{"id":"https://openalex.org/W4399206662","doi":"https://doi.org/10.1109/tmm.2024.3407692","title":"EmotionGesture: Audio-Driven Diverse Emotional Co-Speech 3D Gesture Generation","display_name":"EmotionGesture: Audio-Driven Diverse Emotional Co-Speech 3D Gesture Generation","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4399206662","doi":"https://doi.org/10.1109/tmm.2024.3407692"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2024.3407692","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3407692","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5026841385","display_name":"Xingqun Qi","orcid":"https://orcid.org/0000-0002-9772-5707"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I4210123119","display_name":"The Academy of Sciences of Hong Kong","ror":"https://ror.org/02w1g8568","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123119"]},{"id":"https://openalex.org/I4210137146","display_name":"Hong Kong Academy of Medicine","ror":"https://ror.org/036b4vb45","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210137146"]},{"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":["CN","HK"],"is_corresponding":true,"raw_author_name":"Xingqun Qi","raw_affiliation_strings":["Academy of Interdisciplinary Studies, The Hong Kong University of Science and Technology, Hong Kong","Academy of Interdisciplinary Studies, The Hong Kong University of Science and Technology, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-9772-5707","affiliations":[{"raw_affiliation_string":"Academy of Interdisciplinary Studies, The Hong Kong University of Science and Technology, Hong Kong","institution_ids":["https://openalex.org/I4210137146","https://openalex.org/I4210123119","https://openalex.org/I200769079","https://openalex.org/I889458895"]},{"raw_affiliation_string":"Academy of Interdisciplinary Studies, The Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100322208","display_name":"Chen Liu","orcid":"https://orcid.org/0000-0003-3159-0034"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Chen Liu","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, The University of Queensland, St Lucia, QLD, Australia"],"raw_orcid":"https://orcid.org/0000-0003-3159-0034","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, The University of Queensland, St Lucia, QLD, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019036797","display_name":"Lincheng Li","orcid":"https://orcid.org/0000-0002-6047-0472"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lincheng Li","raw_affiliation_strings":["NetEase Fuxi AI Lab, Hangzhou, China","NetEase, Fuxi AI Lab, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-6047-0472","affiliations":[{"raw_affiliation_string":"NetEase Fuxi AI Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]},{"raw_affiliation_string":"NetEase, Fuxi AI Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067241967","display_name":"Jie Hou","orcid":"https://orcid.org/0000-0001-5587-0132"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Hou","raw_affiliation_strings":["NetEase Fuxi AI Lab, Hangzhou, China","NetEase, Fuxi AI Lab, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Fuxi AI Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]},{"raw_affiliation_string":"NetEase, Fuxi AI Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063324093","display_name":"Haoran Xin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoran Xin","raw_affiliation_strings":["NetEase Fuxi AI Lab, Hangzhou, China","NetEase, Fuxi AI Lab, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Fuxi AI Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]},{"raw_affiliation_string":"NetEase, Fuxi AI Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003076238","display_name":"Xin Yu","orcid":"https://orcid.org/0000-0002-0269-5649"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xin Yu","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, The University of Queensland, St Lucia, QLD, Australia"],"raw_orcid":"https://orcid.org/0000-0002-0269-5649","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, The University of Queensland, St Lucia, QLD, Australia","institution_ids":["https://openalex.org/I165143802"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5026841385"],"corresponding_institution_ids":["https://openalex.org/I200769079","https://openalex.org/I4210123119","https://openalex.org/I4210137146","https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":9.6477,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.98565624,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"26","issue":null,"first_page":"10420","last_page":"10430"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.988099992275238,"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":0.988099992275238,"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/T12031","display_name":"Speech and dialogue systems","score":0.9771999716758728,"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/T11285","display_name":"Hearing Impairment and Communication","score":0.9657999873161316,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8513028621673584},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6919146776199341},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.6824427247047424},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3470461964607239},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3413650393486023},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28448399901390076}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8513028621673584},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6919146776199341},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.6824427247047424},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3470461964607239},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3413650393486023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28448399901390076}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmm.2024.3407692","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3407692","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-138842","