{"id":"https://openalex.org/W4408280907","doi":"https://doi.org/10.1109/access.2025.3549478","title":"Improving Visual Question Answering by Image Captioning","display_name":"Improving Visual Question Answering by Image Captioning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4408280907","doi":"https://doi.org/10.1109/access.2025.3549478"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3549478","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3549478","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.2025.3549478","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048208804","display_name":"Xiangjun Shao","orcid":"https://orcid.org/0000-0002-1401-621X"},"institutions":[{"id":"https://openalex.org/I196038209","display_name":"Hunan University of Arts and Science","ror":"https://ror.org/01ggnn306","country_code":"CN","type":"education","lineage":["https://openalex.org/I196038209"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangjun Shao","raw_affiliation_strings":["School of Computer and Electrical Engineering, Hunan University of Arts and Science, Changde, China"],"raw_orcid":"https://orcid.org/0000-0002-1401-621X","affiliations":[{"raw_affiliation_string":"School of Computer and Electrical Engineering, Hunan University of Arts and Science, Changde, China","institution_ids":["https://openalex.org/I196038209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036292926","display_name":"Hongsong Dong","orcid":"https://orcid.org/0000-0002-5355-1995"},"institutions":[{"id":"https://openalex.org/I4210105359","display_name":"Shanghai Liangyou (China)","ror":"https://ror.org/029zp7d63","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210105359"]},{"id":"https://openalex.org/I4210148119","display_name":"Luliang University","ror":"https://ror.org/05495v729","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210148119"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongsong Dong","raw_affiliation_strings":["Department of Computer Science, Lyuliang University, Lüliang, China","Department of Computer Science, Lyuliang University, Lvliang, China"],"raw_orcid":"https://orcid.org/0000-0002-5355-1995","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Lyuliang University, Lüliang, China","institution_ids":["https://openalex.org/I4210105359"]},{"raw_affiliation_string":"Department of Computer Science, Lyuliang University, Lvliang, China","institution_ids":["https://openalex.org/I4210148119"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027950316","display_name":"Guangsheng Wu","orcid":"https://orcid.org/0000-0002-7739-9422"},"institutions":[{"id":"https://openalex.org/I4210109434","display_name":"Xinyu University","ror":"https://ror.org/021xwcd05","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210109434"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangsheng Wu","raw_affiliation_strings":["School of Mathematics and Computer Science, Xinyu University, Xinyu, China","School of Mathematics and Computer Science, Xinyu University, Xingyu, China"],"raw_orcid":"https://orcid.org/0000-0002-7739-9422","affiliations":[{"raw_affiliation_string":"School of Mathematics and Computer Science, Xinyu University, Xinyu, China","institution_ids":["https://openalex.org/I4210109434"]},{"raw_affiliation_string":"School of Mathematics and Computer Science, Xinyu University, Xingyu, China","institution_ids":["https://openalex.org/I4210109434"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02678786,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"46299","last_page":"46311"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9959999918937683,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9908000230789185,"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":0.8966953754425049},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7881277799606323},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7530931830406189},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5438358187675476},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48425742983818054},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.46090707182884216},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4574519693851471},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.41859686374664307},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36061590909957886}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8966953754425049},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7881277799606323},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7530931830406189},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5438358187675476},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48425742983818054},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.46090707182884216},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4574519693851471},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41859686374664307},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36061590909957886}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3549478","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3549478","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:e4668c2298b04e33a1b617526d430b6e","is_oa":true,"landing_page_url":"https://doaj.org/article/e4668c2298b04e33a1b617526d430b6e","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 