{"id":"https://openalex.org/W4390872809","doi":"https://doi.org/10.1109/iccv51070.2023.00288","title":"Open-Vocabulary Video Question Answering: A New Benchmark for Evaluating the Generalizability of Video Question Answering Models","display_name":"Open-Vocabulary Video Question Answering: A New Benchmark for Evaluating the Generalizability of Video Question Answering Models","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4390872809","doi":"https://doi.org/10.1109/iccv51070.2023.00288"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51070.2023.00288","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51070.2023.00288","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008798023","display_name":"Dohwan Ko","orcid":null},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dohwan Ko","raw_affiliation_strings":["Korea University,Department of Computer Science and Engineering","Department of Computer Science and Engineering, Korea University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University,Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Korea University","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101482853","display_name":"Ji Soo Lee","orcid":"https://orcid.org/0009-0003-9055-5236"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ji Soo Lee","raw_affiliation_strings":["Korea University,Department of Computer Science and Engineering","Department of Computer Science and Engineering, Korea University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University,Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Korea University","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111027793","display_name":"Miso Choi","orcid":null},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Miso Choi","raw_affiliation_strings":["Korea University,Department of Computer Science and Engineering","Department of Computer Science and Engineering, Korea University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University,Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Korea University","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079985802","display_name":"Jaewon Chu","orcid":null},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaewon Chu","raw_affiliation_strings":["Korea University,Department of Computer Science and Engineering","Department of Computer Science and Engineering, Korea University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University,Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Korea University","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100740584","display_name":"Jihwan Park","orcid":"https://orcid.org/0009-0007-2223-7278"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jihwan Park","raw_affiliation_strings":["Korea University,Department of Computer Science and Engineering","Department of Computer Science and Engineering, Korea University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University,Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Korea University","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084814930","display_name":"Hyunwoo J. Kim","orcid":"https://orcid.org/0000-0002-2181-9264"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyunwoo J. Kim","raw_affiliation_strings":["Korea University,Department of Computer Science and Engineering","Department of Computer Science and Engineering, Korea University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University,Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Korea University","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I197347611"],"apc_list":null,"apc_paid":null,"fwci":0.5835,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.77221342,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3078","last_page":"3089"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.996399998664856,"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":0.9952999949455261,"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":0.9409792423248291},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.8224073648452759},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7777428030967712},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7228792309761047},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6297043561935425},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5177420973777771},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5095255970954895},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4189125895500183},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3396740257740021},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1214894950389862},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07140237092971802}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.9409792423248291},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.8224073648452759},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7777428030967712},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7228792309761047},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6297043561935425},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5177420973777771},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5095255970954895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4189125895500183},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3396740257740021},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1214894950389862},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07140237092971802},{"id":"https://openalex.org/C138496976","wikidata":"https://www.wikidata.org/wiki/Q175002","display_name":"Developmental