{"id":"https://openalex.org/W4285981714","doi":"https://doi.org/10.1145/3528233.3530750","title":"A Motion Matching-based Framework for Controllable Gesture Synthesis from Speech","display_name":"A Motion Matching-based Framework for Controllable Gesture Synthesis from Speech","publication_year":2022,"publication_date":"2022-07-20","ids":{"openalex":"https://openalex.org/W4285981714","doi":"https://doi.org/10.1145/3528233.3530750"},"language":"en","primary_location":{"id":"doi:10.1145/3528233.3530750","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3528233.3530750","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3528233.3530750","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special Interest Group on Computer Graphics and Interactive Techniques Conference Proceedings","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3528233.3530750","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010909245","display_name":"Ikhsanul Habibie","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Ikhsanul Habibie","raw_affiliation_strings":["Department of Visual Computing and Artificial Intelligence, Max Planck Institute for Informatics, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Visual Computing and Artificial Intelligence, Max Planck Institute for Informatics, Germany","institution_ids":["https://openalex.org/I4210109712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079162835","display_name":"Mohamed Elgharib","orcid":"https://orcid.org/0000-0001-8727-0895"},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mohamed Elgharib","raw_affiliation_strings":["Department of Visual Computing and Artificial Intelligence, Max Planck Institute for Informatics, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Visual Computing and Artificial Intelligence, Max Planck Institute for Informatics, Germany","institution_ids":["https://openalex.org/I4210109712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056783532","display_name":"Kripasindhu Sarkar","orcid":"https://orcid.org/0000-0002-0220-0853"},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kripasindhu Sarkar","raw_affiliation_strings":["Department of Visual Computing and Artificial Intelligence, Max Planck Institute for Informatics, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Visual Computing and Artificial Intelligence, Max Planck Institute for Informatics, Germany","institution_ids":["https://openalex.org/I4210109712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101072270","display_name":"Ahsan Abdullah","orcid":null},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ahsan Abdullah","raw_affiliation_strings":["UC Davis, United States of America"],"affiliations":[{"raw_affiliation_string":"UC Davis, United States of America","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030586293","display_name":"Simbarashe Nyatsanga","orcid":"https://orcid.org/0009-0004-2315-6339"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Simbarashe Nyatsanga","raw_affiliation_strings":["UC Davis, United States of America"],"affiliations":[{"raw_affiliation_string":"UC Davis, United States of America","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013628099","display_name":"Michael Neff","orcid":"https://orcid.org/0000-0003-0226-2808"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Neff","raw_affiliation_strings":["UC Davis, United States of America"],"affiliations":[{"raw_affiliation_string":"UC Davis, United States of America","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020664641","display_name":"Christian Theobalt","orcid":"https://orcid.org/0000-0001-6104-6625"},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Theobalt","raw_affiliation_strings":["Department of Visual Computing and Artificial Intelligence, Max Planck Institute for Informatics, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Visual Computing and Artificial Intelligence, Max Planck Institute for Informatics, Germany","institution_ids":["https://openalex.org/I4210109712"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5010909245"],"corresponding_institution_ids":["https://openalex.org/I4210109712"],"apc_list":null,"apc_paid":null,"fwci":5.7351,"has_fulltext":true,"cited_by_count":57,"citation_normalized_percentile":{"value":0.97226985,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9998999834060669,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9998999834060669,"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/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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/gesture","display_name":"Gesture","score":0.8310014009475708},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8195840120315552},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.566997230052948},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5569331049919128},{"id":"https://openalex.org/keywords/motion-capture","display_name":"Motion capture","score":0.5498759746551514},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5106530785560608},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.4894186556339264},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.4570690393447876},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4333345592021942},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43139609694480896},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.42301735281944275},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4107936918735504},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.37159839272499084},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3571861982345581},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.11969450116157532}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.8310014009475708},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8195840120315552},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.566997230052948},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5569331049919128},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.5498759746551514},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5106530785560608},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4894186556339264},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.4570690393447876},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4333345592021942},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43139609694480896},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.42301735281944275},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4107936918735504},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37159839272499084},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3571861982345581},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.11969450116157532},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3528233.3530750","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3528233.3530750","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3528233.3530750","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special