{"id":"https://openalex.org/W4385275735","doi":"https://doi.org/10.1145/3592456","title":"Bodyformer: Semantics-guided 3D Body Gesture Synthesis with Transformer","display_name":"Bodyformer: Semantics-guided 3D Body Gesture Synthesis with Transformer","publication_year":2023,"publication_date":"2023-07-26","ids":{"openalex":"https://openalex.org/W4385275735","doi":"https://doi.org/10.1145/3592456"},"language":"en","primary_location":{"id":"doi:10.1145/3592456","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3592456","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2310.06851","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010382176","display_name":"Kunkun Pang","orcid":"https://orcid.org/0000-0002-0168-3697"},"institutions":[{"id":"https://openalex.org/I4210103524","display_name":"Guangdong Academy of Sciences","ror":"https://ror.org/01g9hkj35","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210103524"]},{"id":"https://openalex.org/I4210142539","display_name":"Guangdong Institute of Intelligent Manufacturing","ror":"https://ror.org/049jpjz09","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210142539"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kunkun Pang","raw_affiliation_strings":["Guangdong Key Laboratory of Modern Control Technology, Institute of Intelligent Manufacturing, Guangdong Academy of Sciences, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-0168-3697","affiliations":[{"raw_affiliation_string":"Guangdong Key Laboratory of Modern Control Technology, Institute of Intelligent Manufacturing, Guangdong Academy of Sciences, Guangzhou, China","institution_ids":["https://openalex.org/I4210142539","https://openalex.org/I4210103524"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037765030","display_name":"Dafei Qin","orcid":"https://orcid.org/0009-0001-4992-4760"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Dafei Qin","raw_affiliation_strings":["University of Hong Kong, Pokfulam, Hong Kong"],"raw_orcid":"https://orcid.org/0009-0001-4992-4760","affiliations":[{"raw_affiliation_string":"University of Hong Kong, Pokfulam, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072087245","display_name":"Yingruo Fan","orcid":"https://orcid.org/0000-0001-8977-4958"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yingruo Fan","raw_affiliation_strings":["University of Hong Kong, Pokfulam, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-8977-4958","affiliations":[{"raw_affiliation_string":"University of Hong Kong, Pokfulam, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043266801","display_name":"Julian Habekost","orcid":"https://orcid.org/0009-0004-0894-5954"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Julian Habekost","raw_affiliation_strings":["University of Edinburgh, Edinburgh, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0004-0894-5954","affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072453520","display_name":"Takaaki Shiratori","orcid":"https://orcid.org/0000-0002-1012-415X"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takaaki Shiratori","raw_affiliation_strings":["Meta Reality Labs, Pittsburgh, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-1012-415X","affiliations":[{"raw_affiliation_string":"Meta Reality Labs, Pittsburgh, United States of America","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-2752-3955","affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014324841","display_name":"Taku Komura","orcid":"https://orcid.org/0000-0002-2729-5860"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK","JP"],"is_corresponding":false,"raw_author_name":"Taku Komura","raw_affiliation_strings":["Research Institute of Electrical Communication, Tohoku University, Sendai, Japan","University of Hong Kong, Pokfulam, Hong Kong","University of Hong Kong, Pokfulam, Hong Kong Research Institute of Electrical Communication, Tohoku University, Sendai, Japan"],"raw_orcid":"https://orcid.org/0000-0002-2729-5860","affiliations":[{"raw_affiliation_string":"Research Institute of Electrical Communication, Tohoku University, Sendai, Japan","institution_ids":["https://openalex.org/I201537933"]},{"raw_affiliation_string":"University of Hong Kong, Pokfulam, Hong Kong","institution_ids":["https://openalex.org/I889458895"]},{"raw_affiliation_string":"University of Hong Kong, Pokfulam, Hong Kong Research Institute of Electrical Communication, Tohoku University, Sendai, Japan","institution_ids":["https://openalex.org/I201537933","https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":5,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5010382176"],"corresponding_institution_ids":["https://openalex.org/I4210103524","https://openalex.org/I4210142539"],"apc_list":null,"apc_paid":null,"fwci":2.8208,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.90891593,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"42","issue":"4","first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9997000098228455,"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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9994999766349792,"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":0.998199999332428,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.9198814630508423},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7814996838569641},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.560316801071167},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5285716652870178},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5072423815727234},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4750021696090698},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.44750720262527466},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4356991648674011},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.43055158853530884},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.4111037254333496},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3614013195037842},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3364698886871338},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.33484768867492676},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08397141098976135}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.9198814630508423},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7814996838569641},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.560316801071167},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