{"id":"https://openalex.org/W3181758331","doi":"https://doi.org/10.1109/tmm.2021.3097171","title":"DualVGR: A Dual-Visual Graph Reasoning Unit for Video Question Answering","display_name":"DualVGR: A Dual-Visual Graph Reasoning Unit for Video Question Answering","publication_year":2021,"publication_date":"2021-08-24","ids":{"openalex":"https://openalex.org/W3181758331","doi":"https://doi.org/10.1109/tmm.2021.3097171","mag":"3181758331"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2021.3097171","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3097171","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2107.04768","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103068994","display_name":"Jianyu Wang","orcid":"https://orcid.org/0000-0002-8304-680X"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jianyu Wang","raw_affiliation_strings":["College of Telecommunications &amp; Information Engineering, Nanjing University of Posts, and Telecommunications, Nanjing, China","College of Telecommunications &amp"],"affiliations":[{"raw_affiliation_string":"College of Telecommunications &amp; Information Engineering, Nanjing University of Posts, and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"College of Telecommunications &amp","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007962086","display_name":"Bing\u2010Kun Bao","orcid":"https://orcid.org/0000-0001-5956-831X"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing-Kun Bao","raw_affiliation_strings":["College of Telecommunications &amp; Information Engineering, Nanjing University of Posts, and Telecommunications, Nanjing, China","College of Telecommunications &amp"],"affiliations":[{"raw_affiliation_string":"College of Telecommunications &amp; Information Engineering, Nanjing University of Posts, and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"College of Telecommunications &amp","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022636178","display_name":"Changsheng Xu","orcid":"https://orcid.org/0000-0001-8343-9665"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changsheng Xu","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103068994"],"corresponding_institution_ids":["https://openalex.org/I41198531"],"apc_list":null,"apc_paid":null,"fwci":6.8962,"has_fulltext":false,"cited_by_count":85,"citation_normalized_percentile":{"value":0.97818987,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"24","issue":null,"first_page":"3369","last_page":"3380"},"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":0.9975000023841858,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9944999814033508,"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/computer-science","display_name":"Computer science","score":0.8779779672622681},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6078082323074341},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6077977418899536},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5404428243637085},{"id":"https://openalex.org/keywords/spatial-intelligence","display_name":"Spatial intelligence","score":0.5269347429275513},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4943537712097168},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.4478602409362793},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41077014803886414},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34461766481399536},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.17477408051490784}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8779779672622681},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6078082323074341},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6077977418899536},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5404428243637085},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.5269347429275513},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4943537712097168},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.4478602409362793},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41077014803886414},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34461766481399536},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.17477408051490784},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmm.2021.3097171","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3097171","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:arXiv.org:2107.04768","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.04768","pdf_url":"https://arxiv.org/pdf/2107.04768","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2107.04768","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.04768","pdf_url":"https://arxiv.org/pdf/2107.04768","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.8100000023841858,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1498893086","display_name":null,"funder_award_id":"62036012","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1573172955","display_name":null,"funder_award_id":"BK20200037","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