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-138842","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":67,"referenced_works":["https://openalex.org/W215088529","https://openalex.org/W1614298861","https://openalex.org/W1821462560","https://openalex.org/W1974604838","https://openalex.org/W2007337857","https://openalex.org/W2008208299","https://openalex.org/W2012856192","https://openalex.org/W2024536104","https://openalex.org/W2132891289","https://openalex.org/W2140304104","https://openalex.org/W2169262156","https://openalex.org/W2497597915","https://openalex.org/W2532511219","https://openalex.org/W2884374054","https://openalex.org/W2949924544","https://openalex.org/W2962795401","https://openalex.org/W2963355540","https://openalex.org/W2967443589","https://openalex.org/W2982625143","https://openalex.org/W2983925976","https://openalex.org/W3013020904","https://openalex.org/W3035054804","https://openalex.org/W3083173864","https://openalex.org/W3110095664","https://openalex.org/W3118288752","https://openalex.org/W3121072133","https://openalex.org/W3125775899","https://openalex.org/W3136525061","https://openalex.org/W3184385152","https://openalex.org/W3203663566","https://openalex.org/W4221142137","https://openalex.org/W4225145829","https://openalex.org/W4230429791","https://openalex.org/W4283780626","https://openalex.org/W4297808394","https://openalex.org/W4298186886","https://openalex.org/W4303448003","https://openalex.org/W4304080460","https://openalex.org/W4304087182","https://openalex.org/W4310831393","https://openalex.org/W4312238253","https://openalex.org/W4312309978","https://openalex.org/W4312429630","https://openalex.org/W4312492610","https://openalex.org/W4312662707","https://openalex.org/W4312674262","https://openalex.org/W4312719027","https://openalex.org/W4312774977","https://openalex.org/W4385245566","https://openalex.org/W4385284180","https://openalex.org/W4385764101","https://openalex.org/W4386075984","https://openalex.org/W4386076103","https://openalex.org/W4386076313","https://openalex.org/W4386083126","https://openalex.org/W4390873634","https://openalex.org/W6636510571","https://openalex.org/W6638523607","https://openalex.org/W6680369585","https://openalex.org/W6687045409","https://openalex.org/W6779823529","https://openalex.org/W6787473312","https://openalex.org/W6844194202","https://openalex.org/W6844223692","https://openalex.org/W6846112426","https://openalex.org/W6847123917","https://openalex.org/W6996224657"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2066003895","https://openalex.org/W2537963312","https://openalex.org/W2537762514","https://openalex.org/W2349788282","https://openalex.org/W577271088","https://openalex.org/W2120801881","https://openalex.org/W1982853263","https://openalex.org/W1974473538"],"abstract_inverted_index":{"Generating":[0],"vivid":[1,70,252],"and":[2,71,103,147,164,253,261],"diverse":[3,72,239,254],"3D":[4,75,171,257],"co-speech":[5,47,74,172,256],"gestures":[6,22,76,131,173,221],"is":[7,39,81],"crucial":[8],"for":[9,68,216],"various":[10],"applications":[11],"in":[12,88],"animating":[13],"virtual":[14],"avatars.":[15],"While":[16],"most":[17],"existing":[18,183],"methods":[19],"can":[20],"generate":[21,129,170,238],"from":[23,77,132],"audio":[24,104,165],"directly,":[25],"they":[26],"usually":[27],"overlook":[28],"that":[29,245],"<bold":[30,36,55,61],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[31,34,37,56,59,62,271],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"/>":[32,38,57,63],"<italic":[33,58],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><b>emotion</b></i>":[35],"one":[40],"of":[41,45,182],"the":[42,85,101,133,140,144,148,153,180,249,267],"key":[43],"factors":[44],"authentic":[46],"gesture":[48],"generation.":[49],"In":[50],"this":[51,189,198],"work,":[52],"we":[53,91,119,159,168,200,210,226],"propose":[54,120,201],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><b>EmotionGesture</b></i>":[60],",":[64],"a":[65,114,175],"novel":[66],"framework":[67,247],"synthesizing":[69],"emotional":[73,240,255],"audio.":[78],"Considering":[79],"emotion":[80,102,233],"often":[82,185],"entangled":[83],"with":[84],"rhythmic":[86],"beat":[87,105,166],"speech":[89],"audio,":[90],"first":[92],"develop":[93],"an":[94,121,202,228],"Emotion-Beat":[95],"Mining":[96],"module":[97],"(EBM)":[98],"to":[99,128,192,214,222,231,237],"extract":[100],"features":[106],"as":[107,109],"well":[108],"model":[110,211],"their":[111],"correlation":[112],"via":[113],"transcript-based":[115],"visual-rhythm":[116],"alignment.":[117],"Then,":[118],"initial":[122,135,145],"pose":[123,156,161],"based":[124],"Spatial-Temporal":[125],"Prompter":[126],"(STP)":[127],"future":[130,149],"given":[134],"poses.":[136],"STP":[137],"effectively":[138],"models":[139],"spatial-temporal":[141,154],"correlations":[142],"between":[143],"poses":[146,181],"gestures,":[150],"thus":[151],"producing":[152],"coherent":[155],"prompt.":[157],"Once":[158],"obtain":[160],"prompts,":[162],"emotion,":[163],"features,":[167,234],"will":[169,263],"through":[174],"transformer":[176],"architecture.":[177],"However,":[178],"considering":[179],"datasets":[184],"contain":[186],"jittering":[187,217],"effects,":[188],"would":[190],"lead":[191],"generating":[193],"unstable":[194],"gestures.":[195,258],"To":[196],"address":[197],"issue,":[199],"effective":[203],"objective":[204],"function,":[205],"dubbed":[206],"Motion-Smooth":[207],"Loss.":[208],"Specifically,":[209],"motion":[212],"offset":[213],"compensate":[215],"ground-truth":[218],"by":[219],"forcing":[220],"be":[223,264],"smooth.":[224],"Last,":[225],"present":[227],"emotion-conditioned":[229],"VAE":[230],"sample":[232],"enabling":[235],"us":[236],"results.":[241],"Extensive":[242],"experiments":[243],"demonstrate":[244],"our":[246],"outperforms":[248],"state-of-the-art,":[250],"achieving":[251],"Our":[259],"code":[260],"dataset":[262],"released":[265],"on":[266],"project":[268],"page:":[269],"<uri":[270],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://xingqunqi-lab.github.io/Emotion-Gesture-Web/</uri>":[272]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}