{"id":"https://openalex.org/W7137892337","doi":"https://doi.org/10.1609/aaai.v40i8.37567","title":"VividListener: Expressive and Controllable Listener Dynamics Modeling for Multi-Modal Responsive Interaction","display_name":"VividListener: Expressive and Controllable Listener Dynamics Modeling for Multi-Modal Responsive Interaction","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137892337","doi":"https://doi.org/10.1609/aaai.v40i8.37567"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i8.37567","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i8.37567","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37567/41529","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37567/41529","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129684492","display_name":"Shiying Li","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiying Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026841385","display_name":"Xingqun Qi","orcid":"https://orcid.org/0000-0002-9772-5707"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xingqun Qi","raw_affiliation_strings":["Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113034289","display_name":"Bingkun Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bingkun Yang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129650964","display_name":"Weile Chen","orcid":null},"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":"Weile Chen","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112608678","display_name":"Zezhao Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zezhao Tian","raw_affiliation_strings":["Beijing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084960489","display_name":"Muyi Sun","orcid":"https://orcid.org/0000-0001-9506-7643"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Muyi Sun","raw_affiliation_strings":["Beijing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121612467","display_name":"Qifeng Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Qifeng Liu","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129702089","display_name":"Man Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Man Zhang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129647973","display_name":"Zhenan Sun","orcid":null},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenan Sun","raw_affiliation_strings":["Institute of automation, Chinese academy of science, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of automation, Chinese academy of science, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"8","first_page":"6396","last_page":"6404"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.2696000039577484,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.2696000039577484,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.24580000340938568,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.2232999950647354,"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/dynamics","display_name":"Dynamics (music)","score":0.7459999918937683},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.625},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5672000050544739},{"id":"https://openalex.org/keywords/avatar","display_name":"Avatar","score":0.5490000247955322},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5428000092506409},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.4918000102043152},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.426800012588501},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.37689998745918274}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7591999769210815},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.7459999918937683},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.625},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5672000050544739},{"id":"https://openalex.org/C2777365542","wikidata":"https://www.wikidata.org/wiki/Q83090","display_name":"Avatar","level":2,"score":0.5490000247955322},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5428000092506409},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5375999808311462},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.4918000102043152},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.426800012588501},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39739999175071716},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.37689998745918274},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.367900013923645},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3197000026702881},{"id":"https://openalex.org/C2780226923","wikidata":"https://www.wikidata.org/wiki/Q929848","display_name":"Movement (music)","level":2,"score":0.3176000118255615},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.2867000102996826},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C2992801459","wikidata":"https://www.wikidata.org/wiki/Q223642","display_name":"Interpersonal interaction","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C195818886","wikidata":"https://www.wikidata.org/wiki/Q5421724","display_name":"Expressive power","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i8.37567","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i8.37567","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37567/41529","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i8.37567","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i8.37567","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37567/41529","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137892337.pdf","grobid_xml":"https://content.openalex.org/works/W7137892337.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Generating":[0],"responsive":[1,92],"listener":[2,31,108,145,185,207],"head":[3,59],"dynamics":[4,60,109,146],"with":[5,151,160,175],"nuanced":[6],"emotions":[7],"and":[8,41,53,61,106,125,154,184,205],"expressive":[9,158,204],"reactions":[10],"is":[11],"crucial":[12],"for":[13,90,119,171],"dialogue":[14,69],"modeling":[15],"in":[16,45],"various":[17],"virtual":[18],"avatar":[19],"animations.":[20],"Previous":[21],"studies":[22],"mainly":[23],"focus":[24],"on":[25,191],"the":[26,35,49,66,130,138,144,166],"direct":[27],"short-term":[28],"production":[29],"of":[30,51,68,80],"behavior.":[32,162],"They":[33],"overlook":[34],"fine-grained":[36,62,148],"control":[37],"over":[38],"motion":[39,186],"variations":[40],"emotional":[42],"intensity,":[43],"especially":[44],"long-sequence":[46],"modeling.":[47,70,110],"Moreover,":[48],"lack":[50],"long-term":[52],"large-scale":[54,77],"paired":[55],"speaker-listener":[56],"corpora":[57],"incorporating":[58],"multi-modality":[63],"annotations":[64],"limits":[65],"application":[67],"Therefore,":[71],"we":[72,97,128,164],"first":[73],"newly":[74,193],"collect":[75],"a":[76,100],"multi-turn":[78],"dataset":[79,196],"3D":[81],"dyadic":[82],"conversation":[83],"containing":[84],"more":[85],"than":[86],"1.4M":[87],"valid":[88],"frames":[89],"multi-modal":[91,114,139,176],"interaction,":[93],"dubbed":[94],"ListenerX.":[95],"Additionally,":[96],"propose":[98,165],"VividListener,":[99],"novel":[101],"framework":[102,112],"enabling":[103],"fine-grained,":[104],"expressive,":[105],"controllable":[107,206],"This":[111],"leverages":[113],"conditions":[115],"as":[116],"guiding":[117],"principles":[118],"fostering":[120],"coherent":[121],"interactions":[122],"between":[123],"speakers":[124],"listeners.":[126],"Specifically,":[127],"design":[129],"Responsive":[131],"Interaction":[132],"Module":[133],"(RIM)":[134],"to":[135,180],"adaptively":[136],"represent":[137],"interactive":[140],"embeddings.":[141],"RIM":[142],"ensures":[143],"achieve":[147],"semantic":[149],"coordination":[150],"textual":[152],"descriptions":[153,183],"adjustments,":[155],"while":[156],"preserving":[157],"reaction":[159],"speaker":[161],"Meanwhile,":[163],"Emotional":[167],"Intensity":[168],"Tags":[169],"(EIT)":[170],"emotion":[172],"intensity":[173],"editing":[174],"information":[177],"integration,":[178],"applying":[179],"both":[181],"text":[182],"amplitude.":[187],"Extensive":[188],"experiments":[189],"conducted":[190],"our":[192],"collected":[194],"ListenerX":[195],"demonstrate":[197],"that":[198],"VividListener":[199],"achieves":[200],"state-of-the-art":[201],"performance,":[202],"realizing":[203],"dynamics.":[208]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}