{"id":"https://openalex.org/W4386270206","doi":"https://doi.org/10.1145/3577190.3616114","title":"The DiffuseStyleGesture+ entry to the GENEA Challenge 2023","display_name":"The DiffuseStyleGesture+ entry to the GENEA Challenge 2023","publication_year":2023,"publication_date":"2023-10-07","ids":{"openalex":"https://openalex.org/W4386270206","doi":"https://doi.org/10.1145/3577190.3616114"},"language":"en","primary_location":{"id":"doi:10.1145/3577190.3616114","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3577190.3616114","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3577190.3616114","source":{"id":"https://openalex.org/S4363608440","display_name":"INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3577190.3616114","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113092484","display_name":"Sicheng Yang","orcid":"https://orcid.org/0009-0004-8472-9022"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Sicheng Yang","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, China"],"raw_orcid":"https://orcid.org/0000-0002-0928-034X","affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102788950","display_name":"Haiwei Xue","orcid":"https://orcid.org/0000-0001-7318-9682"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiwei Xue","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, China"],"raw_orcid":"https://orcid.org/0000-0001-7318-9682","affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043901952","display_name":"Zhensong Zhang","orcid":"https://orcid.org/0009-0001-7911-7564"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhensong Zhang","raw_affiliation_strings":["Huawei Noah's Ark Lab, China"],"raw_orcid":"https://orcid.org/0009-0001-7911-7564","affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100780135","display_name":"Minglei Li","orcid":"https://orcid.org/0000-0002-1427-3507"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minglei Li","raw_affiliation_strings":["Huawei Cloud Computing Technologies Co., Ltd, China"],"raw_orcid":"https://orcid.org/0000-0002-1427-3507","affiliations":[{"raw_affiliation_string":"Huawei Cloud Computing Technologies Co., Ltd, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102869280","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0001-8533-0524"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, China and The Chinese University of Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0001-8533-0524","affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, China and The Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I4210116924","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101566020","display_name":"Xiaofei Wu","orcid":"https://orcid.org/0009-0007-0143-1485"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofei Wu","raw_affiliation_strings":["Huawei Noah's Ark Lab, China"],"raw_orcid":"https://orcid.org/0009-0007-0143-1485","affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030497493","display_name":"Songcen Xu","orcid":"https://orcid.org/0000-0002-0022-0906"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songcen Xu","raw_affiliation_strings":["Huawei Noah's Ark Lab, China"],"raw_orcid":"https://orcid.org/0000-0002-0022-0906","affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103105111","display_name":"Zonghong Dai","orcid":"https://orcid.org/0009-0006-7723-4130"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zonghong Dai","raw_affiliation_strings":["Huawei Cloud Computing Technologies Co., Ltd, China"],"raw_orcid":"https://orcid.org/0009-0006-7723-4130","affiliations":[{"raw_affiliation_string":"Huawei Cloud Computing Technologies Co., Ltd, China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5113092484"],"corresponding_institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.2715,"has_fulltext":true,"cited_by_count":29,"citation_normalized_percentile":{"value":0.94375,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"779","last_page":"785"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9997000098228455,"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":0.9988999962806702,"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/computer-science","display_name":"Computer science","score":0.44197404384613037}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44197404384613037}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3577190.3616114","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3577190.3616114","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3577190.3616114","source":{"id":"https://openalex.org/S4363608440","display_name":"INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2308.13879","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.13879","pdf_url":"https://arxiv.org/pdf/2308.13879","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3577190.3616114","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3577190.3616114","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3577190.3616114","source":{"id":"https://openalex.org/S4363608440","display_name":"INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.47999998927116394,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G2603945996","display_name":null,"funder_award_id":"62076144","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386270206.pdf","grobid_xml":"https://content.openalex.org/works/W4386270206.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1208039178","https://openalex.org/W2140304104","https://openalex.org/W2493916176","https://openalex.org/W2901872500","https://openalex.org/W2902318149","https://openalex.org/W2922298118","https://openalex.org/W2967443589","https://openalex.org/W3036167779","https://openalex.org/W3083173864","https://openalex.org/W3099073275","https://openalex.org/W3118288752","https://openalex.org/W3125775899","https://openalex.org/W3131922516","https://openalex.org/W3209984917","https://openalex.org/W4221142137","https://openalex.org/W4230429791","https://openalex.org/W4249736682","https://openalex.org/W4292945985","https://openalex.org/W4293352083","https://openalex.org/W4294530172","https://openalex.org/W4308222758","https://openalex.org/W4312462635","https://openalex.org/W4312635677","https://openalex.org/W4312671789","https://openalex.org/W4312674262","https://openalex.org/W4312719027","https://openalex.org/W4327673403","https://openalex.org/W4372346581","https://openalex.org/W4386065807","https://openalex.org/W4386076405","https://openalex.org/W4387421378","https://openalex.org/W6779823529"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"In":[0],"this":[1,172],"paper,":[2],"we":[3],"introduce":[4],"the":[5,10,27,96,106,113,117,130,137],"DiffuseStyleGesture+,":[6,55],"our":[7,148],"solution":[8],"for":[9,17,33,99,129,142,160],"Generation":[11],"and":[12,44,75,87,132,152,157,167],"Evaluation":[13],"of":[14,29,68],"Non-verbal":[15],"Behavior":[16],"Embodied":[18],"Agents":[19],"(GENEA)":[20],"Challenge":[21],"2023,":[22],"which":[23],"aims":[24],"to":[25,60,83,94],"foster":[26],"development":[28],"realistic,":[30],"automated":[31],"systems":[32,46],"generating":[34,155],"conversational":[35],"gestures.":[36,77],"Participants":[37],"are":[38,47,81,169],"provided":[39],"with":[40,112,123,136],"a":[41,57,66,84,90,100],"pre-processed":[42],"dataset":[43],"their":[45],"evaluated":[48],"through":[49],"crowdsourced":[50],"scoring.":[51],"Our":[52],"proposed":[53],"model,":[54],"leverages":[56],"diffusion":[58,92],"model":[59,93,139,149],"generate":[61],"gestures":[62,159],"automatically.":[63],"It":[64],"incorporates":[65],"variety":[67],"modalities,":[69],"including":[70],"audio,":[71],"text,":[72],"speaker":[73],"ID,":[74],"seed":[76],"These":[78],"diverse":[79],"modalities":[80],"mapped":[82],"hidden":[85],"space":[86],"processed":[88],"by":[89],"modified":[91],"produce":[95],"corresponding":[97],"gesture":[98],"given":[101,161],"speech":[102],"input.":[103],"Upon":[104],"evaluation,":[105],"DiffuseStyleGesture+":[107],"demonstrated":[108],"performance":[109,135],"on":[110,140],"par":[111],"top-tier":[114],"models":[115,125],"in":[116,126,154],"challenge,":[118],"showing":[119],"no":[120],"significant":[121],"differences":[122],"those":[124],"human-likeness,":[127],"appropriateness":[128,141],"interlocutor,":[131],"achieving":[133],"competitive":[134,151],"best":[138],"agent":[143],"speech.":[144,162],"This":[145],"indicates":[146],"that":[147],"is":[150],"effective":[153],"realistic":[156],"appropriate":[158],"The":[163],"code,":[164],"pre-trained":[165],"models,":[166],"demos":[168],"available":[170],"at":[171],"URL.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
