{"id":"https://openalex.org/W4229449886","doi":"https://doi.org/10.1109/tpami.2022.3173208","title":"Learning to Answer Visual Questions From Web Videos","display_name":"Learning to Answer Visual Questions From Web Videos","publication_year":2022,"publication_date":"2022-05-09","ids":{"openalex":"https://openalex.org/W4229449886","doi":"https://doi.org/10.1109/tpami.2022.3173208","pmid":"https://pubmed.ncbi.nlm.nih.gov/35533174"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2022.3173208","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2022.3173208","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/hal-03664182","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009826104","display_name":"Antoine Yang","orcid":"https://orcid.org/0000-0002-7258-571X"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I29607241","display_name":"\u00c9cole Normale Sup\u00e9rieure - PSL","ror":"https://ror.org/05a0dhs15","country_code":"FR","type":"other","lineage":["https://openalex.org/I2746051580","https://openalex.org/I29607241"]},{"id":"https://openalex.org/I4210161954","display_name":"D\u00e9partement d'Informatique","ror":"https://ror.org/05y6rqs46","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I2746051580","https://openalex.org/I29607241","https://openalex.org/I4210159245","https://openalex.org/I4210161954"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Antoine Yang","raw_affiliation_strings":["Inria Paris and Département d'informatique de l'ENS, CNRS, PSL Research University, Paris, France","WILLOW - Models of visual object recognition and scene understanding (France)","DI-ENS - D\u00e9partement d'informatique - ENS Paris (\u00c9cole normale sup\u00e9rieure 45 rue d'Ulm F-75230 Paris Cedex 05 - France)"],"raw_orcid":"https://orcid.org/0000-0002-7258-571X","affiliations":[{"raw_affiliation_string":"Inria Paris and Département d'informatique de l'ENS, CNRS, PSL Research University, Paris, France","institution_ids":["https://openalex.org/I29607241","https://openalex.org/I1326498283","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"WILLOW - Models of visual object recognition and scene understanding (France)","institution_ids":[]},{"raw_affiliation_string":"DI-ENS - D\u00e9partement d'informatique - ENS Paris (\u00c9cole normale sup\u00e9rieure 45 rue d'Ulm F-75230 Paris Cedex 05 - France)","institution_ids":["https://openalex.org/I29607241","https://openalex.org/I4210161954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021766835","display_name":"Antoine Miech","orcid":"https://orcid.org/0000-0001-6657-7812"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Antoine Miech","raw_affiliation_strings":["DeepMind, London, U.K","DeepMind [London] (Royaume-Uni)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind, London, U.K","institution_ids":["https://openalex.org/I4210090411"]},{"raw_affiliation_string":"DeepMind [London] (Royaume-Uni)","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025398783","display_name":"Josef \u0160ivic","orcid":"https://orcid.org/0000-0002-2554-5301"},"institutions":[{"id":"https://openalex.org/I4210152232","display_name":"Institute of Informatics of the Slovak Academy of Sciences","ror":"https://ror.org/04jgqpc26","country_code":"SK","type":"facility","lineage":["https://openalex.org/I207624831","https://openalex.org/I4210152232"]},{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ","SK"],"is_corresponding":false,"raw_author_name":"Josef Sivic","raw_affiliation_strings":["Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague, Prague, Czechia","CIIRC - Czech Institute of Informatics, Robotics and Cybernetics [Prague] (Czech Technical University in Prague - R\u00e9publique tch\u00e8que)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague, Prague, Czechia","institution_ids":["https://openalex.org/I44504214"]},{"raw_affiliation_string":"CIIRC - Czech Institute of Informatics, Robotics and Cybernetics [Prague] (Czech Technical University in Prague - R\u00e9publique tch\u00e8que)","institution_ids":["https://openalex.org/I4210152232","https://openalex.org/I44504214"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087781064","display_name":"Ivan Laptev","orcid":"https://orcid.org/0000-0001-7072-3325"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I29607241","display_name":"\u00c9cole Normale Sup\u00e9rieure - PSL","ror":"https://ror.org/05a0dhs15","country_code":"FR","type":"other","lineage":["https://openalex.org/I2746051580","https://openalex.org/I29607241"]},{"id":"https://openalex.org/I4210161954","display_name":"D\u00e9partement d'Informatique","ror":"https://ror.org/05y6rqs46","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I2746051580","https://openalex.org/I29607241","https://openalex.org/I4210159245","https://openalex.org/I4210161954"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ivan