{"id":"https://openalex.org/W4383112678","doi":"https://doi.org/10.1109/tpami.2023.3292266","title":"Contrastive Video Question Answering via Video Graph Transformer","display_name":"Contrastive Video Question Answering via Video Graph Transformer","publication_year":2023,"publication_date":"2023-07-04","ids":{"openalex":"https://openalex.org/W4383112678","doi":"https://doi.org/10.1109/tpami.2023.3292266","pmid":"https://pubmed.ncbi.nlm.nih.gov/37402185"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2023.3292266","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3292266","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/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":true,"raw_author_name":"Junbin Xiao","raw_affiliation_strings":["National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010883708","display_name":"Pan Zhou","orcid":"https://orcid.org/0000-0003-3400-8943"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pan Zhou","raw_affiliation_strings":["Sea AI Lab, Singapore"],"affiliations":[{"raw_affiliation_string":"Sea AI Lab, Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006278133","display_name":"Angela Yao","orcid":"https://orcid.org/0000-0001-7418-6141"},"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":"Angela Yao","raw_affiliation_strings":["National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","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":false,"raw_author_name":"Yicong Li","raw_affiliation_strings":["National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051332325","display_name":"Richang Hong","orcid":"https://orcid.org/0000-0001-5461-3986"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Richang Hong","raw_affiliation_strings":["Hefei University of Technology, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100381753","display_name":"Shuicheng Yan","orcid":"https://orcid.org/0000-0001-8906-3777"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuicheng Yan","raw_affiliation_strings":["Sea AI Lab, Singapore"],"affiliations":[{"raw_affiliation_string":"Sea AI Lab, Singapore","institution_ids":[]}]},{"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"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5024669782"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":4.6941,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.96215608,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"45","issue":"11","first_page":"13265","last_page":"13280"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9969000220298767,"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":0.995199978351593,"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":0.7871213555335999},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7075116634368896},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.582856297492981},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5402708649635315},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.513615071773529},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40108609199523926},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3758207857608795}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7871213555335999},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7075116634368896},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.582856297492981},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5402708649635315},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.513615071773529},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40108609199523926},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3758207857608795},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2023.3292266","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3292266","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:37402185","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37402185","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":"Quality Education","score":0.6399999856948853,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1829462488","display_name":null,"funder_award_id":"61932009","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":116,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1861492603","https://openalex.org/W1933349210","https://openalex.org/W2117539524","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2425121537","https://openalex.org/W2606982687","https://openalex.org/W2745461083","https://openalex.org/W2765716052","https://openalex.org/W2795378892","https://openalex.org/W2805516822","https://openalex.org/W2883429621","https://openalex.org/W2885775891","https://openalex.org/W2886641317","https://openalex.org/W2896457183","https://openalex.org/W2904452845","https://openalex.org/W2951323451","https://openalex.org/W2953106684","https://openalex.org/W2954199749","https://openalex.org/W2962949233","https://openalex.org/W2964015378","https://openalex.org/W2965373594","https://openalex.org/W2966715458","https://openalex.org/W2968124245","https://openalex.org/W2969876226","https://openalex.org/W2970066309","https://openalex.org/W2981665364","https://openalex.org/W2981851019","https://openalex.org/W2982515679","https://openalex.org/W2984008963","https://openalex.org/W2995993311","https://openalex.org/W2997344006","https://openalex.org/W2997805943","https://openalex.org/W2998166190","https://openalex.org/W3034679267