{"id":"https://openalex.org/W4387446765","doi":"https://doi.org/10.1145/3610661.3616552","title":"DiffuGesture: Generating Human Gesture From Two-person Dialogue With Diffusion Models","display_name":"DiffuGesture: Generating Human Gesture From Two-person Dialogue With Diffusion Models","publication_year":2023,"publication_date":"2023-10-09","ids":{"openalex":"https://openalex.org/W4387446765","doi":"https://doi.org/10.1145/3610661.3616552"},"language":"en","primary_location":{"id":"doi:10.1145/3610661.3616552","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3610661.3616552","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Cconference on Multimodal Interaction","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/A5002473193","display_name":"Weiyu Zhao","orcid":"https://orcid.org/0009-0002-2661-3692"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weiyu Zhao","raw_affiliation_strings":["Harbin Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084899380","display_name":"Liangxiao Hu","orcid":"https://orcid.org/0000-0001-5233-473X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liangxiao Hu","raw_affiliation_strings":["Harbin Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084025984","display_name":"Shengping Zhang","orcid":"https://orcid.org/0000-0001-5200-3420"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengping Zhang","raw_affiliation_strings":["Harbin Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5002473193"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":1.2178,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.83580595,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"179","last_page":"185"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9980999827384949,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9980000257492065,"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":0.9375891089439392},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7168866395950317},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.5252225399017334},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5185754299163818},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.50217604637146},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.49224820733070374},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4745631814002991},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4521333575248718},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41750848293304443},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3893657922744751},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15272101759910583}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.9375891089439392},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7168866395950317},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.5252225399017334},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5185754299163818},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.50217604637146},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.49224820733070374},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4745631814002991},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4521333575248718},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41750848293304443},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3893657922744751},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15272101759910583},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3610661.3616552","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3610661.3616552","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Cconference on Multimodal Interaction","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":22,"referenced_works":["https://openalex.org/W2007337857","https://openalex.org/W2126776405","https://openalex.org/W2802076562","https://openalex.org/W2962795401","https://openalex.org/W2967443589","https://openalex.org/W3002310794","https://openalex.org/W3083173864","https://openalex.org/W3125277150","https://openalex.org/W3125775899","https://openalex.org/W3135367836","https://openalex.org/W4206861281","https://openalex.org/W4230312136","https://openalex.org/W4230429791","https://openalex.org/W4281487633","https://openalex.org/W4292945985","https://openalex.org/W4303448003","https://openalex.org/W4308222520","https://openalex.org/W4308222716","https://openalex.org/W4308222758","https://openalex.org/W4312674262","https://openalex.org/W4313145975","https://openalex.org/W4387421378"],"related_works":["https://openalex.org/W2066003895","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":{"This":[0],"paper":[1],"describes":[2],"the":[3,7,21,32,40,46,54,67,92,106],"DiffuGesture":[4,26,49],"entry":[5],"to":[6,19,39,65,82,91],"GENEA":[8,97],"Challenge":[9,98],"2023.":[10],"In":[11],"this":[12],"paper,":[13],"we":[14,59,77],"utilize":[15],"conditional":[16],"diffusion":[17],"models":[18],"formulate":[20],"gesture":[22,88],"generation":[23],"problem.":[24],"The":[25],"system":[27,50,101],"generates":[28],"human-like":[29],"gestures":[30,72],"from":[31],"two-person":[33],"dialogue":[34],"scenario,":[35],"which":[36],"are":[37],"responsive":[38],"interlocutor":[41],"motions":[42],"and":[43,73,87],"accompany":[44],"with":[45],"input":[47],"speech.":[48],"is":[51],"built":[52],"upon":[53],"recent":[55],"DiffGesture":[56],"[39].":[57],"Specifically,":[58],"introduce":[60],"a":[61],"lightweight":[62],"transformer":[63],"encoder":[64],"fuse":[66],"temporal":[68],"relationships":[69],"between":[70,85],"human":[71],"multi-modal":[74],"conditions.":[75],"Moreover,":[76],"adopt":[78],"implicit":[79],"classifier-free":[80],"guidance":[81],"trade":[83],"off":[84],"diversity":[86],"quality.":[89],"According":[90],"collective":[93],"evaluation":[94],"released":[95],"by":[96],"2023,":[99],"our":[100],"demonstrates":[102],"strong":[103],"competitiveness":[104],"in":[105],"appropriateness":[107],"evaluation.":[108]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
