{"id":"https://openalex.org/W4385695880","doi":"https://doi.org/10.1109/tpami.2023.3303451","title":"Transformer-Empowered Invariant Grounding for Video Question Answering","display_name":"Transformer-Empowered Invariant Grounding for Video Question Answering","publication_year":2023,"publication_date":"2023-08-09","ids":{"openalex":"https://openalex.org/W4385695880","doi":"https://doi.org/10.1109/tpami.2023.3303451","pmid":"https://pubmed.ncbi.nlm.nih.gov/37556333"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2023.3303451","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3303451","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101762861","display_name":"Yicong Li","orcid":"https://orcid.org/0000-0002-5659-793X"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Yicong Li","raw_affiliation_strings":["National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-5659-793X","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100389037","display_name":"Xiang Wang","orcid":"https://orcid.org/0000-0002-6148-6329"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Wang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China","University of Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0000-0002-6148-6329","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024669782","display_name":"Junbin Xiao","orcid":"https://orcid.org/0000-0001-5573-6195"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Junbin Xiao","raw_affiliation_strings":["National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-5573-6195","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101397422","display_name":"Wei Ji","orcid":"https://orcid.org/0000-0002-8106-9768"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wei Ji","raw_affiliation_strings":["National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-8106-9768","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089404640","display_name":"Tat\u2010Seng Chua","orcid":"https://orcid.org/0000-0001-6097-7807"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tat-Seng Chua","raw_affiliation_strings":["National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-6097-7807","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101762861"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":0.928,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.76919868,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"47","issue":"11","first_page":"9510","last_page":"9522"},"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":0.9962000250816345,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9940999746322632,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.7626062631607056},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7498553991317749},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6866046190261841},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6281312108039856},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.5897011160850525},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.5880475044250488},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5482909083366394},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48847877979278564},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.41870805621147156},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3561321496963501},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10982751846313477}],"concepts":[{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.7626062631607056},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7498553991317749},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6866046190261841},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6281312108039856},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.5897011160850525},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.5880475044250488},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5482909083366394},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48847877979278564},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.41870805621147156},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3561321496963501},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10982751846313477},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"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/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2023.3303451","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3303451","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:37556333","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37556333","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}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.47999998927116394}],"awards":[{"id":"https://openalex.org/G6730572696","display_name":null,"funder_award_id":"9227010114","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W2031342017","https://openalex.org/W2064675550","https://openalex.org/W2143891888","https://openalex.org/W2765716052","https://openalex.org/W2896457183","https://openalex.org/W2904452845","https://openalex.org/W2954199749","https://openalex.org/W2962735233","https://openalex.org/W2962949233","https://openalex.org/W2963693848","https://openalex.org/W2963798744","https://openalex.org/W2963800628","https://openalex.org/W2964072591","https://openalex.org/W2964306924","https://openalex.org/W2964935470","https://openalex.org/W2970379526","https://openalex.org/W2997344006","https://openalex.org/W2997805943","https://openalex.org/W2998166190","https://openalex.org/W3023993913","https://openalex.org/W3034730770","https://openalex.org/W3035517717","https://openalex.org/W3096609285","https://openalex.org/W3109142545","https://openalex.org/W3159619744","https://openalex.org/W3167092180","https://openalex.org/W3171516518","https://openalex.org/W3175961224","https://openalex.org/W3181758331","https://openalex.org/W3189890868","https://openalex.org/W3206675006","https://openalex.org/W4200631219","https://openalex.org/W4214519690","https://openalex.org/W4285600797","https://openalex.org/W4304098887","https://openalex.org/W4312246181","https://openalex.org/W4312692509","https://openalex.org/W4312761939","https://openalex.org/W4312974690","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W3113091479","https://openalex.org/W2162899405","https://openalex.org/W941090075","https://openalex.org/W17155033","https://openalex.org/W2044987316","https://openalex.org/W3134374554","https://openalex.org/W4381058564","https://openalex.org/W3003945460","https://openalex.org/W2964413124","https://openalex.org/W4288267738"],"abstract_inverted_index":{"Video":[0],"Question":[1],"Answering":[2],"(VideoQA)":[3],"is":[4,16,193],"the":[5,17,20,30,36,47,58,66,95,109,120,123,137,161,188],"task":[6],"of":[7,19,56,61,126,139,155,163,180],"answering":[8,121],"questions":[9],"about":[10],"a":[11,76,83,145,152,167],"video.":[12],"At":[13],"its":[14],"core":[15],"understanding":[18],"alignments":[21],"between":[22,50],"video":[23],"scenes":[24,52],"and":[25,53,81,184],"question":[26],"semantics":[27],"to":[28,45,93,118],"yield":[29],"answer.":[31],"In":[32,71],"leading":[33,113,189],"VideoQA":[34,80,91,114,150],"models,":[35],"typical":[37],"learning":[38,85],"objective,":[39],"empirical":[40],"risk":[41],"minimization":[42],"(ERM),":[43],"tends":[44],"over-exploit":[46],"spurious":[48,127],"correlations":[49],"question-irrelevant":[51],"answers,":[54],"instead":[55],"inspecting":[57],"causal":[59,77,99],"effect":[60],"question-critical":[62,96],"scenes,":[63],"which":[64,129],"undermines":[65],"prediction":[67],"with":[68,101],"unreliable":[69],"reasoning.":[70],"this":[72,140],"work,":[73],"we":[74,142],"take":[75],"look":[78],"at":[79,195],"propose":[82],"modal-agnostic":[84],"framework,":[86,141],"named":[87],"Invariant":[88,147],"Grounding":[89,148],"for":[90,149],"(IGV),":[92],"ground":[94],"scene,":[97],"whose":[98],"relations":[100],"answers":[102],"are":[103,116],"invariant":[104,164],"across":[105],"different":[106],"interventions":[107],"on":[108,171],"complement.":[110],"With":[111],"IGV,":[112],"models":[115],"forced":[117],"shield":[119],"from":[122],"negative":[124],"influence":[125],"correlations,":[128],"significantly":[130],"improves":[131],"their":[132],"reasoning":[133],"ability.":[134],"To":[135],"unleash":[136],"potential":[138],"further":[143],"provide":[144],"Transformer-Empowered":[146],"(TIGV),":[151],"substantial":[153],"instantiation":[154],"IGV":[156],"framework":[157],"that":[158],"naturally":[159],"integrates":[160],"idea":[162],"grounding":[165],"into":[166],"transformer-style":[168],"backbone.":[169],"Experiments":[170],"four":[172],"benchmark":[173],"datasets":[174],"validate":[175],"our":[176],"design":[177],"in":[178],"terms":[179],"accuracy,":[181],"visual":[182],"explainability,":[183],"generalization":[185],"ability":[186],"over":[187],"baselines.":[190],"Our":[191],"code":[192],"available":[194],"https://github.com/yl3800/TIGV.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}