{"id":"https://openalex.org/W4415540496","doi":"https://doi.org/10.1145/3746027.3755286","title":"Disentangle Identity, Cooperate Emotion: Correlation-Aware Emotional Talking Portrait Generation","display_name":"Disentangle Identity, Cooperate Emotion: Correlation-Aware Emotional Talking Portrait Generation","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540496","doi":"https://doi.org/10.1145/3746027.3755286"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755286","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755286","pdf_url":null,"source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3755286","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056057340","display_name":"Weipeng Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weipeng Tan","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0006-0165-9052","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090180766","display_name":"Chuming Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuming Lin","raw_affiliation_strings":["Tencent, YouTu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0001-5882-9458","affiliations":[{"raw_affiliation_string":"Tencent, YouTu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101908952","display_name":"Chengming Xu","orcid":"https://orcid.org/0000-0003-3891-2227"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengming Xu","raw_affiliation_strings":["Tencent, YouTu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-3891-2227","affiliations":[{"raw_affiliation_string":"Tencent, YouTu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036692892","display_name":"FeiFan Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"FeiFan Xu","raw_affiliation_strings":["Tencent, YouTu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-2256-0179","affiliations":[{"raw_affiliation_string":"Tencent, YouTu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101735199","display_name":"Xiaobin Hu","orcid":"https://orcid.org/0000-0002-5764-3096"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaobin Hu","raw_affiliation_strings":["Tencent, YouTu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-5764-3096","affiliations":[{"raw_affiliation_string":"Tencent, YouTu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055612307","display_name":"Xiaozhong Ji","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaozhong Ji","raw_affiliation_strings":["Tencent, YouTu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0000-1044-5853","affiliations":[{"raw_affiliation_string":"Tencent, YouTu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112347878","display_name":"Junwei Zhu","orcid":"https://orcid.org/0000-0002-5407-5150"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junwei Zhu","raw_affiliation_strings":["Tencent, YouTu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-5407-5150","affiliations":[{"raw_affiliation_string":"Tencent, YouTu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023834700","display_name":"Chengjie Wang","orcid":"https://orcid.org/0000-0003-4216-8090"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengjie Wang","raw_affiliation_strings":["Tencent, YouTu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-4216-8090","affiliations":[{"raw_affiliation_string":"Tencent, YouTu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084959430","display_name":"Yanwei Fu","orcid":"https://orcid.org/0000-0002-6595-6893"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanwei Fu","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-6595-6893","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9987","last_page":"9995"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T11309","display_name":"Music and Audio Processing","score":0.9944999814033508,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9939000010490417,"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/identity","display_name":"Identity (music)","score":0.4794999957084656},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44290000200271606},{"id":"https://openalex.org/keywords/portrait","display_name":"Portrait","score":0.3986999988555908},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.38109999895095825},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.3776000142097473},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.367900013923645},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.35989999771118164},{"id":"https://openalex.org/keywords/emotional-expression","display_name":"Emotional expression","score":0.3433000147342682}],"concepts":[{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.5536999702453613},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.5092999935150146},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.4794999957084656},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44290000200271606},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4399000108242035},{"id":"https://openalex.org/C162462552","wikidata":"https://www.wikidata.org/wiki/Q134307","display_name":"Portrait","level":2,"score":0.3986999988555908},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.38109999895095825},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.3776000142097473},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.367900013923645},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.35989999771118164},{"id":"https://openalex.org/C143110190","wikidata":"https://www.wikidata.org/wiki/Q5373787","display_name":"Emotional