{"id":"https://openalex.org/W4414687879","doi":"https://doi.org/10.1145/3746027.3754933","title":"MEDTalk: Multimodal Controlled 3D Facial Animation with Dynamic Emotions by Disentangled Embedding","display_name":"MEDTalk: Multimodal Controlled 3D Facial Animation with Dynamic Emotions by Disentangled Embedding","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4414687879","doi":"https://doi.org/10.1145/3746027.3754933"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3754933","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754933","pdf_url":null,"source":null,"license":null,"license_id":null,"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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.06071","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Chang Liu","orcid":"https://orcid.org/0009-0001-1379-2583"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chang Liu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0001-1379-2583","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071175541","display_name":"Ye Pan","orcid":"https://orcid.org/0000-0003-0355-989X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye Pan","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-0355-989X","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chenyang Ding","orcid":"https://orcid.org/0009-0008-6079-0688"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenyang Ding","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-6079-0688","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054558832","display_name":"Susanto Rahardja","orcid":"https://orcid.org/0000-0003-0831-6934"},"institutions":[{"id":"https://openalex.org/I168639165","display_name":"Singapore Institute of Technology","ror":"https://ror.org/01v2c2791","country_code":"SG","type":"education","lineage":["https://openalex.org/I168639165"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Susanto Rahardja","raw_affiliation_strings":["Singapore Institute of Technology, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-0831-6934","affiliations":[{"raw_affiliation_string":"Singapore Institute of Technology, Singapore, Singapore","institution_ids":["https://openalex.org/I168639165"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xiaokang Yang","orcid":"https://orcid.org/0000-0003-4029-3322"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaokang Yang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-4029-3322","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"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":"7538","last_page":"7547"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9994000196456909,"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/T11448","display_name":"Face recognition and analysis","score":0.9994000196456909,"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/T10860","display_name":"Speech and Audio Processing","score":0.9976999759674072,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9711999893188477,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.7465000152587891},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7224000096321106},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.7102000117301941},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.6126000285148621},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5091000199317932},{"id":"https://openalex.org/keywords/facial-motion-capture","display_name":"Facial motion capture","score":0.49380001425743103},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4936999976634979},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.4763000011444092}],"concepts":[{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.7465000152587891},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7432000041007996},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7224000096321106},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.7102000117301941},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.6126000285148621},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5091000199317932},{"id":"https://openalex.org/C98907195","wikidata":"https://www.wikidata.org/wiki/Q5428562","display_name":"Facial motion capture","level":5,"score":0.49380001425743103},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4936999976634979},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4763000011444092},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4722000062465668},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.41029998660087585},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4059999883174896},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40560001134872437},{"id":"https://openalex.org/C40346341","wikidata":"https://www.wikidata.org/wiki/Q1391629","display_name":"Facial Action Coding System","level":3,"score":0.4049000144004822},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3959999978542328},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.3926999866962433},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.38929998874664307},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3513999879360199},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.29420000314712524},{"id":"https://openalex.org/C143110190","wikidata":"https://www.wikidata.org/wiki/Q5373787","display_name":"Emotional expression","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.25049999356269836}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3754933","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754933","pdf_url":null,"source":null,"license":null,"license_id":null,"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:arXiv.org:2507.06071","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.06071","pdf_url":"https://arxiv.org/pdf/2507.06071","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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:2507.06071","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.06071","pdf_url":"https://arxiv.org/pdf/2507.06071","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Audio-driven":[0],"emotional":[1,45,100],"3D":[2],"facial":[3,13,74,123],"animation":[4],"aims":[5],"to":[6,97,103],"generate":[7,98],"synchronized":[8],"lip":[9,71,79],"movements":[10,72],"and":[11,22,29,43,54,73,84,91,106,114],"vivid":[12],"expressions.":[14,75,101,124],"However,":[15],"most":[16],"existing":[17],"approaches":[18],"focus":[19],"on":[20],"static":[21,94],"predefined":[23],"emotion":[24,55,95],"labels,":[25],"limiting":[26],"their":[27],"diversity":[28],"naturalness.":[30],"To":[31],"address":[32],"these":[33],"challenges,":[34],"we":[35,81,108],"propose":[36],"MEDTalk,":[37],"a":[38,62],"novel":[39],"framework":[40],"for":[41],"fine-grained":[42],"dynamic":[44],"talking":[46],"head":[47],"generation.":[48],"Our":[49],"approach":[50],"first":[51],"disentangles":[52],"content":[53],"embedding":[56],"spaces":[57],"from":[58],"motion":[59],"sequences":[60],"using":[61],"carefully":[63],"designed":[64],"cross-reconstruction":[65],"process,":[66],"enabling":[67],"independent":[68],"control":[69,105],"over":[70],"Beyond":[76],"conventional":[77],"audio-driven":[78],"synchronization,":[80],"integrate":[82],"audio":[83],"speech":[85],"text,":[86],"predicting":[87],"frame-wise":[88],"intensity":[89],"variations":[90],"dynamically":[92],"adjusting":[93],"features":[96],"realistic":[99],"Furthermore,":[102],"enhance":[104],"personalization,":[107],"incorporate":[109],"multimodal":[110],"inputs-including":[111],"text":[112],"descriptions":[113],"reference":[115],"expression":[116],"images-to":[117],"guide":[118],"the":[119,128,138],"generation":[120],"of":[121],"user-specified":[122],"With":[125],"MetaHuman":[126],"as":[127],"priority,":[129],"our":[130],"generated":[131],"results":[132],"can":[133],"be":[134],"conveniently":[135],"integrated":[136],"into":[137],"industrial":[139],"production":[140],"pipeline.":[141],"The":[142],"code":[143],"is":[144],"available":[145],"at:":[146],"https://github.com/SJTU-Lucy/MEDTalk.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}
