{"id":"https://openalex.org/W4403488562","doi":"https://doi.org/10.3233/faia240501","title":"Generalizing Visual Question Answering from Synthetic to Human-Written Questions via a Chain of QA with a Large Language Model","display_name":"Generalizing Visual Question Answering from Synthetic to Human-Written Questions via a Chain of QA with a Large Language Model","publication_year":2024,"publication_date":"2024-10-16","ids":{"openalex":"https://openalex.org/W4403488562","doi":"https://doi.org/10.3233/faia240501"},"language":"en","primary_location":{"id":"doi:10.3233/faia240501","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240501","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240501","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"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":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240501","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100369148","display_name":"Taehee Kim","orcid":"https://orcid.org/0000-0003-0577-4032"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Taehee Kim","raw_affiliation_strings":["Radisen Co. Ltd"],"affiliations":[{"raw_affiliation_string":"Radisen Co. Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109878326","display_name":"Yeongjae Cho","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yeongjae Cho","raw_affiliation_strings":["Seoul National University"],"affiliations":[{"raw_affiliation_string":"Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101841498","display_name":"Heejun Shin","orcid":"https://orcid.org/0009-0005-7437-7278"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heejun Shin","raw_affiliation_strings":["Radisen Co. Ltd"],"affiliations":[{"raw_affiliation_string":"Radisen Co. Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021733732","display_name":"Yohan Jo","orcid":"https://orcid.org/0009-0006-9296-3403"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yohan Jo","raw_affiliation_strings":["Seoul National University"],"affiliations":[{"raw_affiliation_string":"Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113724376","display_name":"Dong-Myung Shin","orcid":"https://orcid.org/0000-0002-2549-0136"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongmyung Shin","raw_affiliation_strings":["Radisen Co. Ltd"],"affiliations":[{"raw_affiliation_string":"Radisen Co. Ltd","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100369148"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6182,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.94066349,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9997000098228455,"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":0.987500011920929,"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":0.9765999913215637,"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/question-answering","display_name":"Question answering","score":0.841981053352356},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6383389234542847},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.546248197555542},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.5038699507713318},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4705268144607544},{"id":"https://openalex.org/keywords/chain","display_name":"Chain (unit)","score":0.41461828351020813},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.17949599027633667},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08554983139038086}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.841981053352356},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6383389234542847},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.546248197555542},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5038699507713318},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4705268144607544},{"id":"https://openalex.org/C199185054","wikidata":"https://www.wikidata.org/wiki/Q552299","display_name":"Chain (unit)","level":2,"score":0.41461828351020813},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.17949599027633667},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08554983139038086},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia240501","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240501","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240501","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"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":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia240501","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240501","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240501","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"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":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403488562.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W2349927912","https://openalex.org/W3159777597","https://openalex.org/W4212839359","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Visual":[0],"question":[1],"answering":[2],"(VQA)":[3],"is":[4,10,34,37,47,166],"a":[5,13,28,48,75,88,94,99],"task":[6],"where":[7],"an":[8,24],"image":[9],"given,":[11],"and":[12,98,108,130,134,154],"series":[14],"of":[15,31,80,90,119,124,144],"questions":[16,84],"are":[17],"asked":[18],"about":[19],"the":[20,117],"image.":[21],"To":[22,69],"build":[23],"efficient":[25],"VQA":[26,55,100,126,152],"algorithm,":[27],"large":[29,95],"amount":[30],"QA":[32,42,81,91],"data":[33,60,105],"required":[35],"which":[36],"very":[38],"expensive.":[39],"Generating":[40],"synthetic":[41,104],"pairs":[43],"based":[44],"on":[45,58,65,103,121],"templates":[46],"practical":[49],"way":[50],"to":[51,106],"obtain":[52],"data.":[53,145],"However,":[54],"models":[56,157],"trained":[57,102],"those":[59],"do":[61],"not":[62],"perform":[63],"well":[64],"complex,":[66],"human-written":[67,83,113,125],"questions.":[68,114],"address":[70],"this":[71],"issue,":[72],"we":[73],"propose":[74],"new":[76],"method":[77],"called":[78],"chain":[79],"for":[82,112,128,164],"(CoQAH).":[85],"CoQAH":[86,120,147,165],"utilizes":[87],"sequence":[89],"interactions":[92],"between":[93],"language":[96],"model":[97,101],"reason":[107],"derive":[109],"logical":[110],"answers":[111],"We":[115],"tested":[116],"effectiveness":[118],"two":[122],"types":[123,143],"datasets":[127],"3D-rendered":[129],"chest":[131],"X-ray":[132],"images":[133],"found":[135],"that":[136],"it":[137],"achieved":[138],"state-of-the-art":[139],"accuracy":[140],"in":[141],"both":[142],"Notably,":[146],"outperformed":[148],"general":[149],"vision-language":[150],"models,":[151,153],"medical":[155],"foundation":[156],"with":[158],"no":[159],"finetuning.":[160],"The":[161],"source":[162],"code":[163],"available":[167],"[10].":[168]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-25T14:56:36.534964","created_date":"2025-10-10T00:00:00"}