{"id":"https://openalex.org/W4410636387","doi":"https://doi.org/10.1145/3701716.3717563","title":"Diverse Knowledge Selection for Enhanced Zero-shot Visual Question Answering","display_name":"Diverse Knowledge Selection for Enhanced Zero-shot Visual Question Answering","publication_year":2025,"publication_date":"2025-05-08","ids":{"openalex":"https://openalex.org/W4410636387","doi":"https://doi.org/10.1145/3701716.3717563"},"language":"en","primary_location":{"id":"doi:10.1145/3701716.3717563","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3717563","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3717563","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3717563","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101411564","display_name":"Seunghoon Han","orcid":"https://orcid.org/0009-0008-3393-4797"},"institutions":[{"id":"https://openalex.org/I196345858","display_name":"Chungnam National University","ror":"https://ror.org/0227as991","country_code":"KR","type":"education","lineage":["https://openalex.org/I196345858"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Seunghoon Han","raw_affiliation_strings":["Chungnam National University, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Chungnam National University, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I196345858"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110178360","display_name":"Min-Gyu Choi","orcid":"https://orcid.org/0009-0006-2909-150X"},"institutions":[{"id":"https://openalex.org/I196345858","display_name":"Chungnam National University","ror":"https://ror.org/0227as991","country_code":"KR","type":"education","lineage":["https://openalex.org/I196345858"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Mingyu Choi","raw_affiliation_strings":["Chungnam National University, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Chungnam National University, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I196345858"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102507492","display_name":"Hyewon Lee","orcid":"https://orcid.org/0009-0003-9573-2916"},"institutions":[{"id":"https://openalex.org/I196345858","display_name":"Chungnam National University","ror":"https://ror.org/0227as991","country_code":"KR","type":"education","lineage":["https://openalex.org/I196345858"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyewon Lee","raw_affiliation_strings":["Chungnam National University, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Chungnam National University, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I196345858"]}]},{"author_position":"middle","author":{"id":null,"display_name":"SoYoung Park","orcid":"https://orcid.org/0009-0000-7755-0041"},"institutions":[{"id":"https://openalex.org/I196345858","display_name":"Chungnam National University","ror":"https://ror.org/0227as991","country_code":"KR","type":"education","lineage":["https://openalex.org/I196345858"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"SoYoung Park","raw_affiliation_strings":["Chungnam National University, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Chungnam National University, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I196345858"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101953394","display_name":"Jong-Ryul Lee","orcid":"https://orcid.org/0000-0003-0774-3619"},"institutions":[{"id":"https://openalex.org/I196345858","display_name":"Chungnam National University","ror":"https://ror.org/0227as991","country_code":"KR","type":"education","lineage":["https://openalex.org/I196345858"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jong-Ryul Lee","raw_affiliation_strings":["Chungnam National University, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Chungnam National University, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I196345858"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011058984","display_name":"Sungsu Lim","orcid":"https://orcid.org/0000-0001-5924-3398"},"institutions":[{"id":"https://openalex.org/I196345858","display_name":"Chungnam National University","ror":"https://ror.org/0227as991","country_code":"KR","type":"education","lineage":["https://openalex.org/I196345858"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sungsu Lim","raw_affiliation_strings":["Chungnam National University, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Chungnam National University, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I196345858"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100452223","display_name":"Taeho Kim","orcid":"https://orcid.org/0000-0003-4522-5388"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tae-Ho Kim","raw_affiliation_strings":["Nota Inc., Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Nota Inc., Seoul, Republic of Korea","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101411564"],"corresponding_institution_ids":["https://openalex.org/I196345858"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09232831,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2161","last_page":"2169"},"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":0.9987000226974487,"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":0.9984999895095825,"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":0.8094834089279175},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.7023402452468872},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6797118782997131},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.42828384041786194},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.41418319940567017},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38498643040657043},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