{"id":"https://openalex.org/W4407304464","doi":"https://doi.org/10.1109/access.2025.3540388","title":"BVQA: Connecting Language and Vision Through Multimodal Attention for Open-Ended Question Answering","display_name":"BVQA: Connecting Language and Vision Through Multimodal Attention for Open-Ended Question Answering","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4407304464","doi":"https://doi.org/10.1109/access.2025.3540388"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3540388","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3540388","pdf_url":null,"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://doi.org/10.1109/access.2025.3540388","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Md. Shalha Mucha Bhuyan","orcid":"https://orcid.org/0009-0002-3875-2526"},"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":false,"raw_author_name":"Md. Shalha Mucha Bhuyan","raw_affiliation_strings":["Department of Electronics and Telecommunication Engineering, Chittagong University of Engineering and Technology, Chattogram, Bangladesh"],"raw_orcid":"https://orcid.org/0009-0002-3875-2526","affiliations":[{"raw_affiliation_string":"Department of Electronics and Telecommunication Engineering, Chittagong University of Engineering and Technology, Chattogram, 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"},"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":false,"raw_author_name":"Eftekhar Hossain","raw_affiliation_strings":["Department of Electronics and Telecommunication Engineering, Chittagong University of Engineering and Technology, Chattogram, Bangladesh"],"raw_orcid":"https://orcid.org/0000-0003-4575-0596","affiliations":[{"raw_affiliation_string":"Department of Electronics and Telecommunication Engineering, Chittagong University of Engineering and Technology, Chattogram, Bangladesh","institution_ids":["https://openalex.org/I102782458"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079313734","display_name":"Khaleda Akhter Sathi","orcid":"https://orcid.org/0000-0003-0031-9284"},"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":false,"raw_author_name":"Khaleda Akhter Sathi","raw_affiliation_strings":["Department of Electronics and Telecommunication Engineering, Chittagong University of Engineering and Technology, Chattogram, Bangladesh"],"raw_orcid":"https://orcid.org/0000-0003-0031-9284","affiliations":[{"raw_affiliation_string":"Department of Electronics and Telecommunication Engineering, Chittagong University of Engineering and Technology, Chattogram, Bangladesh","institution_ids":["https://openalex.org/I102782458"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020909684","display_name":"Md. Azad Hossain","orcid":"https://orcid.org/0000-0002-8251-5168"},"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":false,"raw_author_name":"Md. Azad Hossain","raw_affiliation_strings":["Department of Electronics and Telecommunication Engineering, Chittagong University of Engineering and Technology, Chattogram, Bangladesh"],"raw_orcid":"https://orcid.org/0000-0002-8251-5168","affiliations":[{"raw_affiliation_string":"Department of Electronics and Telecommunication Engineering, Chittagong University of Engineering and Technology, Chattogram, 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"},"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":false,"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, Canada","Faculty of Science and Technology, School of Computing and Information Systems, Athabasca University, Athabasca, AB, Canada"],"raw_orcid":"https://orcid.org/0000-0001-6347-7509","affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, Faculty of Science and Technology, Athabasca University, Athabasca, AB, Canada","institution_ids":["https://openalex.org/I86897205"]},{"raw_affiliation_string":"Faculty of Science and Technology, School of Computing and Information Systems, Athabasca University, Athabasca, AB, Canada","institution_ids":["https://openalex.org/I86897205"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2075,"currency":"USD","value_usd":2075},"apc_paid":{"value":2075,"currency":"USD","value_usd":2075},"fwci":10.1781,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.97721495,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"13","issue":null,"first_page":"27570","last_page":"27586"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9909999966621399,"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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9909999966621399,"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/T10028","display_name":"Topic Modeling","score":0.9851999878883362,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9749000072479248,"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/computer-science","display_name":"Computer science","score":0.6985869407653809},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6505798101425171},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4676249623298645},{"id":"https://openalex.org/keywords/closed-ended-question","display_name":"Closed-ended question","score":0.4432781934738159},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4377218782901764},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3369220495223999},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.30917829275131226},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.07779252529144287}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6985869407653809},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6505798101425171},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4676249623298645},{"id":"https://openalex.org/C193035329","wikidata":"https://www.wikidata.org/wiki/Q17007046","display_name":"Closed-ended question","level":2,"score":0.4432781934738159},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4377218782901764},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3369220495223999},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.30917829275131226},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.07779252529144287}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3540388","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3540388","pdf_url":null,"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:36a75d04fc6f4edbae3b790979c3a34c","is_oa":true,"landing_page_url":"https://doaj.org/article/36a75d04fc6f4edbae3b790979c3a34c","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 