{"id":"https://openalex.org/W4385768011","doi":"https://doi.org/10.24963/ijcai.2023/146","title":"Answer Mining from a Pool of Images: Towards Retrieval-Based Visual Question Answering","display_name":"Answer Mining from a Pool of Images: Towards Retrieval-Based Visual Question Answering","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385768011","doi":"https://doi.org/10.24963/ijcai.2023/146"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/146","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/146","pdf_url":"https://www.ijcai.org/proceedings/2023/0146.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0146.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009838940","display_name":"Abhirama Subramanyam Penamakuri","orcid":"https://orcid.org/0000-0003-3646-8492"},"institutions":[{"id":"https://openalex.org/I154549908","display_name":"Indian Institute of Technology Jodhpur","ror":"https://ror.org/03yacj906","country_code":"IN","type":"education","lineage":["https://openalex.org/I154549908"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Abhirama Subramanyam Penamakuri","raw_affiliation_strings":["Indian Institute of Technology Jodhpur"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Jodhpur","institution_ids":["https://openalex.org/I154549908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101454729","display_name":"Manish Gupta","orcid":"https://orcid.org/0000-0003-0848-6132"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Manish Gupta","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100898350","display_name":"Mithun Das Gupta","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mithun Das Gupta","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075621328","display_name":"Anand Mishra","orcid":"https://orcid.org/0000-0002-7806-2557"},"institutions":[{"id":"https://openalex.org/I154549908","display_name":"Indian Institute of Technology Jodhpur","ror":"https://ror.org/03yacj906","country_code":"IN","type":"education","lineage":["https://openalex.org/I154549908"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anand Mishra","raw_affiliation_strings":["Indian Institute of Technology Jodhpur"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Jodhpur","institution_ids":["https://openalex.org/I154549908"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7859,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.74029629,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1312","last_page":"1321"},"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":0.9952999949455261,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9937999844551086,"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/question-answering","display_name":"Question answering","score":0.8729227781295776},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8213306069374084},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7062636613845825},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6260194778442383},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.6091320514678955},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.592663586139679},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5497744679450989},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.5102584362030029},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48297300934791565},{"id":"https://openalex.org/keywords/fluency","display_name":"Fluency","score":0.4586254954338074},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4359472393989563},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.43308448791503906},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.41146695613861084},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34219858050346375},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.11799359321594238}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8729227781295776},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8213306069374084},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7062636613845825},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6260194778442383},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.6091320514678955},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.592663586139679},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5497744679450989},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.5102584362030029},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48297300934791565},{"id":"https://openalex.org/C2777413886","wikidata":"https://www.wikidata.org/wiki/Q3276013","display_name":"Fluency","level":2,"score":0.4586254954338074},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4359472393989563},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.43308448791503906},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.41146695613861084},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34219858050346375},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.11799359321594238},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/146","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/146","pdf_url":"https://www.ijcai.org/proceedings/2023/0146.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/146","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/146","pdf_url":"https://www.ijcai.org/proceedings/2023/0146.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8500000238418579,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385768011.pdf"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1522301498","https://openalex.org/W1575833922","https://openalex.org/W1861492603","https://openalex.org/W1933349210","https://openalex.org/W2142192571","https://openalex.org/W2189070436","https://openalex.org/W2277195237","https://openalex.org/W2293453011","https://openalex.org/W2463565445","https://openalex.org/W2561715562","https://openalex.org/W2746097825","https://openalex.org/W2896457183","https://openalex.org/W2947312908","https://openalex.org/W2962749469","https://openalex.org/W2963191264","https://openalex.org/W2963224792","https://openalex.org/W2963323070","https://openalex.org/W2963383024","https://openalex.org/W2963530300","https://openalex.org/W2963541336","https://openalex.org/W2963890755","https://openalex.org/W2963954913","https://openalex.org/W2964118342","https://openalex.org/W2964138017","https://openalex.org/W2966317026","https://openalex.org/W2968124245","https://openalex.org/W2970231061","https://openalex.org/W2979382951","https://openalex.org/W2979826702","https://openalex.org/W2997591391","https://openalex.org/W3016211260","https://openalex.org/W3034636873","https://openalex.org/W3034727271","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3109643012","https://openalex.org/W3126792443","https://openalex.org/W3167118264","https://openalex.org/W3170560353","https://openalex.org/W3174863418","https://openalex.org/W3176456866","https://openalex.org/W3193402170","https://openalex.org/W3195541832","https://openalex.org/W4287214436","https://openalex.org/W4295312788","https://openalex.org/W4312643954","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2063218608","https://openalex.org/W4386105885","https://openalex.org/W2184288218","https://openalex.org/W2947282851","https://openalex.org/W2374066281","https://openalex.org/W4387423606","https://openalex.org/W2071180033","https://openalex.org/W2036058638","https://openalex.org/W2130409173","https://openalex.org/W2528082075"],"abstract_inverted_index":{"We":[0,49],"study":[1],"visual":[2,56],"question":[3,44,57,81,109],"answering":[4,58],"in":[5,61,91,128],"a":[6,16,25,29,31,79,87,100,108,148,154,171],"setting":[7],"where":[8,78],"the":[9,39,43,72,95,125,135,176,191,195,201],"answer":[10,42,120],"has":[11,82,134],"to":[12,51,83],"be":[13,84],"mined":[14],"from":[15,38,45],"pool":[17,40,149],"of":[18,150,156,168,173,194],"relevant":[19,36,89],"and":[20,41,68,110,140,158,170,181,188,203],"irrelevant":[21],"images":[22,37,112],"given":[23,80],"as":[24,54],"context.":[26,92],"For":[27],"such":[28],"setting,":[30],"model":[32],"must":[33],"first":[34],"retrieve":[35],"these":[46],"retrieved":[47,111],"images.":[48],"refer":[50],"this":[52,129],"problem":[53],"retrieval-based":[55],"(or":[59],"RETVQA":[60,64,96,180],"short).":[62],"The":[63],"is":[65],"distinctively":[66],"different":[67],"more":[69],"challenging":[70],"than":[71],"traditionally-studied":[73],"Visual":[74],"Question":[75],"Answering":[76],"(VQA),":[77],"answered":[85],"with":[86],"single":[88],"image":[90,192],"Towards":[93],"solving":[94],"task,":[97],"we":[98,123],"propose":[99],"unified":[101],"Multi":[102],"Image":[103],"BART":[104],"(MI-BART)":[105],"that":[106],"takes":[107],"using":[113],"our":[114],"relevance":[115],"encoder":[116],"for":[117,143],"free-form":[118],"fluent":[119],"generation.":[121],"Further,":[122],"introduce":[124],"largest":[126],"dataset":[127,199],"space,":[130],"namely":[131,179],"RETVQA,":[132],"which":[133],"following":[136],"salient":[137],"features:":[138],"multi-image":[139],"retrieval":[141],"requirement":[142],"VQA,":[144],"metadata-independent":[145],"questions":[146],"over":[147],"heterogeneous":[151],"images,":[152],"expecting":[153],"mix":[155],"classification-oriented":[157],"open-ended":[159],"generative":[160],"answers.":[161],"Our":[162],"proposed":[163,177],"framework":[164],"achieves":[165],"an":[166],"accuracy":[167,202],"76.5%":[169],"fluency":[172,204],"79.3%":[174],"on":[175,190,200],"dataset,":[178],"also":[182],"outperforms":[183],"state-of-the-art":[184],"methods":[185],"by":[186],"4.9%":[187],"11.8%":[189],"segment":[193],"publicly":[196],"available":[197],"WebQA":[198],"metrics,":[205],"respectively.":[206]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}