{"id":"https://openalex.org/W2993371911","doi":"https://doi.org/10.1109/tcsvt.2019.2957309","title":"Video Dialog via Multi-Grained Convolutional Self-Attention Context Multi-Modal Networks","display_name":"Video Dialog via Multi-Grained Convolutional Self-Attention Context Multi-Modal Networks","publication_year":2019,"publication_date":"2019-12-03","ids":{"openalex":"https://openalex.org/W2993371911","doi":"https://doi.org/10.1109/tcsvt.2019.2957309","mag":"2993371911"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2019.2957309","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2019.2957309","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/A5045029972","display_name":"Mao Gu","orcid":"https://orcid.org/0000-0002-3996-8399"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mao Gu","raw_affiliation_strings":["College of Computer Science, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079260216","display_name":"Zhou Zhao","orcid":"https://orcid.org/0000-0001-6121-0384"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Zhao","raw_affiliation_strings":["College of Computer Science, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051494566","display_name":"Weike Jin","orcid":"https://orcid.org/0000-0002-3132-5567"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weike Jin","raw_affiliation_strings":["College of Computer Science, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037942269","display_name":"Deng Cai","orcid":"https://orcid.org/0000-0001-9817-4065"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deng Cai","raw_affiliation_strings":["College of Computer Science, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004882141","display_name":"Fei Wu","orcid":"https://orcid.org/0000-0003-2139-8807"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Wu","raw_affiliation_strings":["College of Computer Science, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5045029972"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.6073,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.73163057,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"30","issue":"12","first_page":"4453","last_page":"4466"},"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/T10028","display_name":"Topic Modeling","score":0.9904999732971191,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.989300012588501,"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/dialog-box","display_name":"Dialog box","score":0.8806011080741882},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8780667781829834},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5263456106185913},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5248575210571289},{"id":"https://openalex.org/keywords/dialog-system","display_name":"Dialog system","score":0.5073489546775818},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4863870441913605},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4108278453350067},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.353565514087677},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.07436135411262512}],"concepts":[{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.8806011080741882},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8780667781829834},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5263456106185913},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5248575210571289},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.5073489546775818},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4863870441913605},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4108278453350067},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.353565514087677},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.07436135411262512},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2019.2957309","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2019.2957309","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1022706131","display_name":null,"funder_award_id":"61602405","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5526867466","display_name":null,"funder_award_id":"U1611461","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6605900608","display_name":null,"funder_award_id":"61751209","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7528510259","display_name":null,"funder_award_id":"61836002","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/F4320327609","display_name":"China Knowledge Centre for Engineering Sciences and Technology","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":104,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1522734439","https://openalex.org/W1596841185","https://openalex.org/W1614298861","https://openalex.org/W1686810756","https://openalex.org/W1933349210","https://openalex.org/W2016053056","https://openalex.org/W2049538695","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2123301721","https://openalex.org/W2123432324","https://openalex.org/W2136480620","https://openalex.org/W2139501017","https://openalex.org/W2142192571","https://openalex.org/W2151498684","https://openalex.org/W2154652894","https://openalex.org/W2164290393","https://openalex.org/W2250539671","https://openalex.org/W2337601653","https://openalex.org/W2412393473","https://openalex.org/W2418993857","https://openalex.org/W2558809543","https://openalex.org/W2567070169","https://openalex.org/W2597655663","https://openalex.org/W2603266952","https://openalex.org/W2606982687","https://openalex.org/