{"id":"https://openalex.org/W4409883279","doi":"https://doi.org/10.1109/tpami.2025.3562651","title":"Interactive Conversational Head Generation","display_name":"Interactive Conversational Head Generation","publication_year":2025,"publication_date":"2025-04-28","ids":{"openalex":"https://openalex.org/W4409883279","doi":"https://doi.org/10.1109/tpami.2025.3562651","pmid":"https://pubmed.ncbi.nlm.nih.gov/40293876"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3562651","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3562651","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/A5006824435","display_name":"Mohan Zhou","orcid":"https://orcid.org/0000-0003-3250-4978"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210122117","display_name":"Harbin Foresty Machinery Institute","ror":"https://ror.org/02mj3be11","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210122117","https://openalex.org/I4210128615","https://openalex.org/I4210134523"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mohan Zhou","raw_affiliation_strings":["Machine Intelligence and Translation Lab, Faculty of Computing, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Machine Intelligence and Translation Lab, Faculty of Computing, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4210122117"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054533256","display_name":"Yalong Bai","orcid":"https://orcid.org/0000-0002-8416-9027"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yalong Bai","raw_affiliation_strings":["JD Explore Academy, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD Explore Academy, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wei Zhang","orcid":"https://orcid.org/0000-0002-1492-8286"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["JD Explore Academy, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD Explore Academy, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088760097","display_name":"Ting Yao","orcid":"https://orcid.org/0000-0001-7587-101X"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Yao","raw_affiliation_strings":["JD Explore Academy, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD Explore Academy, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101661008","display_name":"Tiejun Zhao","orcid":"https://orcid.org/0000-0003-4659-4935"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210122117","display_name":"Harbin Foresty Machinery Institute","ror":"https://ror.org/02mj3be11","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210122117","https://openalex.org/I4210128615","https://openalex.org/I4210134523"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiejun Zhao","raw_affiliation_strings":["Machine Intelligence and Translation Lab, Faculty of Computing, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Machine Intelligence and Translation Lab, Faculty of Computing, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4210122117"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5006824435"],"corresponding_institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4210122117"],"apc_list":null,"apc_paid":null,"fwci":2.3568,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.88817799,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"47","issue":"8","first_page":"6673","last_page":"6686"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9965000152587891,"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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9965000152587891,"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/T12128","display_name":"AI in Service Interactions","score":0.974399983882904,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.9550999999046326,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7034275531768799},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.5459621548652649},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5316282510757446},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4168003797531128},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3862585127353668},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3753799498081207},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3399532437324524}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7034275531768799},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.5459621548652649},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5316282510757446},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4168003797531128},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3862585127353668},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3753799498081207},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3399532437324524},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003142","descriptor_name":"Communication","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003142","descriptor_name":"Communication","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003142","descriptor_name":"Communication","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D005260","descriptor_name":"Female","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005260","descriptor_name":"Female","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005260","descriptor_name":"Female","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006257","descriptor_name":"Head","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D006257","descriptor_name":"Head","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D006257","descriptor_name":"Head","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008297","descriptor_