{"id":"https://openalex.org/W3119243803","doi":"https://doi.org/10.1109/tcsvt.2020.3048440","title":"Action-Centric Relation Transformer Network for Video Question Answering","display_name":"Action-Centric Relation Transformer Network for Video Question Answering","publication_year":2020,"publication_date":"2020-12-31","ids":{"openalex":"https://openalex.org/W3119243803","doi":"https://doi.org/10.1109/tcsvt.2020.3048440","mag":"3119243803"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2020.3048440","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2020.3048440","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","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/A5100622779","display_name":"Jipeng Zhang","orcid":"https://orcid.org/0000-0002-3269-6992"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jipeng Zhang","raw_affiliation_strings":["Center for Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"Center for Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072350518","display_name":"Jie Shao","orcid":"https://orcid.org/0000-0003-2615-1555"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Shao","raw_affiliation_strings":["Center for Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","Sichuan Artificial Intelligence Research Institute, Yibin, China"],"affiliations":[{"raw_affiliation_string":"Center for Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"Sichuan Artificial Intelligence Research Institute, Yibin, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077167782","display_name":"Rui Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Rui Cao","raw_affiliation_strings":["School of Information Systems, Singapore Management University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Information Systems, Singapore Management University, Singapore","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066645546","display_name":"Lianli Gao","orcid":"https://orcid.org/0000-0002-2522-6394"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianli Gao","raw_affiliation_strings":["Center for Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"Center for Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009074046","display_name":"Xing Xu","orcid":"https://orcid.org/0000-0001-5685-3123"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Xu","raw_affiliation_strings":["Center for Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"Center for Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052993469","display_name":"Heng Tao Shen","orcid":"https://orcid.org/0000-0002-2999-2088"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Tao Shen","raw_affiliation_strings":["Center for Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","Sichuan Artificial Intelligence Research Institute, Yibin, China"],"affiliations":[{"raw_affiliation_string":"Center for Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"Sichuan Artificial Intelligence Research Institute, Yibin, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100622779"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":2.4533,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.911575,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"32","issue":"1","first_page":"63","last_page":"74"},"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":0.9987999796867371,"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":0.9943000078201294,"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":0.7784286737442017},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6109368205070496},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5671494007110596},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5530505776405334},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5039553046226501},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.44857701659202576},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.4482460618019104},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.44168877601623535},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.427295446395874},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3443661332130432},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.343122661113739},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.06693047285079956},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06630069017410278}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7784286737442017},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6109368205070496},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5671494007110596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5530505776405334},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5039553046226501},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.44857701659202576},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.4482460618019104},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.44168877601623535},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.427295446395874},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3443661332130432},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.343122661113739},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.06693047285079956},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06630069017410278},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcsvt.2020.3048440","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2020.3048440","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"},{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-7023","is_oa":false,"landing_page_url":"https://ink.library.smu.edu.sg/cgi/viewcontent.cgi?article=7023&amp;amp;context=sis_research","pdf_url":null,"source":{"id":"https://openalex.org/S4377196871","display_name":"Institutional