W2622980782","https://openalex.org/W2732016772","https://openalex.org/W2737435850","https://openalex.org/W2741903908","https://openalex.org/W2747623286","https://openalex.org/W2750998636","https://openalex.org/W2751525844","https://openalex.org/W2765716052","https://openalex.org/W2766690867","https://openalex.org/W2768661419","https://openalex.org/W2808124938","https://openalex.org/W2810643877","https://openalex.org/W2891416139","https://openalex.org/W2892245540","https://openalex.org/W2892347792","https://openalex.org/W2918888132","https://openalex.org/W2950577311","https://openalex.org/W2952620298","https://openalex.org/W2953016680","https://openalex.org/W2955738936","https://openalex.org/W2962707484","https://openalex.org/W2962749469","https://openalex.org/W2962883855","https://openalex.org/W2962949233","https://openalex.org/W2963174729","https://openalex.org/W2963176022","https://openalex.org/W2963187678","https://openalex.org/W2963319085","https://openalex.org/W2963403868","https://openalex.org/W2963623904","https://openalex.org/W2963643760","https://openalex.org/W2963781647","https://openalex.org/W2963790827","https://openalex.org/W2963791035","https://openalex.org/W2963917086","https://openalex.org/W2963970792","https://openalex.org/W2964004697","https://openalex.org/W2964022527","https://openalex.org/W2964121744","https://openalex.org/W2964138017","https://openalex.org/W2964199361","https://openalex.org/W2964220823","https://openalex.org/W2964259363","https://openalex.org/W2966238183","https://openalex.org/W2966683369","https://openalex.org/W2972113750","https://openalex.org/W2981985547","https://openalex.org/W3022187094","https://openalex.org/W3023993913","https://openalex.org/W3099768435","https://openalex.org/W3105758476","https://openalex.org/W4235505822","https://openalex.org/W4249013746","https://openalex.org/W4298392976","https://openalex.org/W4385245566","https://openalex.org/W6623987585","https://openalex.org/W6631190155","https://openalex.org/W6636510571","https://openalex.org/W6637373629","https://openalex.org/W6678262379","https://openalex.org/W6682086655","https://openalex.org/W6682631176","https://openalex.org/W6684090549","https://openalex.org/W6703665502","https://openalex.org/W6712878229","https://openalex.org/W6715144786","https://openalex.org/W6717541995","https://openalex.org/W6730666313","https://openalex.org/W6731370813","https://openalex.org/W6735377749","https://openalex.org/W6739177970","https://openalex.org/W6739901393","https://openalex.org/W6743696045","https://openalex.org/W6748686444","https://openalex.org/W6752922659","https://openalex.org/W6754450847","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W2500779211","https://openalex.org/W48079147","https://openalex.org/W326836678","https://openalex.org/W1963944933","https://openalex.org/W2563921006","https://openalex.org/W1600043506","https://openalex.org/W2111550420","https://openalex.org/W2735573723","https://openalex.org/W3133893348","https://openalex.org/W2549666521"],"abstract_inverted_index":{"Video":[0],"dialog":[1,17,31,48,60,101,113,147],"is":[2,150],"a":[3,15,28,30,34,96,126,145],"new":[4,35,201],"and":[5,33,61,74,135,165,180,197,211],"challenging":[6],"task,":[7],"which":[8,65,108,169],"requires":[9],"an":[10],"AI":[11],"agent":[12,41],"to":[13,43,50,67,84,88,119,131,152,173,181,194],"maintain":[14],"meaningful":[16],"with":[18,47,112],"humans":[19],"in":[20,163],"natural":[21],"language":[22],"about":[23,37],"video":[24,45,62,72,89,100,110,178],"contents.":[25],"Specifically,":[26],"given":[27],"video,":[29,39],"history":[32,49,80,148],"question":[36,63,156],"the":[38,40,52,55,69,76,121,154,175,195,200,212,217],"has":[42],"combine":[44],"information":[46,73,111],"infer":[51],"answer.":[53],"However,":[54],"existing":[56],"methods":[57],"of":[58,71,79,116,199,219],"image":[59],"answering,":[64],"fail":[66],"process":[68],"complexity":[70],"establish":[75,160],"logical":[77],"dependency":[78],"contexts,":[81],"are":[82],"inappropriate":[83],"be":[85],"applied":[86],"directly":[87],"dialog.":[90],"In":[91],"this":[92],"paper,":[93],"we":[94,124,159],"propose":[95],"novel":[97],"approach":[98],"for":[99],"called":[102],"multi-grained":[103,127,141],"convolutional":[104,128],"self-attention":[105,129],"context":[106],"network,":[107],"combines":[109],"history.":[114],"Instead":[115],"using":[117],"RNN":[118],"encode":[120],"sequence":[122,142],"information,":[123],"design":[125],"mechanism":[130],"capture":[132],"both":[133],"element":[134],"segment":[136],"level":[137],"interactions":[138],"that":[139],"contain":[140],"information.":[143],"Moreover,":[144],"hierarchical":[146],"encoder":[149],"designed":[151],"learn":[153],"context-aware":[155,177],"representation.":[157],"Finally,":[158],"two":[161,190],"decoders":[162],"multiple-choice":[164],"open-ended":[166],"forms":[167],"respectively,":[168],"utilize":[170],"different":[171],"strategies":[172],"get":[174],"multi-model":[176],"representation":[179],"generate":[182],"human-like":[183],"answers.":[184],"We":[185],"evaluate":[186],"our":[187,204,220],"method":[188,205],"on":[189],"large-scale":[191],"datasets.":[192],"Due":[193],"flexibility":[196],"parallelism":[198],"attention":[202],"mechanism,":[203],"can":[206],"achieve":[207],"higher":[208],"time":[209],"efficiency,":[210],"extensive":[213],"experiments":[214],"also":[215],"show":[216],"effectiveness":[218],"method.":[221]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}