name":"Male","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008297","descriptor_name":"Male","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008297","descriptor_name":"Male","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3562651","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3562651","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:40293876","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40293876","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":[],"awards":[{"id":"https://openalex.org/G1912045422","display_name":null,"funder_award_id":"62376075","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2672658670","display_name":null,"funder_award_id":"HIT.DZJJ.2023076","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W1488075209","https://openalex.org/W1511502075","https://openalex.org/W1885185971","https://openalex.org/W1971199318","https://openalex.org/W2025567128","https://openalex.org/W2074525651","https://openalex.org/W2082669741","https://openalex.org/W2097615438","https://openalex.org/W2115114490","https://openalex.org/W2122515591","https://openalex.org/W2132555391","https://openalex.org/W2137374537","https://openalex.org/W2145868338","https://openalex.org/W2161813860","https://openalex.org/W2237250383","https://openalex.org/W2604379605","https://openalex.org/W2804621595","https://openalex.org/W2806833697","https://openalex.org/W2808631503","https://openalex.org/W2889050557","https://openalex.org/W2896628364","https://openalex.org/W2962701817","https://openalex.org/W2962795401","https://openalex.org/W2963308316","https://openalex.org/W2963726353","https://openalex.org/W2963917969","https://openalex.org/W2964449965","https://openalex.org/W2973673960","https://openalex.org/W3081492798","https://openalex.org/W3099284785","https://openalex.org/W3107561632","https://openalex.org/W3154411171","https://openalex.org/W3154807520","https://openalex.org/W3158777120","https://openalex.org/W3177150198","https://openalex.org/W3178147929","https://openalex.org/W3186700381","https://openalex.org/W3195529437","https://openalex.org/W3204680331","https://openalex.org/W3211147706","https://openalex.org/W4225760288","https://openalex.org/W4229699119","https://openalex.org/W4230100653","https://openalex.org/W4245458154","https://openalex.org/W4312990833","https://openalex.org/W4323529965","https://openalex.org/W4386075487","https://openalex.org/W4404738447","https://openalex.org/W4409369524","https://openalex.org/W6600381294","https://openalex.org/W6629166835","https://openalex.org/W6630412731","https://openalex.org/W6765779288","https://openalex.org/W6768091732","https://openalex.org/W6770108805","https://openalex.org/W6811548253","https://openalex.org/W6870782382"],"related_works":["https://openalex.org/W3097502728","https://openalex.org/W2113206756","https://openalex.org/W3009949491","https://openalex.org/W1927475415","https://openalex.org/W2613352840","https://openalex.org/W2379547295","https://openalex.org/W2180861836","https://openalex.org/W2079398652","https://openalex.org/W4388166999","https://openalex.org/W2724652190"],"abstract_inverted_index":{"We":[0],"introduce":[1],"a":[2,12,16,65],"new":[3],"conversation":[4,69],"head":[5,56,98,135,150,163],"generation":[6,57,99,136,151,164],"benchmark":[7],"for":[8,38,68,93,107],"synthesizing":[9,108],"behaviors":[10],"of":[11,76,157],"single":[13],"interlocutor":[14],"in":[15,28,110,170],"face-to-face":[17,130],"conversation.":[18,211],"The":[19],"capability":[20],"to":[21,63,73,88,141,154,165,183,207],"automatically":[22],"synthesize":[23],"interlocutors":[24,109],"which":[25],"can":[26,202],"participate":[27],"long":[29],"and":[30,35,46,78,96,105,117,160,198],"multi-turn":[31,111],"conversations":[32],"is":[33],"vital":[34],"offer":[36],"benefits":[37],"various":[39],"applications,":[40],"including":[41],"digital":[42,66],"humans,":[43],"virtual":[44],"agents,":[45],"social":[47],"robots.":[48],"While":[49],"existing":[50],"research":[51],"primarily":[52],"focuses":[53],"on":[54,115],"talking":[55,95,149],"(one-way":[58],"interaction),":[59],"hindering":[60],"the":[61,74,102,125,129,142,167,175,184,209],"ability":[62,169],"create":[64],"human":[67],"(two-way)":[70],"interaction":[71,79,126],"due":[72],"absence":[75],"listening":[77,97,134],"parts.":[80],"In":[81],"this":[82,90],"work,":[83],"we":[84,119,177],"construct":[85],"two":[86],"datasets":[87],"address":[89],"issue,":[91],"\"ViCo\"":[92],"independent":[94],"tasks":[100,123],"at":[101],"sentence":[103],"level,":[104],"\"ViCo-X\",":[106],"conversational":[112,162],"scenarios.":[113],"Based":[114],"ViCo":[116],"ViCo-X,":[118],"define":[120],"three":[121,185],"novel":[122],"targeting":[124],"modeling":[127],"during":[128],"conversation:":[131],"1)":[132],"responsive":[133,197],"making":[137],"listeners":[138],"respond":[139],"actively":[140],"speaker":[143],"with":[144,174,204],"non-verbal":[145],"signals,":[146],"2)":[147],"expressive":[148],"guiding":[152],"speakers":[153],"be":[155],"aware":[156],"listeners'":[158],"behaviors,":[159],"3)":[161],"integrate":[166],"talking/listening":[168],"one":[171],"interlocutor.":[172],"Along":[173],"datasets,":[176],"also":[178],"propose":[179],"corresponding":[180],"baseline":[181,193],"solutions":[182],"aforementioned":[186],"tasks.":[187],"Experimental":[188],"results":[189],"show":[190],"that":[191,201],"our":[192],"method":[194],"could":[195],"generate":[196],"vivid":[199],"agents":[200],"collaborate":[203],"real":[205],"person":[206],"fulfil":[208],"whole":[210]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}