G4317995357","display_name":null,"funder_award_id":"61936005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7379443965","display_name":null,"funder_award_id":"61872424","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/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W1638081485","https://openalex.org/W1933349210","https://openalex.org/W1983364832","https://openalex.org/W2013822448","https://openalex.org/W2101267652","https://openalex.org/W2104657103","https://openalex.org/W2164290393","https://openalex.org/W2170653751","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2302255633","https://openalex.org/W2425121537","https://openalex.org/W2532034655","https://openalex.org/W2561715562","https://openalex.org/W2606982687","https://openalex.org/W2747623286","https://openalex.org/W2751525844","https://openalex.org/W2765716052","https://openalex.org/W2897857500","https://openalex.org/W2904452845","https://openalex.org/W2907492528","https://openalex.org/W2908791737","https://openalex.org/W2918888132","https://openalex.org/W2952620298","https://openalex.org/W2954199749","https://openalex.org/W2962779575","https://openalex.org/W2962949233","https://openalex.org/W2963150162","https://openalex.org/W2963176022","https://openalex.org/W2963224792","https://openalex.org/W2963383024","https://openalex.org/W2963579811","https://openalex.org/W2963705779","https://openalex.org/W2963738360","https://openalex.org/W2963858333","https://openalex.org/W2963954913","https://openalex.org/W2964118342","https://openalex.org/W2966683369","https://openalex.org/W2969679616","https://openalex.org/W2981591098","https://openalex.org/W2981721414","https://openalex.org/W2982139784","https://openalex.org/W2995993311","https://openalex.org/W2997344006","https://openalex.org/W2998166190","https://openalex.org/W2998631105","https://openalex.org/W3003991937","https://openalex.org/W3004349648","https://openalex.org/W3004413500","https://openalex.org/W3023700693","https://openalex.org/W3034730770","https://openalex.org/W3039075121","https://openalex.org/W3100993589","https://openalex.org/W3139478705","https://openalex.org/W4210257598","https://openalex.org/W6684090549","https://openalex.org/W6697449767","https://openalex.org/W6728881024","https://openalex.org/W6754944153","https://openalex.org/W6757902542","https://openalex.org/W6768853884","https://openalex.org/W6777188697","https://openalex.org/W6792405717"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2387743295","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W972276598","https://openalex.org/W2087343574"],"abstract_inverted_index":{"Video":[0],"question":[1],"answering":[2],"is":[3,105,129,169],"a":[4,85],"challenging":[5],"task,":[6],"which":[7,71,91,114,137],"requires":[8],"agents":[9],"to":[10,13,27,54,76],"be":[11],"able":[12],"understand":[14],"rich":[15],"video":[16,50],"contents":[17],"and":[18,65,74,143,156,159],"perform":[19,28],"spatial-temporal":[20],"reasoning.":[21,125],"However,":[22],"existing":[23],"graph-based":[24],"methods":[25],"fail":[26],"multi-step":[29],"reasoning":[30],"well,":[31],"neglecting":[32],"two":[33],"properties":[34],"of":[35,49,102,108,124],"VideoQA:":[36],"(1)":[37],"Even":[38],"for":[39],"the":[40,56,106,130,139,153],"same":[41],"video,":[42],"different":[43,47],"questions":[44],"may":[45],"require":[46],"amount":[48],"clips":[51],"or":[52],"objects":[53],"infer":[55],"answer":[57],"with":[58],"relational":[59],"reasoning;":[60],"(2)":[61],"During":[62],"reasoning,":[63],"appearance":[64,142],"motion":[66,144],"features":[67,120],"have":[68],"complicated":[69],"interdependence":[70],"are":[72],"correlated":[73],"complementary":[75],"each":[77],"other.":[78],"Based":[79],"on":[80,152,163],"these":[81],"observations,":[82],"we":[83],"propose":[84],"Dual-Visual":[86],"Graph":[87,134],"Reasoning":[88],"Unit":[89],"(DualVGR)":[90],"reasons":[92],"over":[93],"videos":[94],"in":[95],"an":[96,109],"end-to-end":[97],"fashion.":[98],"The":[99,126],"first":[100],"contribution":[101,128],"our":[103],"DualVGR":[104,147],"design":[107],"explainable":[110],"Query":[111],"Punishment":[112],"Module,":[113],"can":[115],"filter":[116],"out":[117],"irrelevant":[118],"visual":[119],"through":[121],"multiple":[122],"cycles":[123],"second":[127],"proposed":[131],"Video-based":[132],"Multi-view":[133],"Attention":[135],"Network,":[136],"captures":[138],"relations":[140],"between":[141],"features.":[145],"Our":[146,167],"network":[148],"achieves":[149],"state-of-the-art":[150],"performance":[151],"benchmark":[154,164],"MSVD-QA":[155],"SVQA":[157],"datasets,":[158],"demonstrates":[160],"competitive":[161],"results":[162],"MSRVTT-QA":[165],"datasets.":[166],"code":[168],"available":[170],"at":[171],"<uri>https://github.com/MM-IR/DualVGR-VideoQA</uri>.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":33},{"year":2023,"cited_by_count":25},{"year":2022,"cited_by_count":13}],"updated_date":"2026-04-04T08:04:53.788161","created_date":"2025-10-10T00:00:00"}