3847897946834564},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.12176364660263062},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06455138325691223}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8094834089279175},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.7023402452468872},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6797118782997131},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.42828384041786194},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.41418319940567017},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38498643040657043},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3847897946834564},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.12176364660263062},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06455138325691223},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3701716.3717563","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3717563","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3717563","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3701716.3717563","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3717563","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3717563","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2811919172","display_name":null,"funder_award_id":"RS-2022-00155857","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G4380231476","display_name":null,"funder_award_id":"RS-2024-00468747","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G4700831490","display_name":null,"funder_award_id":"2022-","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G4939975072","display_name":null,"funder_award_id":"RS-2022-00155857","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G6072120315","display_name":null,"funder_award_id":"funded","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G6789273066","display_name":null,"funder_award_id":"RS-2022-00155857","funder_id":"https://openalex.org/F4320321204","funder_display_name":"Chungnam National University"},{"id":"https://openalex.org/G8582691448","display_name":null,"funder_award_id":"MOTIE, Korea","funder_id":"https://openalex.org/F4320321681","funder_display_name":"Ministry of Trade, Industry and Energy"},{"id":"https://openalex.org/G992484961","display_name":null,"funder_award_id":"Korea","funder_id":"https://openalex.org/F4320321681","funder_display_name":"Ministry of Trade, Industry and Energy"}],"funders":[{"id":"https://openalex.org/F4320321204","display_name":"Chungnam National University","ror":"https://ror.org/0227as991"},{"id":"https://openalex.org/F4320321681","display_name":"Ministry of Trade, Industry and Energy","ror":"https://ror.org/008nkqk13"},{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410636387.pdf","grobid_xml":"https://content.openalex.org/works/W4410636387.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W2069153192","https://openalex.org/W2138621811","https://openalex.org/W2560730294","https://openalex.org/W2962933067","https://openalex.org/W2963191264","https://openalex.org/W2963477107","https://openalex.org/W2963954913","https://openalex.org/W2964138343","https://openalex.org/W2970641574","https://openalex.org/W2981852735","https://openalex.org/W2997789966","https://openalex.org/W3199693760","https://openalex.org/W3202473058","https://openalex.org/W4288089799","https://openalex.org/W4385574156","https://openalex.org/W4387968292","https://openalex.org/W4389519546","https://openalex.org/W4393782427"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2384605597","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2387743295","https://openalex.org/W2366718574","https://openalex.org/W2359774528"],"abstract_inverted_index":{"Visual":[0,92],"Question":[1,93],"Answering":[2,94],"(VQA)":[3],"is":[4,79,148],"one":[5],"of":[6,24,56,64,75,98,116,138],"the":[7,16,21,73,113,134,145],"important":[8],"tasks":[9],"that":[10,46],"can":[11],"help":[12],"artificial":[13],"intelligence":[14],"understand":[15],"real":[17],"world.":[18],"Recently,":[19],"with":[20,126],"growing":[22],"popularity":[23],"zero-shot":[25,127],"VQA,":[26],"research":[27],"has":[28],"focused":[29],"on":[30,118],"utilizing":[31],"external":[32,50],"knowledge":[33,51,57,66,78],"to":[34,48,70],"tackle":[35],"complex":[36],"problems,":[37],"especially":[38],"those":[39],"requiring":[40],"common":[41],"sense.":[42],"However,":[43],"existing":[44],"studies":[45],"attempt":[47],"leverage":[49],"often":[52],"use":[53],"large":[54],"amounts":[55],"without":[58],"any":[59],"selection":[60],"process.":[61],"Since":[62],"some":[63],"this":[65,83],"may":[67],"not":[68],"contribute":[69],"accurate":[71],"predictions,":[72],"process":[74],"selecting":[76],"relevant":[77],"essential.":[80],"To":[81],"address":[82],"issue,":[84],"we":[85],"propose":[86],"Diverse":[87],"Knowledge":[88,104,109],"Selection":[89],"for":[90],"Enhanced":[91],"(DKSVQA),":[95],"which":[96],"consists":[97],"three":[99],"stages:":[100],"Image-Context":[101],"Generation,":[102],"Similarity-based":[103],"Selection,":[105],"and":[106,123,136],"Query-Knowledge":[107],"Graph-based":[108],"Selection.":[110],"We":[111,131],"demonstrate":[112],"superior":[114],"performance":[115],"DKSVQA":[117,139],"two":[119],"VQA":[120,128],"benchmark":[121],"datasets":[122],"compare":[124],"it":[125],"baseline":[129],"models.":[130],"highlight":[132],"both":[133],"effectiveness":[135],"efficiency":[137],"through":[140],"extensive":[141],"experiments.":[142],"For":[143],"reproducibility,":[144],"source":[146],"code":[147],"available":[149],"at":[150],"https://github.com/gooriiie/DKSVQA.":[151]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