5285716652870178},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5072423815727234},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4750021696090698},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.44750720262527466},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4356991648674011},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.43055158853530884},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.4111037254333496},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3614013195037842},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3364698886871338},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33484768867492676},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08397141098976135},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3592456","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3592456","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2310.06851","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.06851","pdf_url":"https://arxiv.org/pdf/2310.06851","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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:2310.06851","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.06851","pdf_url":"https://arxiv.org/pdf/2310.06851","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[{"id":"https://openalex.org/G845706179","display_name":null,"funder_award_id":"ITS/319/21FP","funder_id":"https://openalex.org/F4320321920","funder_display_name":"Innovation and Technology Commission"}],"funders":[{"id":"https://openalex.org/F4320321920","display_name":"Innovation and Technology Commission","ror":"https://ror.org/04vf9tr09"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385275735.pdf","grobid_xml":"https://content.openalex.org/works/W4385275735.grobid-xml"},"referenced_works_count":61,"referenced_works":["https://openalex.org/W112381816","https://openalex.org/W1566289585","https://openalex.org/W1974604838","https://openalex.org/W2007337857","https://openalex.org/W2108598243","https://openalex.org/W2116261113","https://openalex.org/W2169262156","https://openalex.org/W2191779130","https://openalex.org/W2612690371","https://openalex.org/W2727071501","https://openalex.org/W2780124704","https://openalex.org/W2801567109","https://openalex.org/W2901285216","https://openalex.org/W2908510526","https://openalex.org/W2922298118","https://openalex.org/W2924334974","https://openalex.org/W2936774411","https://openalex.org/W2945629925","https://openalex.org/W2949924544","https://openalex.org/W2953273646","https://openalex.org/W2962795401","https://openalex.org/W2963341956","https://openalex.org/W2964110616","https://openalex.org/W2967443589","https://openalex.org/W2981802563","https://openalex.org/W3002310794","https://openalex.org/W3009042479","https://openalex.org/W3009385801","https://openalex.org/W3083173864","https://openalex.org/W3093647117","https://openalex.org/W3094502228","https://openalex.org/W3098994456","https://openalex.org/W3099073275","https://openalex.org/W3102619627","https://openalex.org/W3107914916","https://openalex.org/W3115266783","https://openalex.org/W3121309507","https://openalex.org/W3123650687","https://openalex.org/W3125775899","https://openalex.org/W3133090439","https://openalex.org/W3153551559","https://openalex.org/W3181695292","https://openalex.org/W3188493377","https://openalex.org/W3194605252","https://openalex.org/W3194872882","https://openalex.org/W3198131199","https://openalex.org/W3206228555","https://openalex.org/W4200526174","https://openalex.org/W4206706211","https://openalex.org/W4221142137","https://openalex.org/W4230429791","https://openalex.org/W4239072543","https://openalex.org/W4285981714","https://openalex.org/W4295312788","https://openalex.org/W4299390018","https://openalex.org/W4303448003","https://openalex.org/W4304080460","https://openalex.org/W4312674262","https://openalex.org/W4321351659","https://openalex.org/W4385245566","https://openalex.org/W4386076103"],"related_works":["https://openalex.org/W2537963312","https://openalex.org/W2902873204","https://openalex.org/W2185750513","https://openalex.org/W2010878661","https://openalex.org/W3147379364","https://openalex.org/W2026258298","https://openalex.org/W3204639664","https://openalex.org/W2970836791","https://openalex.org/W2805039731","https://openalex.org/W2989699735"],"abstract_inverted_index":{"Automatic":[0],"gesture":[1,66,78,144],"synthesis":[2,67],"from":[3,68,145],"speech":[4,25,140],"is":[5,30,49,153],"a":[6,44,58,83,89,104,146],"topic":[7],"that":[8,48,132,171],"has":[9],"attracted":[10],"researchers":[11],"for":[12,51,62],"applications":[13],"in":[14,115],"remote":[15],"communication,":[16],"video":[17],"games":[18],"and":[19,26,40,141,179],"Metaverse.":[20],"Learning":[21],"the":[22,34,38,41,72,76,111,122,135,139,142,157,162],"mapping":[23,137],"between":[24,138],"3D":[27,64,143],"full-body":[28],"gestures":[29,98,182],"difficult":[31],"due":[32],"to":[33,86,109,184],"stochastic":[35,73],"nature":[36,74],"of":[37,43,75,124,149],"problem":[39],"lack":[42],"rich":[45],"cross-modal":[46],"dataset":[47,160],"needed":[50],"training.":[52],"In":[53],"this":[54],"paper,":[55],"we":[56,81,102,126],"propose":[57,82],"novel":[59],"transformer-based":[60],"framework":[61],"automatic":[63],"body":[65,77,181],"speech.":[69],"To":[70,119],"learn":[71,134],"during":[79,99],"speech,":[80],"variational":[84],"transformer":[85],"effectively":[87],"model":[88],"probabilistic":[90],"distribution":[91],"over":[92],"gestures,":[93],"which":[94],"can":[95,133,174],"produce":[96,175],"diverse":[97,180],"inference.":[100],"Furthermore,":[101],"introduce":[103],"mode":[105],"positional":[106],"embedding":[107],"layer":[108],"capture":[110],"different":[112,116],"motion":[113],"speeds":[114],"speaking":[117],"modes.":[118],"cope":[120],"with":[121,155],"scarcity":[123],"data,":[125],"design":[127],"an":[128],"intra-modal":[129],"pre-training":[130],"scheme":[131],"complex":[136],"limited":[147],"amount":[148],"data.":[150],"Our":[151],"system":[152,173],"trained":[154],"either":[156],"Trinity":[158],"speech-gesture":[159],"or":[161],"Talking":[163],"With":[164],"Hands":[165],"16.2M":[166],"dataset.":[167],"The":[168],"results":[169],"show":[170],"our":[172],"more":[176],"realistic,":[177],"appropriate,":[178],"compared":[183],"existing":[185],"state-of-the-art":[186],"approaches.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}