Laptev","raw_affiliation_strings":["Inria Paris and Département d'informatique de l'ENS, CNRS, PSL Research University, Paris, France","DI-ENS - D\u00e9partement d'informatique - ENS Paris (\u00c9cole normale sup\u00e9rieure 45 rue d'Ulm F-75230 Paris Cedex 05 - France)","WILLOW - Models of visual object recognition and scene understanding (France)"],"raw_orcid":"https://orcid.org/0000-0001-7072-3325","affiliations":[{"raw_affiliation_string":"Inria Paris and Département d'informatique de l'ENS, CNRS, PSL Research University, Paris, France","institution_ids":["https://openalex.org/I29607241","https://openalex.org/I1326498283","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"DI-ENS - D\u00e9partement d'informatique - ENS Paris (\u00c9cole normale sup\u00e9rieure 45 rue d'Ulm F-75230 Paris Cedex 05 - France)","institution_ids":["https://openalex.org/I29607241","https://openalex.org/I4210161954"]},{"raw_affiliation_string":"WILLOW - Models of visual object recognition and scene understanding (France)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109890544","display_name":"Cordelia Schmid","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I29607241","display_name":"\u00c9cole Normale Sup\u00e9rieure - PSL","ror":"https://ror.org/05a0dhs15","country_code":"FR","type":"other","lineage":["https://openalex.org/I2746051580","https://openalex.org/I29607241"]},{"id":"https://openalex.org/I4210161954","display_name":"D\u00e9partement d'Informatique","ror":"https://ror.org/05y6rqs46","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I2746051580","https://openalex.org/I29607241","https://openalex.org/I4210159245","https://openalex.org/I4210161954"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Cordelia Schmid","raw_affiliation_strings":["Inria Paris and Département d'informatique de l'ENS, CNRS, PSL Research University, Paris, France","WILLOW - Models of visual object recognition and scene understanding (France)","DI-ENS - D\u00e9partement d'informatique - ENS Paris (\u00c9cole normale sup\u00e9rieure 45 rue d'Ulm F-75230 Paris Cedex 05 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria Paris and Département d'informatique de l'ENS, CNRS, PSL Research University, Paris, France","institution_ids":["https://openalex.org/I29607241","https://openalex.org/I1326498283","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"WILLOW - Models of visual object recognition and scene understanding (France)","institution_ids":[]},{"raw_affiliation_string":"DI-ENS - D\u00e9partement d'informatique - ENS Paris (\u00c9cole normale sup\u00e9rieure 45 rue d'Ulm F-75230 Paris Cedex 05 - France)","institution_ids":["https://openalex.org/I29607241","https://openalex.org/I4210161954"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3491,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.89810152,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"47","issue":"5","first_page":"3202","last_page":"3218"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.95169997215271,"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":0.9344000220298767,"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/computer-science","display_name":"Computer science","score":0.856752872467041},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6722652912139893},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6060435771942139},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5771160125732422},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5564539432525635},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5446807742118835},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.512131929397583},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.49326246976852417},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4588937759399414},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4457538425922394},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4345407485961914},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.4206976890563965},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.11826074123382568}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.856752872467041},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6722652912139893},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6060435771942139},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5771160125732422},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5564539432525635},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5446807742118835},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.512131929397583},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.49326246976852417},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4588937759399414},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4457538425922394},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