{"id":"https://openalex.org/W7123361299","doi":"https://doi.org/10.1109/tmm.2026.3651115","title":"Admitting Ignorance Helps the Video Question Answering Models to Answer","display_name":"Admitting Ignorance Helps the Video Question Answering Models to Answer","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7123361299","doi":"https://doi.org/10.1109/tmm.2026.3651115"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2026.3651115","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3651115","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Multimedia","raw_type":"journal-article"},"type":"article","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/A5033332392","display_name":"H. Li","orcid":null},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Haopeng Li","raw_affiliation_strings":["School of Computing and Information Systems, University of Melbourne, Melbourne, VIC, Australia"],"raw_orcid":"https://orcid.org/0000-0001-8175-5381","affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, University of Melbourne, Melbourne, VIC, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017469047","display_name":"Tom Drummond","orcid":"https://orcid.org/0000-0001-8204-5904"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tom Drummond","raw_affiliation_strings":["School of Computing and Information Systems, University of Melbourne, Melbourne, VIC, Australia"],"raw_orcid":"https://orcid.org/0000-0001-8204-5904","affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, University of Melbourne, Melbourne, VIC, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mingming Gong","orcid":"https://orcid.org/0000-0001-7147-5589"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mingming Gong","raw_affiliation_strings":["School of Mathematics and Statistics, University of Melbourne, Melbourne, VIC, Australia"],"raw_orcid":"https://orcid.org/0000-0001-7147-5589","affiliations":[{"raw_affiliation_string":"School of Mathematics and Statistics, University of Melbourne, Melbourne, VIC, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mohammed Bennamoun","orcid":"https://orcid.org/0000-0002-6603-3257"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mohammed Bennamoun","raw_affiliation_strings":["School of Physics, Maths and Computing, The University of Western Australia, Perth, WA, Australia"],"raw_orcid":"https://orcid.org/0000-0002-6603-3257","affiliations":[{"raw_affiliation_string":"School of Physics, Maths and Computing, The University of Western Australia, Perth, WA, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"last","author":{"id":null,"display_name":"Qiuhong Ke","orcid":"https://orcid.org/0000-0001-9998-3614"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Qiuhong Ke","raw_affiliation_strings":["Department of Data Science &amp; AI, Monash University, Melbourne, VIC, Australia"],"raw_orcid":"https://orcid.org/0000-0001-9998-3614","affiliations":[{"raw_affiliation_string":"Department of Data Science &amp; AI, Monash University, Melbourne, VIC, Australia","institution_ids":["https://openalex.org/I56590836"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.8969,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.94589299,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"28","issue":null,"first_page":"3300","last_page":"3312"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.984000027179718,"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":0.984000027179718,"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/T10028","display_name":"Topic Modeling","score":0.005499999970197678,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.002099999925121665,"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/spurious-relationship","display_name":"Spurious relationship","score":0.8532000184059143},{"id":"https://openalex.org/keywords/ignorance","display_name":"Ignorance","score":0.7893999814987183},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7450000047683716},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6194000244140625},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5245000123977661}],"concepts":[{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.8532000184059143},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8291000127792358},{"id":"https://openalex.org/C2778732403","wikidata":"https://www.wikidata.org/wiki/Q815577","display_name":"Ignorance","level":2,"score":0.7893999814987183},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7450000047683716},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6194000244140625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.551800012588501},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5245000123977661},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.44209998846054077},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.40799999237060547},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35249999165534973},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3310999870300293},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32179999351501465},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3215000033378601},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2809000015258789},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2689000070095062}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmm.2026.3651115","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3651115","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Multimedia","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:publications/8c3d8cb9-f4fa-44a6-ba12-e311a00f4f3b","is_oa":false,"landing_page_url":"https://admin.research-repository.uwa.edu.au/en/publications/8c3d8cb9-f4fa-44a6-ba12-e311a00f4f3b","pdf_url":null,"source":{"id":"https://openalex.org/S4306402523","display_name":"UWA Profiles and Research Repository (University of Western Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177877127","host_organization_name":"The University of Western Australia","host_organization_lineage":["https://openalex.org/I177877127"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Li, H, Drummond, T, Gong, M, Bennamoun, M & Ke, Q 2026, 'Admitting Ignorance Helps the Video Question Answering Models to Answer', IEEE Transactions on Multimedia, vol. 28, pp. 3300-3312. https://doi.org/10.1109/TMM.2026.3651115","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320315885","display_name":"Australian Government","ror":"https://ror.org/0314h5y94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Significant":[0],"progress":[1],"has":[2],"been":[3],"made":[4],"in":[5,57,86,117,138],"the":[6,21,39,66,88,130,169],"field":[7],"of":[8,23,136,171],"video":[9,69],"question":[10],"answering":[11],"(VideoQA)":[12],"thanks":[13],"to":[14,92,132,155],"deep":[15],"learning":[16],"and":[17,27,43,62,70,124,126,142],"large-scale":[18],"pretraining.":[19],"Despite":[20],"presence":[22],"sophisticated":[24],"model":[25,89,131,151],"structures":[26],"powerful":[28],"video-text":[29],"foundation":[30],"models,":[31],"most":[32],"existing":[33],"methods":[34],"focus":[35],"solely":[36,106],"on":[37,108],"maximizing":[38],"correlation":[40],"between":[41,60,68],"answers":[42],"video-question":[44],"pairs":[45],"during":[46],"training.":[47],"We":[48,112],"argue":[49],"that":[50,163],"these":[51,77],"models":[52,173],"often":[53],"establish":[54],"shortcuts,":[55],"resulting":[56],"spurious":[58,78],"correlations":[59],"questions":[61],"answers,":[63],"especially":[64],"when":[65,96],"alignment":[67],"text":[71],"data":[72],"is":[73,90],"suboptimal.":[74],"To":[75],"address":[76],"correlations,":[79],"we":[80,147],"propose":[81],"a":[82,149],"novel":[83],"training":[84],"framework":[85,154,165],"which":[87],"compelled":[91],"acknowledge":[93],"its":[94,134,157],"ignorance":[95],"presented":[97],"with":[98,174],"an":[99],"intervened":[100],"question,":[101],"rather":[102],"than":[103],"making":[104],"guesses":[105],"based":[107],"superficial":[109],"question-answer":[110],"correlations.":[111],"introduce":[113],"methodologies":[114],"for":[115,129],"intervening":[116],"questions,":[118],"utilizing":[119],"techniques":[120],"such":[121],"as":[122],"displacement":[123],"perturbation,":[125],"design":[127],"frameworks":[128],"admit":[133],"lack":[135],"knowledge":[137],"both":[139],"multi-choice":[140],"VideoQA":[141,172],"open-ended":[143],"settings.":[144],"In":[145],"practice,":[146],"integrate":[148],"state-of-the-art":[150],"into":[152],"our":[153,164],"validate":[156],"effectiveness.":[158],"The":[159],"results":[160],"clearly":[161],"demonstrate":[162],"can":[166],"significantly":[167],"enhance":[168],"performance":[170],"minimal":[175],"structural":[176],"modifications.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-25T06:01:18.069262","created_date":"2026-01-14T00:00:00"}
