalex.org/W4235877265","https://openalex.org/W4236965008","https://openalex.org/W4245472345","https://openalex.org/W4245696960","https://openalex.org/W4282968790","https://openalex.org/W4283717754","https://openalex.org/W4301409532","https://openalex.org/W4312300614","https://openalex.org/W4312604481","https://openalex.org/W4312801478","https://openalex.org/W4313131769","https://openalex.org/W4313530366","https://openalex.org/W4319996369","https://openalex.org/W4365128502","https://openalex.org/W4380434588","https://openalex.org/W4386072307","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4407563560","https://openalex.org/W4411172119","https://openalex.org/W4405271501","https://openalex.org/W4321080401","https://openalex.org/W4411172439","https://openalex.org/W4406001730","https://openalex.org/W7125767149","https://openalex.org/W2965558087","https://openalex.org/W7164380454","https://openalex.org/W4213280450"],"abstract_inverted_index":{"Image":[0],"captioning,":[1],"the":[2,91,97,106,146],"process":[3],"of":[4,80,148,159],"generating":[5],"natural":[6],"language":[7],"descriptions":[8],"based":[9],"on":[10,34,210],"image":[11,72,98,193],"content,":[12],"has":[13,32],"garnered":[14],"attention":[15,62,66,129],"in":[16,22,47,74,134,138,176,201,207],"AI":[17],"research":[18,31],"for":[19,37,71,95],"its":[20,102],"implications":[21],"scene":[23],"understanding":[24],"and":[25,83,110,169,186],"human-computer":[26],"interaction.":[27],"While":[28],"much":[29],"prior":[30],"focused":[33],"caption":[35,203],"generation":[36,204],"English,":[38],"addressing":[39],"low-resource":[40],"languages":[41],"like":[42],"Bengali":[43,161,202],"presents":[44],"challenges,":[45],"particularly":[46],"producing":[48],"coherent":[49],"captions":[50,209],"linking":[51],"visual":[52],"objects":[53,70],"with":[54,127,154],"corresponding":[55],"words.":[56],"This":[57],"paper":[58,143],"proposes":[59],"a":[60,84,119],"context-aware":[61],"mechanism":[63,130],"over":[64,90,179],"semantic":[65],"to":[67,101,104],"accurately":[68],"diagnose":[69],"captioning":[73,194],"Bengali.":[75],"The":[76,142,189],"proposed":[77,190],"architecture":[78,125],"consists":[79],"an":[81,128],"encoder":[82],"decoder":[85],"block.":[86],"We":[87],"chose":[88],"ResNet-50":[89],"other":[92],"pre-trained":[93],"models":[94,200],"encoding":[96],"features":[99],"due":[100],"ability":[103],"solve":[105],"vanishing":[107],"gradient":[108],"problem":[109],"recognize":[111],"complex":[112],"object":[113],"features.":[114],"For":[115],"decoding":[116],"generated":[117],"captions,":[118],"bidirectional":[120],"Gated":[121],"Recurrent":[122],"Unit":[123],"(GRU)":[124],"combined":[126],"captures":[131],"contextual":[132],"dependencies":[133],"both":[135],"directions,":[136],"resulting":[137],"more":[139],"accurate":[140],"captions.":[141],"also":[144],"highlights":[145],"challenge":[147],"transferring":[149],"knowledge":[150],"between":[151],"domains,":[152],"especially":[153],"culturally":[155],"specific":[156],"images.":[157],"Evaluation":[158],"three":[160],"benchmark":[162],"datasets,":[163],"namely":[164],"BAN-Cap":[165],",":[166,168,171],"BanglaLekhaImageCaption":[167],"Bornon":[170],"demonstrates":[172],"significant":[173],"performance":[174],"improvement":[175],"METEOR":[177],"score":[178],"existing":[180],"methods":[181],"by":[182],"approximately":[183],"30%,":[184],"18%,":[185],"45%,":[187],"respectively.":[188],"context-aware,":[191],"attention-based":[192],"system":[195],"significantly":[196],"outperforms":[197],"current":[198],"state-of-the-art":[199],"despite":[205],"limitations":[206],"reference":[208],"certain":[211],"datasets.":[212]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2024-08-20T00:00:00"}