expression","level":2,"score":0.3433000147342682},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.33739998936653137},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.32249999046325684},{"id":"https://openalex.org/C128534915","wikidata":"https://www.wikidata.org/wiki/Q3475770","display_name":"Affective science","level":3,"score":0.3199000060558319},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.31459999084472656},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3100000023841858},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C6438553","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Affective computing","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.2946999967098236},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C2776141551","wikidata":"https://www.wikidata.org/wiki/Q16000087","display_name":"Emotion perception","level":3,"score":0.2784999907016754},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.2632000148296356},{"id":"https://openalex.org/C3018587665","wikidata":"https://www.wikidata.org/wiki/Q7268696","display_name":"Qualitative analysis","level":3,"score":0.25369998812675476}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3755286","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755286","pdf_url":null,"source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1838825","is_oa":true,"landing_page_url":"https://mediatum.ub.tum.de/1838825","pdf_url":null,"source":{"id":"https://openalex.org/S4306400453","display_name":"mediaTUM \u2013 the media and publications repository of the Technical University Munich (Technical University Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferencePaper"}],"best_oa_location":{"id":"doi:10.1145/3746027.3755286","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755286","pdf_url":null,"source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2237250383","https://openalex.org/W2808631503","https://openalex.org/W3081492798","https://openalex.org/W3187364420","https://openalex.org/W3197199219","https://openalex.org/W4200631136","https://openalex.org/W4281779270","https://openalex.org/W4303437686","https://openalex.org/W4312444931","https://openalex.org/W4312933868","https://openalex.org/W4386065999","https://openalex.org/W4390872769"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,36,51,165],"Talking":[3],"Head":[4],"Generation":[5],"(THG)":[6],"have":[7],"achieved":[8],"impressive":[9],"lip":[10],"synchronization":[11],"and":[12,54,80,129,155,175],"visual":[13],"quality":[14],"through":[15,100,126,148],"diffusion":[16,146],"models;":[17],"yet":[18],"existing":[19],"methods":[20],"struggle":[21],"to":[22,183,195],"generate":[23,184],"emotionally":[24],"expressive":[25],"portraits":[26,186],"while":[27,168],"preserving":[28],"speaker":[29],"identity.":[30],"We":[31],"identify":[32],"three":[33],"critical":[34],"limitations":[35],"current":[37],"emotional":[38,47,98,190],"talking":[39],"head":[40],"generation:":[41],"insufficient":[42],"utilization":[43],"of":[44,57,75],"audio's":[45],"inherent":[46],"cues,":[48],"identity":[49,77],"leakage":[50],"emotion":[52,58,92,114,119,137,166],"representations,":[53],"isolated":[55],"learning":[56],"correlations.":[59],"To":[60],"address":[61],"these":[62],"challenges,":[63],"we":[64,88,110,134],"propose":[65],"a":[66,90,112],"novel":[67],"framework":[68],"dubbed":[69],"as":[70,105],"DICE-Talk,":[71],"following":[72],"the":[73,145],"idea":[74],"disentangling":[76],"with":[78,84,117,187],"emotion,":[79],"then":[81],"cooperating":[82],"emotions":[83,104],"similar":[85],"characteristics.":[86],"First,":[87],"develop":[89],"disentangled":[91],"embedder":[93],"that":[94,121,140,192],"jointly":[95],"models":[96],"audio-visual":[97],"cues":[99],"cross-modal":[101],"attention,":[102],"representing":[103],"identity-agnostic":[106],"Gaussian":[107],"distributions.":[108],"Second,":[109],"introduce":[111],"correlation-enhanced":[113],"conditioning":[115],"module":[116],"learnable":[118],"banks":[120],"explicitly":[122],"capture":[123],"inter-emotion":[124],"relationships":[125],"vector":[127],"quantization":[128],"attention-based":[130],"feature":[131],"aggregation.":[132],"Third,":[133],"design":[135],"an":[136],"discrimination":[138],"objective":[139],"enforces":[141],"affective":[142],"consistency":[143],"during":[144],"process":[147],"latent-space":[149],"classification.":[150],"Extensive":[151],"experiments":[152],"on":[153],"MEAD":[154],"HDTF":[156],"datasets":[157],"demonstrate":[158],"our":[159,180],"method's":[160,181],"superiority,":[161],"outperforming":[162],"state-of-the-art":[163],"approaches":[164],"accuracy":[167],"maintaining":[169],"competitive":[170],"lip-sync":[171],"performance.":[172],"Qualitative":[173],"results":[174],"user":[176],"studies":[177],"further":[178],"confirm":[179],"ability":[182],"identity-preserving":[185],"rich,":[188],"correlated":[189],"expressions":[191],"naturally":[193],"adapt":[194],"unseen":[196],"identities.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}