Knowledge (InK) - Institutional Knowledge at Singapore Management University (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.1109/TCSVT.2020.3048440","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3950325575","display_name":null,"funder_award_id":"2019YFG0535","funder_id":"https://openalex.org/F4320333335","funder_display_name":"Sichuan Province Science and Technology Support Program"},{"id":"https://openalex.org/G4253300795","display_name":null,"funder_award_id":"61832001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4255492492","display_name":null,"funder_award_id":"61672133","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"},{"id":"https://openalex.org/F4320333335","display_name":"Sichuan Province Science and Technology Support Program","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2471143248","https://openalex.org/W2486996822","https://openalex.org/W2507009361","https://openalex.org/W2560730294","https://openalex.org/W2561715562","https://openalex.org/W2565656701","https://openalex.org/W2603266952","https://openalex.org/W2606982687","https://openalex.org/W2745461083","https://openalex.org/W2765716052","https://openalex.org/W2808181286","https://openalex.org/W2888003147","https://openalex.org/W2904108267","https://openalex.org/W2904291752","https://openalex.org/W2904452845","https://openalex.org/W2914134937","https://openalex.org/W2920582597","https://openalex.org/W2921873695","https://openalex.org/W2954199749","https://openalex.org/W2962677524","https://openalex.org/W2962861647","https://openalex.org/W2962910007","https://openalex.org/W2962949233","https://openalex.org/W2962958773","https://openalex.org/W2963541336","https://openalex.org/W2963890755","https://openalex.org/W2963954913","https://openalex.org/W2964220823","https://openalex.org/W2974161034","https://openalex.org/W2981582341","https://openalex.org/W2981985547","https://openalex.org/W2982139784","https://openalex.org/W2983918066","https://openalex.org/W2997344006","https://openalex.org/W2997429269","https://openalex.org/W2997805943","https://openalex.org/W2998166190","https://openalex.org/W3003991937","https://openalex.org/W3019023591","https://openalex.org/W3034730770","https://openalex.org/W3035218869","https://openalex.org/W3035497460","https://openalex.org/W3037773948","https://openalex.org/W6637373629","https://openalex.org/W6682086655","https://openalex.org/W6722654596","https://openalex.org/W6738893770","https://openalex.org/W6739901393","https://openalex.org/W6752263633"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W4386541577"],"abstract_inverted_index":{"Video":[0],"question":[1],"answering":[2],"(VideoQA)":[3],"has":[4,145],"emerged":[5],"as":[6],"a":[7,124,157],"popular":[8,164],"research":[9],"topic":[10],"in":[11,52,68,73,167],"recent":[12],"years.":[13],"Enormous":[14],"efforts":[15],"have":[16],"been":[17],"devoted":[18],"to":[19,132],"developing":[20],"more":[21],"effective":[22],"fusion":[23],"strategies":[24],"and":[25,109,122],"better":[26,149],"intra-modal":[27],"feature":[28,126],"preparation.":[29],"To":[30],"explore":[31],"these":[32,97],"issues":[33],"further,":[34],"we":[35,99],"identify":[36],"two":[37,111],"key":[38],"problems.":[39],"(1)":[40,114],"Current":[41],"works":[42],"take":[43],"almost":[44],"no":[45],"account":[46],"of":[47,50,65],"introducing":[48],"action":[49,64,90,119],"interest":[51,66],"video":[53],"representation.":[54],"Additionally,":[55],"there":[56],"exists":[57],"insufficient":[58],"labeling":[59],"data":[60],"on":[61,96,163],"where":[62],"the":[63,118,134,143,151],"is":[67],"many":[69],"datasets.":[70],"However,":[71],"questions":[72],"VideoQA":[74,108,168],"are":[75],"usually":[76],"action-centric.":[77],"(2)":[78,147],"Frame-to-frame":[79],"relations,":[80],"which":[81],"can":[82],"provide":[83],"useful":[84],"temporal":[85,154],"attributes":[86],"(e.g.,":[87],"state":[88],"transition,":[89],"counting),":[91],"lack":[92],"relevant":[93],"research.":[94],"Based":[95],"observations,":[98],"propose":[100],"an":[101],"action-centric":[102],"relation":[103,158],"transformer":[104,159],"network":[105,160],"(ACRTransformer)":[106],"for":[107],"make":[110],"significant":[112],"improvements.":[113],"We":[115,148],"explicitly":[116],"consider":[117],"recognition":[120],"problem":[121],"present":[123],"visual":[125],"encoding":[127,130],"technique,":[128],"action-based":[129],"(ABE),":[131],"emphasize":[133],"frames":[135,155],"with":[136],"high":[137],"actionness":[138],"probabilities":[139],"(the":[140],"probability":[141],"that":[142],"frame":[144],"actions).":[146],"exploit":[150],"interplays":[152],"between":[153],"using":[156],"(RTransformer).":[161],"Experiments":[162],"benchmark":[165],"datasets":[166],"clearly":[169],"establish":[170],"our":[171],"superiority":[172],"over":[173],"previous":[174],"state-of-the-art":[175],"models.":[176],"Code":[177],"could":[178],"be":[179],"found":[180],"at":[181],"<uri":[182],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[183],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/op-multimodal/ACRTransformer</uri>":[184],".":[185]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