46299-46311 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3549478","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3549478","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":[{"id":"https://openalex.org/G3835101086","display_name":null,"funder_award_id":"20224BAB202022","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5279157640","display_name":null,"funder_award_id":"22A0490","funder_id":"https://openalex.org/F4320336581","funder_display_name":"Chunhui Project Foundation of the Education Department of China"},{"id":"https://openalex.org/G6792774478","display_name":null,"funder_award_id":"62273142","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336581","display_name":"Chunhui Project Foundation of the Education Department of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W102708294","https://openalex.org/W639708223","https://openalex.org/W1895577753","https://openalex.org/W1933349210","https://openalex.org/W1947481528","https://openalex.org/W1988432728","https://openalex.org/W2194775991","https://openalex.org/W2220981600","https://openalex.org/W2277195237","https://openalex.org/W2302086703","https://openalex.org/W2339652278","https://openalex.org/W2546696630","https://openalex.org/W2552161745","https://openalex.org/W2560730294","https://openalex.org/W2560920409","https://openalex.org/W2584723080","https://openalex.org/W2607768201","https://openalex.org/W2732016772","https://openalex.org/W2745461083","https://openalex.org/W2747623286","https://openalex.org/W2798959609","https://openalex.org/W2808206191","https://openalex.org/W2890531016","https://openalex.org/W2950635152","https://openalex.org/W2962749469","https://openalex.org/W2963150162","https://openalex.org/W2963176022","https://openalex.org/W2963355794","https://openalex.org/W2963383024","https://openalex.org/W2963398599","https://openalex.org/W2963477107","https://openalex.org/W2963656855","https://openalex.org/W2963954913","https://openalex.org/W2964018924","https://openalex.org/W2964023275","https://openalex.org/W2964303913","https://openalex.org/W2966683369","https://openalex.org/W2981694290","https://openalex.org/W2984138079","https://openalex.org/W2986670728","https://openalex.org/W2990069284","https://openalex.org/W3002557610","https://openalex.org/W3005881764","https://openalex.org/W3011329351","https://openalex.org/W3034984754","https://openalex.org/W3093890448","https://openalex.org/W3107273227","https://openalex.org/W3135705837","https://openalex.org/W3152635550","https://openalex.org/W3177244742","https://openalex.org/W3198730297","https://openalex.org/W3198817488","https://openalex.org/W4226397046","https://openalex.org/W4291900964","https://openalex.org/W4380200507","https://openalex.org/W4390241396","https://openalex.org/W6715144786","https://openalex.org/W6728881024","https://openalex.org/W6731370813","https://openalex.org/W6752083267"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757","https://openalex.org/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W1938708284","https://openalex.org/W4380190185"],"abstract_inverted_index":{"Visual":[0],"Question":[1],"Answering":[2],"(VQA)":[3],"is":[4],"a":[5,68],"challenging":[6],"task":[7],"that":[8,100,141,178],"bridges":[9],"the":[10,36,44,52,59,79,102,130,142,155,179],"computer":[11],"vision":[12],"and":[13,38,126,152,157,174],"natural":[14,20],"language":[15,21],"processing":[16],"communities.":[17],"It":[18],"provide":[19],"answers":[22],"to":[23,26,57,89,107,135],"questions":[24,60],"related":[25,91],"an":[27,84,96],"associated":[28],"image.":[29],"Most":[30],"existing":[31,168],"VQA":[32,169],"methods":[33],"focus":[34],"on":[35,154],"fusion":[37],"inference":[39],"of":[40,144,146,161],"visual":[41,48,124],"features":[42,49,125],"with":[43],"textual":[45],"question.":[46],"However,":[47],"often":[50],"lack":[51],"necessary":[53],"semantic":[54,80,127],"information":[55,81,113,128],"required":[56],"answer":[58,90,115,136],"accurately.":[61],"To":[62],"address":[63],"this":[64],"limitation,":[65],"we":[66,94],"propose":[67],"novel":[69],"approach":[70],"called":[71],"Question-Guided":[72],"Parallel":[73],"Attention":[74],"(QGPA),":[75],"which":[76,121,165],"effectively":[77],"leverages":[78],"provided":[82],"by":[83],"embedded":[85,131],"image":[86,132],"captioning":[87,133],"model":[88,134,149],"questions.":[92,137],"First,":[93],"introduce":[95],"Attention-Aware":[97],"(AA)":[98],"mechanism":[99],"extends":[101],"traditional":[103],"attention":[104],"mechanism,":[105],"helping":[106],"filter":[108],"out":[109],"incorrect":[110],"or":[111],"irrelevant":[112],"during":[114],"prediction.":[116],"Second,":[117],"QGPA":[118],"incorporates":[119],"AA,":[120],"simultaneously":[122],"utilizes":[123],"from":[129],"Experiments":[138],"results":[139,173],"demonstrate":[140,177],"accuracy":[143],"\u201cOverall\u201d":[145],"our":[147],"proposed":[148,180],"delivers":[150],"72.57%":[151],"72.55%":[153],"test-dev":[156],"test-std":[158],"split":[159],"set":[160],"VQA-v2.0":[162],"dataset,":[163],"respectively,":[164],"outperforms":[166],"most":[167],"methods.":[170],"The":[171],"experiment":[172],"ablation":[175],"studies":[176],"method":[181],"has":[182],"good":[183],"performance.":[184]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}