4345407485961914},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.4206976890563965},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.11826074123382568},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpami.2022.3173208","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2022.3173208","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:35533174","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35533174","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:HAL:hal-03664182v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-03664182","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, ⟨10.1109/tpami.2022.3173208⟩","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-03664182v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-03664182","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, ⟨10.1109/tpami.2022.3173208⟩","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6899999976158142}],"awards":[{"id":"https://openalex.org/G5838787665","display_name":"PaRis Artificial Intelligence Research InstitutE","funder_award_id":"ANR-19-P3IA-0001","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G7740602712","display_name":null,"funder_award_id":"CZ.02.1.01/0.0/0.0/15 003/0000468","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"}],"funders":[{"id":"https://openalex.org/F4320309327","display_name":"Google","ror":"https://ror.org/00njsd438"},{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":154,"referenced_works":["https://openalex.org/W1531374185","https://openalex.org/W1566289585","https://openalex.org/W1575833922","https://openalex.org/W1861492603","https://openalex.org/W1889081078","https://openalex.org/W1933349210","https://openalex.org/W2095705004","https://openalex.org/W2251645580","https://openalex.org/W2277195237","https://openalex.org/W2293453011","https://openalex.org/W2463565445","https://openalex.org/W2513522215","https://openalex.org/W2525778437","https://openalex.org/W2555661914","https://openalex.org/W2560730294","https://openalex.org/W2606333299","https://openalex.org/W2606982687","https://openalex.org/W2737435850","https://openalex.org/W2741903908","https://openalex.org/W2745461083","https://openalex.org/W2765716052","https://openalex.org/W2798895485","https://openalex.org/W2807750936","https://openalex.org/W2808181286","https://openalex.org/W2883429621","https://openalex.org/W2886641317","https://openalex.org/W2896457183","https://openalex.org/W2897857500","https://openalex.org/W2899663614","https://openalex.org/W2904452845","https://openalex.org/W2907820376","https://openalex.org/W2949178656","https://openalex.org/W2949849869","https://openalex.org/W2954199749","https://openalex.org/W2962717047","https://openalex.org/W2962910007","https://openalex.org/W2962949233","https://openalex.org/W2963351776","https://openalex.org/W2963383024","https://openalex.org/W2963541336","https://openalex.org/W2963656855","https://openalex.org/W2963717374","https://openalex.org/W2963748441","https://openalex.org/W2963890755","https://openalex.org/W2963954913","https://openalex.org/W2963976294","https://openalex.org/W2964057271","https://openalex.org/W2964220823","https://openalex.org/W2964306921","https://openalex.org/W2964322347","https://openalex.org/W2965628639","https://openalex.org/W2966715458","https://openalex.org/W2968124245","https://openalex.org/W2969876226","https://openalex.org/W2970231061","https://openalex.org/W2970869018","https://openalex.org/W2972113750","https://openalex.org/W2978017171","https://openalex.org/W2981851019","https://openalex.org/W2984008963","https://openalex.org/W2988673764","https://openalex.org/W2997344006","https://openalex.org/W2997591391","https://openalex.org/W2997789966","https://openalex.org/W2997805943","https://openalex.org/W2998166190","https://openalex.org/W2998356391","https://openalex.org/W3003260174","https://openalex.org/W3003991937","https://openalex.org/W3004037805","https://openalex.org/W3006320872","https://openalex.org/W3010593057","https://openalex.org/W3014611590","https://openalex.org/W3016211260","https://openalex.org/W3016658915","https://openalex.org/W3022039293","https://openalex.org/W3023993913","https://openalex.org/W3029623490","https://openalex.org/W3034636873","https://openalex.org/W3034726550","https://openalex.org/W3034727271","https://openalex.org/W3034730770","https://openalex.org/W3035167603","https://openalex.org/W3035218869","https://openalex.org/W3035265375","https://openalex.org/W3035635319","https://openalex.org/W3036224891","https://openalex.org/W3043840704","https://openalex.org/W3089358914","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3105232955","https://openalex.org/W3105758476","https://openalex.org/W3105858579","https://openalex.org/W3142774842","https://openalex.org/W3145450063","https://openalex.org/W3159481202","https://openalex.org/W3159630763","https://openalex.org/W3166396011","https://openalex.org/W3167092180","https://openalex.org/W3168620925","https://openalex.org/W3168640669","https://openalex.org/W3172523222","https://openalex.org/W3173367591","https://openalex.org/W3174564426","https://openalex.org/W3175961224","https://openalex.org/W3176362845","https://openalex.org/W3176398504","https://openalex.org/W3176821361","https://openalex.org/W3182683290","https://openalex.org/W3184784418","https://openalex.org/W3197457832","https://openalex.org/W3198966763","https://openalex.org/W3204588463","https://openalex.org/W3213562172","https://openalex.org/W4221166385","https://openalex.org/W4287125738","https://openalex.org/W4287550992","https://openalex.org/W4287757777","https://openalex.org/W4288000169","https://openalex.org/W4288089799","https://openalex.org/W4292779060","https://openalex.org/W4295101003","https://openalex.org/W4385245566","https://openalex.org/W4394666973","https://openalex.org/W6631875545","https://openalex.org/W6634232107","https://openalex.org/W6639432524","https://openalex.org/W6674330103","https://openalex.org/W6691600087","https://openalex.org/W6697449767","https://openalex.org/W6719057275","https://openalex.org/W6727690538","https://openalex.org/W6730088351","https://openalex.org/W6755977528","https://openalex.org/W6763170755","https://openalex.org/W6766904570","https://openalex.org/W6767211374","https://openalex.org/W6767279747","https://openalex.org/W6768851824","https://openalex.org/W6769627184","https://openalex.org/W6770906865","https://openalex.org/W6773737242","https://openalex.org/W6775188310","https://openalex.org/W6776501608","https://openalex.org/W6778449702","https://openalex.org/W6778883912","https://openalex.org/W6779997284","https://openalex.org/W6780226713","https://openalex.org/W6784187948","https://openalex.org/W6786140819","https://openalex.org/W6791353385","https://openalex.org/W6797109355","https://openalex.org/W6804277322"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2129767422","https://openalex.org/W3210196349","https://openalex.org/W4214728004","https://openalex.org/W2950181282","https://openalex.org/W2963261224","https://openalex.org/W2798287483","https://openalex.org/W2913410650"],"abstract_inverted_index":{"Recent":[0],"methods":[1],"for":[2,17,41,135,192,197],"visual":[3],"question":[4,43,54],"answering":[5,44],"rely":[6],"on":[7,58,103,144,223],"large-scale":[8,38],"annotated":[9],"datasets.":[10,150],"Manual":[11],"annotation":[12,34],"of":[13,47,91,164],"questions":[14],"and":[15,23,35,61,112,122,129,148,167,188,212,218],"answers":[16,93],"videos,":[18,74],"however,":[19],"is":[20],"tedious,":[21],"expensive":[22],"prevents":[24],"scalability.":[25],"In":[26],"this":[27,95],"work,":[28],"we":[29,75,97,201],"propose":[30,98],"to":[31,64,161,174],"avoid":[32],"manual":[33,214],"generate":[36,65,78,175],"a":[37,53,99,104,108,198,204],"training":[39,100,193],"dataset":[40,81,157,178,207],"video":[42,70,166],"making":[45],"use":[46,62,171],"automatic":[48],"cross-modal":[49],"supervision.":[50],"We":[51,116,151,170],"leverage":[52],"generation":[55,158],"transformer":[56,111],"trained":[57,219],"text":[59,168],"data":[60],"it":[63],"question-answer":[66],"pairs":[67],"from":[68,179],"transcribed":[69],"narrations.":[71],"Given":[72],"narrated":[73],"then":[76],"automatically":[77],"the":[79,88,118,123,176,180],"HowToVQA69M":[80],"with":[82,185,208],"69M":[83],"video-question-answer":[84],"triplets.":[85],"To":[86],"handle":[87],"open":[89],"vocabulary":[90],"diverse":[92],"in":[94,133],"dataset,":[96,182],"procedure":[101],"based":[102],"contrastive":[105],"loss":[106],"between":[107],"video-question":[109],"multi-modal":[110],"an":[113],"answer":[114],"transformer.":[115],"introduce":[117,202],"zero-shot":[119],"VideoQA":[120,124,156,194,206],"task":[121],"feature":[125],"probe":[126],"evaluation":[127,200],"setting":[128],"show":[130,153,189],"excellent":[131],"results,":[132],"particular":[134],"rare":[136],"answers.":[137],"Furthermore,":[138],"our":[139,155,172,224],"method":[140,173],"achieves":[141],"competitive":[142],"results":[143],"MSRVTT-QA,":[145],"ActivityNet-QA,":[146],"MSVD-QA":[147],"How2QA":[149],"also":[152],"that":[154],"approach":[159],"generalizes":[160],"another":[162],"source":[163],"web":[165],"data.":[169],"WebVidVQA3M":[177],"WebVid":[181],"i.e.,":[183],"videos":[184],"alt-text":[186],"annotations,":[187],"its":[190],"benefits":[191],"models.":[195],"Finally,":[196],"detailed":[199],"iVQA,":[203],"new":[205],"reduced":[209],"language":[210],"bias":[211],"high-quality":[213],"annotations.":[215],"Code,":[216],"datasets":[217],"models":[220],"are":[221],"available":[222],"project":[225],"webpage":[226],"(https://antoyang.github.io/just-ask.html).":[227]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}