Interest Group on Computer Graphics and Interactive Techniques Conference Proceedings","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3528233.3530750","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3528233.3530750","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3528233.3530750","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special Interest Group on Computer Graphics and Interactive Techniques Conference Proceedings","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7799999713897705}],"awards":[{"id":"https://openalex.org/G1191362969","display_name":null,"funder_award_id":"770784","funder_id":"https://openalex.org/F4320334678","funder_display_name":"European Research Council"}],"funders":[{"id":"https://openalex.org/F4320334678","display_name":"European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285981714.pdf","grobid_xml":"https://content.openalex.org/works/W4285981714.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W114912394","https://openalex.org/W216945601","https://openalex.org/W341184420","https://openalex.org/W1974597084","https://openalex.org/W2008208299","https://openalex.org/W2027247754","https://openalex.org/W2131734538","https://openalex.org/W2187250581","https://openalex.org/W2243558602","https://openalex.org/W2249800031","https://openalex.org/W2559085405","https://openalex.org/W2604379605","https://openalex.org/W2607662938","https://openalex.org/W2737477199","https://openalex.org/W2901872500","https://openalex.org/W2962795401","https://openalex.org/W2963544341","https://openalex.org/W2967443589","https://openalex.org/W2981802563","https://openalex.org/W3002310794","https://openalex.org/W3009042479","https://openalex.org/W3048665613","https://openalex.org/W3083173864","https://openalex.org/W3091094344","https://openalex.org/W3099402851","https://openalex.org/W3115266783","https://openalex.org/W3125775899","https://openalex.org/W3133090439","https://openalex.org/W3153551559","https://openalex.org/W3172764674","https://openalex.org/W3188493377","https://openalex.org/W3198131199","https://openalex.org/W4214544731","https://openalex.org/W4214708455","https://openalex.org/W4230312136","https://openalex.org/W4230429791","https://openalex.org/W4310301283"],"related_works":["https://openalex.org/W4380075502","https://openalex.org/W4223943233","https://openalex.org/W4312200629","https://openalex.org/W4360585206","https://openalex.org/W4364306694","https://openalex.org/W3111216657","https://openalex.org/W1033489","https://openalex.org/W1851213814","https://openalex.org/W2348818095","https://openalex.org/W2029399117"],"abstract_inverted_index":{"Recent":[0],"deep":[1,78],"learning-based":[2,170],"approaches":[3,19],"have":[4],"shown":[5],"promising":[6],"results":[7],"for":[8,65,90,200],"synthesizing":[9],"plausible":[10,93],"3D":[11,68,84],"human":[12],"gestures":[13,69],"from":[14,96],"speech":[15],"input.":[16],"However,":[17],"these":[18,59],"typically":[20],"offer":[21],"limited":[22],"freedom":[23],"to":[24,109,135,140],"incorporate":[25],"user":[26,198],"control.":[27],"Furthermore,":[28],"training":[29],"such":[30,189],"models":[31,181],"in":[32],"a":[33,97,100,128,137],"supervised":[34],"manner":[35],"often":[36],"does":[37],"not":[38,166],"capture":[39],"the":[40,44,48,72,91,107,111,115,123,141,149],"multi-modal":[41],"nature":[42],"of":[43,74],"data,":[45],"particularly":[46],"because":[47],"same":[49],"audio":[50,113],"input":[51,112],"can":[52],"produce":[53],"different":[54],"gesture":[55],"outputs.":[56],"To":[57,120],"address":[58],"problems,":[60],"we":[61,126],"present":[62],"an":[63],"approach":[64,156,178],"generating":[66],"controllable":[67],"that":[70,105,164,175],"combines":[71],"advantage":[73],"database":[75,98],"matching":[76],"and":[77,114,159,196],"generative":[79],"modeling.":[80],"Our":[81,154,172],"method":[82],"predicts":[83],"body":[85,117],"motion":[86,191],"by":[87,144],"sequentially":[88],"searching":[89],"most":[92],"audio-gesture":[94,152],"clips":[95],"using":[99,186],"k-Nearest":[101],"Neighbors":[102],"(k-NN)":[103],"algorithm":[104],"considers":[106],"similarity":[108],"both":[110],"previous":[116],"pose":[118],"information.":[119],"further":[121],"improve":[122],"synthesis":[124,184],"quality,":[125],"propose":[127],"conditional":[129],"Generative":[130],"Adversarial":[131],"Network":[132],"(cGAN)":[133],"model":[134],"provide":[136],"data-driven":[138],"refinement":[139],"k-NN":[142],"result":[143],"comparing":[145],"its":[146],"plausibility":[147],"against":[148],"ground":[150],"truth":[151],"pairs.":[153],"novel":[155],"enables":[157],"direct":[158],"more":[160],"varied":[161],"control":[162,199],"manipulation":[163],"is":[165],"possible":[167],"with":[168],"prior":[169],"counterparts.":[171],"experiments":[173],"show":[174],"our":[176],"proposed":[177],"outperforms":[179],"recent":[180],"on":[182],"control-based":[183],"tasks":[185],"high-level":[187],"signals":[188],"as":[190],"statistics":[192],"while":[193],"enabling":[194],"flexible":[195],"effective":[197],"lower-level":[201],"signals.":[202],"1":[203]},"counts_by_year":[{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":20},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}