psychology","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccv51070.2023.00288","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51070.2023.00288","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5299999713897705,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W2250539671","https://openalex.org/W2270070752","https://openalex.org/W2560730294","https://openalex.org/W2561529111","https://openalex.org/W2604254608","https://openalex.org/W2606982687","https://openalex.org/W2765716052","https://openalex.org/W2963518342","https://openalex.org/W2963541336","https://openalex.org/W2963644680","https://openalex.org/W2964051675","https://openalex.org/W2964220823","https://openalex.org/W2978017171","https://openalex.org/W2984008963","https://openalex.org/W3034730770","https://openalex.org/W3096580779","https://openalex.org/W3098267758","https://openalex.org/W3105232955","https://openalex.org/W3153427360","https://openalex.org/W3168640669","https://openalex.org/W3173777717","https://openalex.org/W3173859428","https://openalex.org/W3174366544","https://openalex.org/W3174784402","https://openalex.org/W3175961224","https://openalex.org/W3177934633","https://openalex.org/W3188542058","https://openalex.org/W3197457832","https://openalex.org/W3198377975","https://openalex.org/W3204588463","https://openalex.org/W3216939881","https://openalex.org/W3217059257","https://openalex.org/W4205857304","https://openalex.org/W4285286749","https://openalex.org/W4287887247","https://openalex.org/W4312310776","https://openalex.org/W4312424618","https://openalex.org/W4312458986","https://openalex.org/W4312563428","https://openalex.org/W4312651322","https://openalex.org/W4312747482","https://openalex.org/W4312912313","https://openalex.org/W4312960937","https://openalex.org/W4313026212","https://openalex.org/W4313186260","https://openalex.org/W4386075561","https://openalex.org/W4386076661","https://openalex.org/W4386187806","https://openalex.org/W6726873649","https://openalex.org/W6736685754","https://openalex.org/W6754733129","https://openalex.org/W6755207826","https://openalex.org/W6760001035","https://openalex.org/W6763578275","https://openalex.org/W6764756247","https://openalex.org/W6768851824","https://openalex.org/W6778883912","https://openalex.org/W6779068807","https://openalex.org/W6784333009","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6797109355","https://openalex.org/W6800480908","https://openalex.org/W6802517928","https://openalex.org/W6804277322","https://openalex.org/W6805349323","https://openalex.org/W6811433417","https://openalex.org/W6838434436"],"related_works":["https://openalex.org/W2118717649","https://openalex.org/W2413243053","https://openalex.org/W410723623","https://openalex.org/W2015341305","https://openalex.org/W2035068594","https://openalex.org/W4225593417","https://openalex.org/W2573498121","https://openalex.org/W3022298670","https://openalex.org/W3160494304","https://openalex.org/W3006162251"],"abstract_inverted_index":{"Video":[0,99],"Question":[1,100],"Answering":[2,101],"(VideoQA)":[3],"is":[4,32,223],"a":[5,51,60,95,128,209],"challenging":[6],"task":[7,53],"that":[8,133,184,202],"entails":[9],"complex":[10],"multi-modal":[11],"reasoning.":[12],"In":[13,116],"contrast":[14],"to":[15,20,33,54,78,87,103,120],"multiple-choice":[16],"VideoQA":[17,31,45,49,108,162,216],"which":[18,66],"aims":[19],"predict":[21],"the":[22,27,41,56,76,105,122,135,144,158,191,213],"answer":[23,34,62],"given":[24],"several":[25],"options,":[26],"goal":[28],"of":[29,43,107,215],"open-ended":[30,48,161],"questions":[35],"without":[36],"restricting":[37],"candidate":[38],"answers.":[39,91,115,176,199],"However,":[40],"majority":[42],"previous":[44],"models":[46,109,163,217],"formulate":[47],"as":[50,208],"classification":[52],"classify":[55],"video-question":[57],"pairs":[58],"into":[59,171],"fixed":[61],"set,":[63],"i.e.,":[64],"closed-vocabulary,":[65],"contains":[67],"only":[68,82],"frequent":[69,83],"answers":[70,84,141],"(e.g.,":[71],"top-1000":[72],"answers).":[73],"This":[74],"leads":[75],"model":[77,192],"be":[79],"biased":[80],"toward":[81],"and":[85,113,139,164,174,180,197,218],"fail":[86],"generalize":[88],"on":[89,137,195],"out-of-vocabulary":[90],"We":[92,200],"hence":[93],"propose":[94],"new":[96,154],"benchmark,":[97],"Open-vocabulary":[98],"(OVQA),":[102],"measure":[104],"generalizability":[106,214],"by":[110,142,156,168],"considering":[111],"rare":[112,138,173,196],"unseen":[114,140,175,198],"addition,":[117],"in":[118],"order":[119],"improve":[121,165],"model\u2019s":[123],"generalization":[124],"power,":[125],"we":[126,152],"introduce":[127,153],"novel":[129],"GNN-based":[130,186],"soft":[131,187],"verbalizer":[132,188],"enhances":[134],"prediction":[136],"aggregating":[143],"information":[145],"from":[146],"their":[147,166],"similar":[148],"words.":[149],"For":[150],"evaluation,":[151],"baselines":[155],"modifying":[157],"existing":[159],"(closed-vocabulary)":[160],"performances":[167],"further":[169,189],"taking":[170],"account":[172],"Our":[177],"ablation":[178],"studies":[179],"qualitative":[181],"analyses":[182],"demonstrate":[183],"our":[185,203],"improves":[190],"performance,":[193],"especially":[194],"hope":[201],"benchmark":[204],"OVQA":[205],"can":[206],"serve":[207],"guide":[210],"for":[211],"evaluating":[212],"inspire":[219],"future":[220],"research.":[221],"Code":[222],"available":[224],"at":[225],"https://github.com/mlvlab/OVQA.":[226]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}