","https://openalex.org/W3034730770","https://openalex.org/W3035265375","https://openalex.org/W3035512383","https://openalex.org/W3035635319","https://openalex.org/W3094502228","https://openalex.org/W3099884329","https://openalex.org/W3109142545","https://openalex.org/W3126721948","https://openalex.org/W3134294468","https://openalex.org/W3160404663","https://openalex.org/W3166396011","https://openalex.org/W3167092180","https://openalex.org/W3168640669","https://openalex.org/W3172523222","https://openalex.org/W3173367591","https://openalex.org/W3174564426","https://openalex.org/W3175961224","https://openalex.org/W3176398504","https://openalex.org/W3177934633","https://openalex.org/W3184735396","https://openalex.org/W3189890868","https://openalex.org/W3195577433","https://openalex.org/W3197457832","https://openalex.org/W3203711169","https://openalex.org/W3203995540","https://openalex.org/W3204588463","https://openalex.org/W3206166878","https://openalex.org/W3206675006","https://openalex.org/W3211394146","https://openalex.org/W3213562172","https://openalex.org/W3213957358","https://openalex.org/W3217059257","https://openalex.org/W4200631219","https://openalex.org/W4214648142","https://openalex.org/W4224926131","https://openalex.org/W4229449886","https://openalex.org/W4283801188","https://openalex.org/W4285600797","https://openalex.org/W4287123803","https://openalex.org/W4287125738","https://openalex.org/W4297808394","https://openalex.org/W4304098887","https://openalex.org/W4312246181","https://openalex.org/W4312560592","https://openalex.org/W4312761939","https://openalex.org/W4312974690","https://openalex.org/W4313071966","https://openalex.org/W4385245566","https://openalex.org/W4385572712","https://openalex.org/W6620707391","https://openalex.org/W6631190155","https://openalex.org/W6639102338","https://openalex.org/W6726873649","https://openalex.org/W6739901393","https://openalex.org/W6751796012","https://openalex.org/W6753368589","https://openalex.org/W6755207826","https://openalex.org/W6766673545","https://openalex.org/W6766904570","https://openalex.org/W6767098714","https://openalex.org/W6767211374","https://openalex.org/W6767279747","https://openalex.org/W6768853884","https://openalex.org/W6784333009","https://openalex.org/W6787255299","https://openalex.org/W6790307280","https://openalex.org/W6791353385","https://openalex.org/W6794812656","https://openalex.org/W6796801894","https://openalex.org/W6797109355","https://openalex.org/W6797737728","https://openalex.org/W6798359198","https://openalex.org/W6798805250","https://openalex.org/W6800751262","https://openalex.org/W6803023527","https://openalex.org/W6804049574","https://openalex.org/W6804277322","https://openalex.org/W6805349323","https://openalex.org/W6810488671","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W2349927912","https://openalex.org/W4288102755","https://openalex.org/W4381058564","https://openalex.org/W2964413124"],"abstract_inverted_index":{"We":[0,150],"propose":[1],"to":[2,66],"perform":[3,67],"video":[4,35,54,63,115,133],"question":[5],"answering":[6],"(VideoQA)":[7],"in":[8],"a":[9,13,28],"Contrastive":[10],"manner":[11],"via":[12],"Video":[14],"Graph":[15],"Transformer":[16],"model":[17],"(CoVGT).":[18],"CoVGT's":[19],"uniqueness":[20],"and":[21,44,55,64,94,101,109,117,173,177],"superiority":[22,174],"are":[23,143],"three-fold:":[24],"1)":[25],"It":[26,51,87],"proposes":[27],"dynamic":[29],"graph":[30],"transformer":[31,72],"module":[32],"which":[33],"encodes":[34],"by":[36,81,90],"explicitly":[37],"capturing":[38],"the":[39,62,91,99,107,171],"visual":[40],"objects,":[41],"their":[42],"relations":[43],"dynamics,":[45],"for":[46,58,73,182],"complex":[47],"spatio-temporal":[48],"reasoning.":[49],"2)":[50],"designs":[52],"separate":[53],"text":[56,65],"transformers":[57],"contrastive":[59,96],"learning":[60],"between":[61,98],"QA,":[68],"instead":[69],"of":[70,147,164,175],"multi-modal":[71],"answer":[74],"classification.":[75],"Fine-grained":[76],"video-text":[77],"communication":[78],"is":[79,88],"done":[80],"additional":[82],"cross-modal":[83,159],"interaction":[84],"modules.":[85],"3)":[86],"optimized":[89],"joint":[92],"fully-":[93],"self-supervised":[95],"objectives":[97],"correct":[100],"incorrect":[102],"answers,":[103],"as":[104,106],"well":[105],"relevant":[108],"irrelevant":[110],"questions":[111],"respectively.":[112],"With":[113],"superior":[114],"encoding":[116],"QA":[118],"solution,":[119],"we":[120],"show":[121,152],"that":[122,142,153],"CoVGT":[123,154],"can":[124,155],"achieve":[125],"much":[126],"better":[127],"performances":[128,137],"than":[129],"previous":[130],"arts":[131],"on":[132],"reasoning":[134],"tasks.":[135],"Its":[136],"even":[138],"surpass":[139],"those":[140],"models":[141],"pretrained":[144],"with":[145,162],"millions":[146],"external":[148],"data.":[149,167],"further":[151],"also":[156],"benefit":[157],"from":[158],"pretraining,":[160],"yet":[161],"orders":[163],"magnitude":[165],"smaller":[166],"The":[168],"results":[169],"demonstrate":[170],"effectiveness":[172],"CoVGT,":[176],"additionally":[178],"reveal":[179],"its":[180],"potential":[181],"more":[183],"data-efficient":[184],"pretraining.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":24},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":5}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}