{"id":"https://openalex.org/W4403897432","doi":"https://doi.org/10.1145/3677388.3696336","title":"EmoSpaceTime: Decoupling Emotion and Content through Contrastive Learning for Expressive 3D Speech Animation","display_name":"EmoSpaceTime: Decoupling Emotion and Content through Contrastive Learning for Expressive 3D Speech Animation","publication_year":2024,"publication_date":"2024-10-30","ids":{"openalex":"https://openalex.org/W4403897432","doi":"https://doi.org/10.1145/3677388.3696336"},"language":"en","primary_location":{"id":"doi:10.1145/3677388.3696336","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3677388.3696336","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 17th ACM SIGGRAPH Conference on Motion Interaction and Games","raw_type":"proceedings-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/A5021147268","display_name":"Philine Witzig","orcid":"https://orcid.org/0009-0004-9782-8118"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Philine Witzig","raw_affiliation_strings":["Department of Computer Science, ETH Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069878201","display_name":"Barbara Solenthaler","orcid":"https://orcid.org/0000-0001-7494-8660"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Barbara Solenthaler","raw_affiliation_strings":["Department of Computer Science, ETH Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033076979","display_name":"Markus Gro\u00df","orcid":"https://orcid.org/0009-0003-9324-779X"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Markus Gross","raw_affiliation_strings":["Department of Computer Science, ETH Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015553607","display_name":"Rafael Wampfler","orcid":"https://orcid.org/0000-0003-0158-1305"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Rafael Wampfler","raw_affiliation_strings":["Department of Computer Science, ETH Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5021147268"],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":0.6569,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.70961948,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9983000159263611,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.996999979019165,"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/computer-science","display_name":"Computer science","score":0.780834436416626},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.7536027431488037},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.7218536734580994},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5362241864204407},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.4973621666431427},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.4636958837509155},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40807151794433594},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4009683430194855},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39759504795074463},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.34582316875457764},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.16083014011383057},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06267142295837402},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.058551132678985596}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.780834436416626},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.7536027431488037},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.7218536734580994},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5362241864204407},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.4973621666431427},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.4636958837509155},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40807151794433594},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4009683430194855},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39759504795074463},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.34582316875457764},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.16083014011383057},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06267142295837402},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.058551132678985596},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3677388.3696336","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3677388.3696336","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 17th ACM SIGGRAPH Conference on Motion Interaction and Games","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2011722134","https://openalex.org/W2469134594","https://openalex.org/W2737658251","https://openalex.org/W2739192055","https://openalex.org/W2753738274","https://openalex.org/W2769666294","https://openalex.org/W3019952993","https://openalex.org/W3048474702","https://openalex.org/W3048665613","https://openalex.org/W3048844620","https://openalex.org/W3093933617","https://openalex.org/W3109114891","https://openalex.org/W3112809496","https://openalex.org/W3187364420","https://openalex.org/W3210676520","https://openalex.org/W4231807801","https://openalex.org/W4236061201","https://openalex.org/W4247938635","https://openalex.org/W4284703992","https://openalex.org/W4310379947","https://openalex.org/W4312894597","https://openalex.org/W4328007113","https://openalex.org/W4377010269","https://openalex.org/W4380994134","https://openalex.org/W4386076250","https://openalex.org/W4388157164","https://openalex.org/W4388444845","https://openalex.org/W4390872742","https://openalex.org/W4400397470","https://openalex.org/W6787353492"],"related_works":["https://openalex.org/W1544039745","https://openalex.org/W2121378366","https://openalex.org/W2999276620","https://openalex.org/W2532377291","https://openalex.org/W1976926596","https://openalex.org/W2989004599","https://openalex.org/W2535923857","https://openalex.org/W3094080214","https://openalex.org/W2156310872","https://openalex.org/W2356609371"],"abstract_inverted_index":{"Equipping":[0],"stylized":[1],"conversational":[2,142],"characters":[3],"with":[4],"facial":[5,22,48,139],"animations":[6],"tailored":[7],"to":[8,33,81],"specific":[9],"emotions":[10],"enhances":[11,110],"coherence":[12],"and":[13,44,69,89,103,112,137],"authenticity.":[14],"Many":[15],"data-driven":[16],"speech":[17],"animation":[18,55,140],"methods":[19],"lack":[20],"dynamic":[21],"expressions":[23],"since":[24],"they":[25],"rely":[26],"on":[27,72],"explicit":[28],"semantic":[29],"control":[30,56,116],"signals,":[31],"leading":[32],"static":[34],"emotional":[35,87,100],"expressions.":[36],"We":[37],"present":[38],"a":[39,63],"Transformer-AE":[40,128],"for":[41,85,141],"disentangling":[42],"emotion":[43,68,108,121,131],"content":[45,70],"within":[46],"the":[47,59,77,90,95,127],"motion":[49],"latent":[50],"space.":[51],"Our":[52,123],"method":[53],"processes":[54],"parameters":[57],"in":[58],"frequency":[60],"domain,":[61],"enabling":[62,134],"more":[64,135],"fine-grained":[65],"separation":[66],"of":[67,98],"based":[71],"frequencies.":[73],"Through":[74],"contrastive":[75],"learning,":[76],"model":[78],"is":[79],"encouraged":[80],"learn":[82],"similar":[83,86],"representations":[84],"states":[88],"same":[91],"linguistic":[92],"content.":[93],"Capturing":[94],"full":[96],"dynamics":[97],"an":[99],"episode":[101],"spatially":[102],"temporally,":[104],"this":[105],"approach":[106],"enables":[107],"swapping,":[109],"expressiveness,":[111],"gives":[113],"artists":[114],"fine":[115],"over":[117],"emotion,":[118],"e.g.,":[119],"through":[120],"interpolation.":[122],"analyses":[124],"show":[125],"that":[126],"effectively":[129],"separates":[130],"from":[132],"content,":[133],"nuanced":[136],"realistic":[138],"characters.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}