27570-27586 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3540388","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3540388","pdf_url":null,"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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":75,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1933349210","https://openalex.org/W2165698076","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2529436507","https://openalex.org/W2561715562","https://openalex.org/W2563399268","https://openalex.org/W2745461083","https://openalex.org/W2747623286","https://openalex.org/W2896348597","https://openalex.org/W2901466771","https://openalex.org/W2947312908","https://openalex.org/W2962884579","https://openalex.org/W2963115613","https://openalex.org/W2963150162","https://openalex.org/W2963191264","https://openalex.org/W2963224792","https://openalex.org/W2963364170","https://openalex.org/W2963383024","https://openalex.org/W2963644680","https://openalex.org/W2963954913","https://openalex.org/W2963991868","https://openalex.org/W2964137095","https://openalex.org/W2964138343","https://openalex.org/W2966005000","https://openalex.org/W3012111773","https://openalex.org/W3114239154","https://openalex.org/W3174148569","https://openalex.org/W3208624098","https://openalex.org/W4281641249","https://openalex.org/W4283370663","https://openalex.org/W4285237775","https://openalex.org/W4292828962","https://openalex.org/W4312443924","https://openalex.org/W4323060138","https://openalex.org/W4379879090","https://openalex.org/W4384662964","https://openalex.org/W4385245566","https://openalex.org/W4385571943","https://openalex.org/W4386014382","https://openalex.org/W4386798384","https://openalex.org/W4387498531","https://openalex.org/W4396808612","https://openalex.org/W4403707714","https://openalex.org/W4404782964","https://openalex.org/W6633724138","https://openalex.org/W6634232107","https://openalex.org/W6636510571","https://openalex.org/W6637373629","https://openalex.org/W6679434410","https://openalex.org/W6682086655","https://openalex.org/W6685520387","https://openalex.org/W6686883664","https://openalex.org/W6703809471","https://openalex.org/W6711963698","https://openalex.org/W6719057275","https://openalex.org/W6721087566","https://openalex.org/W6743842864","https://openalex.org/W6753290298","https://openalex.org/W6755207826","https://openalex.org/W6762718338","https://openalex.org/W6766819354","https://openalex.org/W6768851824","https://openalex.org/W6784353115","https://openalex.org/W6791353385","https://openalex.org/W6797704076","https://openalex.org/W6811013733","https://openalex.org/W6849177959","https://openalex.org/W6851592950","https://openalex.org/W6852667213","https://openalex.org/W6855128148","https://openalex.org/W6856037140","https://openalex.org/W6858288548"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W3107555006","https://openalex.org/W4300925379","https://openalex.org/W2391533720","https://openalex.org/W4386858563","https://openalex.org/W4392188973","https://openalex.org/W4402670313","https://openalex.org/W3140009346","https://openalex.org/W3216306357"],"abstract_inverted_index":{"Visual":[0,98],"Question":[1,99],"Answering":[2,100],"(VQA)":[3],"is":[4,234],"a":[5,94,138,167,186,200],"challenging":[6],"problem":[7],"of":[8,16,44,109,130,149],"Artificial":[9],"Intelligence":[10],"(AI)":[11],"that":[12,170,217],"requires":[13],"an":[14,209],"understanding":[15],"natural":[17],"language":[18,140],"and":[19,152,179,196,231],"computer":[20],"vision":[21],"to":[22,24,40,145,175,190,204],"respond":[23],"inquiries":[25],"based":[26],"on":[27,33,66,72,213],"visual":[28,178],"content":[29],"within":[30],"images.":[31,132],"Research":[32],"VQA":[34,135],"has":[35,62],"gained":[36],"immense":[37],"traction":[38],"due":[39,144],"its":[41],"wide":[42],"range":[43],"applications":[45],"in":[46,83,88],"aiding":[47],"visually":[48],"impaired":[49],"individuals,":[50],"enhancing":[51],"human-computer":[52],"interaction,":[53],"facilitating":[54],"content-based":[55],"image":[56],"retrieval":[57],"systems,":[58],"etc.":[59],"While":[60],"there":[61],"been":[63],"extensive":[64],"research":[65,87],"VQA,":[67],"most":[68],"were":[69],"predominantly":[70],"focused":[71],"English,":[73],"often":[74],"overlooking":[75],"the":[76,105,110,127,146,177,206,218,222],"complexity":[77],"associated":[78],"with":[79],"low-resource":[80,139],"languages,":[81],"especially":[82],"Bengali.":[84],"To":[85,157],"facilitate":[86],"this":[89,159],"arena,":[90],"we":[91,161],"have":[92],"developed":[93],"large":[95],"scale":[96],"Bengali":[97],"(BVQA)":[101],"dataset":[102,117,215],"by":[103],"harnessing":[104],"in-context":[106],"learning":[107],"abilities":[108],"Large":[111],"Language":[112],"Model":[113],"(LLM).":[114],"Our":[115],"BVQA":[116,214],"encompasses":[118],"around":[119],"17,800":[120],"diverse":[121],"open-ended":[122],"QA":[123],"Pairs":[124],"generated":[125],"from":[126],"human-annotated":[128],"captions":[129],"\u22483,500":[131],"Replicating":[133],"existing":[134,223],"systems":[136],"for":[137,154],"poses":[141],"significant":[142],"challenges":[143],"complex":[147],"nature":[148],"their":[150],"architectures":[151,174],"adaptations":[153],"particular":[155],"languages.":[156],"overcome":[158],"challenge,":[160],"proposed":[162,219],"Multimodal":[163],"CRoss-Attention":[164],"Network":[165],"(MCRAN),":[166],"novel":[168],"framework":[169],"leverages":[171],"pretrained":[172],"transformer":[173],"encode":[176],"textual":[180],"information.":[181],"Furthermore,":[182],"our":[183],"method":[184,220],"utilizes":[185],"multi-head":[187],"attention":[188],"mechanism":[189,203],"generate":[191],"three":[192],"distinct":[193],"vision-language":[194],"representations":[195],"fuses":[197],"them":[198],"using":[199],"sophisticated":[201],"gating":[202],"answer":[205,227],"query":[207],"regarding":[208],"image.":[210],"Extensive":[211],"experiments":[212],"show":[216],"outperformed":[221],"baseline":[224],"across":[225],"various":[226],"categories.":[228],"The":[229],"benchmark":[230],"source":[232],"code":[233],"available":[235],"athttps://github.com/eftekhar-hossain/Bengali-VQA.":[236]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}