{"id":"https://openalex.org/W4403791551","doi":"https://doi.org/10.1145/3664647.3681392","title":"EGGesture: Entropy-Guided Vector Quantized Variational AutoEncoder for Co-Speech Gesture Generation","display_name":"EGGesture: Entropy-Guided Vector Quantized Variational AutoEncoder for Co-Speech Gesture Generation","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791551","doi":"https://doi.org/10.1145/3664647.3681392"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681392","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681392","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5113883428","display_name":"Yao Xiao","orcid":"https://orcid.org/0000-0001-6639-7387"},"institutions":[{"id":"https://openalex.org/I174104030","display_name":"Taiyuan Normal University","ror":"https://ror.org/051k00p03","country_code":"CN","type":"education","lineage":["https://openalex.org/I174104030"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yiyong Xiao","raw_affiliation_strings":["Taiyuan Normal University, Taiyuan, China"],"affiliations":[{"raw_affiliation_string":"Taiyuan Normal University, Taiyuan, China","institution_ids":["https://openalex.org/I174104030"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010533974","display_name":"Kai Shu","orcid":"https://orcid.org/0009-0007-3302-6003"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kai Shu","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028855371","display_name":"Haoyi Zhang","orcid":"https://orcid.org/0009-0009-3693-786X"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyi Zhang","raw_affiliation_strings":["Xi'an Jiaotong-Liverpool University, SuZhou, China"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong-Liverpool University, SuZhou, China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101341072","display_name":"Baohua Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I168337820","display_name":"Chongqing University of Science and Technology","ror":"https://ror.org/03n3v6d52","country_code":"CN","type":"education","lineage":["https://openalex.org/I168337820"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baohua Yin","raw_affiliation_strings":["Chongqing University of Science & Technology, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Chongqing University of Science & Technology, Shanghai, China","institution_ids":["https://openalex.org/I168337820"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114416524","display_name":"Wai Seng Cheang","orcid":null},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wai Seng Cheang","raw_affiliation_strings":["King's College London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"King's College London, London, United Kingdom","institution_ids":["https://openalex.org/I183935753"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017911557","display_name":"Haoyang Wang","orcid":"https://orcid.org/0009-0003-9569-338X"},"institutions":[{"id":"https://openalex.org/I173963315","display_name":"St. Cloud State University","ror":"https://ror.org/016czhx14","country_code":"US","type":"education","lineage":["https://openalex.org/I173963315","https://openalex.org/I91221267"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haoyang Wang","raw_affiliation_strings":["St.Cloud State University, St.Cloud, MN, USA"],"affiliations":[{"raw_affiliation_string":"St.Cloud State University, St.Cloud, MN, USA","institution_ids":["https://openalex.org/I173963315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012051562","display_name":"Jiechao Gao","orcid":"https://orcid.org/0000-0003-0628-1416"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiechao Gao","raw_affiliation_strings":["University of Virginia, Charlottesville, VA, USA"],"affiliations":[{"raw_affiliation_string":"University of Virginia, Charlottesville, VA, USA","institution_ids":["https://openalex.org/I51556381"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5113883428"],"corresponding_institution_ids":["https://openalex.org/I174104030"],"apc_list":null,"apc_paid":null,"fwci":1.3901,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.84878968,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"6113","last_page":"6122"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9991999864578247,"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":0.9991999864578247,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9980999827384949,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9955999851226807,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.9303966760635376},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5509240031242371},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5465121865272522},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.5002944469451904},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49003875255584717},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4556865692138672},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.20415544509887695},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.14622053503990173}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.9303966760635376},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5509240031242371},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5465121865272522},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.5002944469451904},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49003875255584717},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4556865692138672},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.20415544509887695},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.14622053503990173},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681392","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681392","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2132791018","https://openalex.org/W2194775991","https://openalex.org/W2440599146","https://openalex.org/W2767106145","https://openalex.org/W2901285216","https://openalex.org/W2945629925","https://openalex.org/W2962795401","https://openalex.org/W2963351448","https://openalex.org/W2963691377","https://openalex.org/W2967443589","https://openalex.org/W2978956737","https://openalex.org/W3025893035","https://openalex.org/W3042594325","https://openalex.org/W3083173864","https://openalex.org/W3091564954","https://openalex.org/W3107914916","https://openalex.org/W3125775899","https://openalex.org/W4221142137","https://openalex.org/W4230429791","https://openalex.org/W4303448003","https://openalex.org/W4304080460","https://openalex.org/W4312674262","https://openalex.org/W4312936899","https://openalex.org/W4372183701","https://openalex.org/W4386066602","https://openalex.org/W4386075984","https://openalex.org/W4386076103","https://openalex.org/W4386076137","https://openalex.org/W4387010256","https://openalex.org/W4389518867","https://openalex.org/W4402727140"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2159052453","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W4386815338","https://openalex.org/W2145836866","https://openalex.org/W4220775285"],"abstract_inverted_index":{"Co-Speech":[0,65],"gesture":[1,8,145],"generation":[2],"encounters":[3],"challenges":[4],"with":[5],"imbalanced,":[6,42],"long-tailed":[7],"distributions.":[9],"While":[10],"recent":[11],"methods":[12],"typically":[13],"address":[14,58],"this":[15,60],"by":[16],"employing":[17],"Vector":[18],"Quantized":[19],"Variational":[20],"Autoencoder":[21],"(VQ-VAE),":[22],"encode":[23],"gestures":[24],"into":[25],"a":[26,112,137],"codebook":[27,30,44,80,87,107,117,134],"and":[28,82,102,110,147,158,167],"classify":[29],"indices":[31,81],"based":[32],"on":[33,155],"audio":[34],"or":[35],"text":[36],"cues.":[37],"However,":[38],"due":[39],"to":[40,47,74,119],"the":[41,43,63,77,122,129,133,140,143,148,151,156],"classification":[45,123,152],"tends":[46],"bias":[48],"towards":[49],"majority":[50],"gestures,":[51],"neglecting":[52],"semantically":[53],"rich":[54],"minority":[55],"gestures.":[56],"To":[57],"this,":[59],"paper":[61],"proposes":[62],"Entropy-Guided":[64,72],"Gesture":[66],"Generation":[67],"(EGGesture).":[68],"EGGesture":[69],"leverages":[70],"an":[71],"VQ-VAE":[73],"jointly":[75],"optimizes":[76],"distribution":[78,108],"of":[79,92,132,142,150],"adjusts":[83],"loss":[84,124],"weights":[85],"for":[86,97],"index":[88],"classification,":[89],"which":[90],"consists":[91],"a)":[93],"A":[94],"differentiable":[95],"approach":[96],"entropy":[98,118],"computation":[99],"using":[100],"Gumbel-Softmax":[101],"cosine":[103],"similarity,":[104],"facilitating":[105],"online":[106],"optimization,":[109],"b)":[111],"strategy":[113],"that":[114],"utilizes":[115],"computed":[116],"collaboratively":[120],"guide":[121],"weighting.":[125],"These":[126],"designs":[127],"enable":[128],"dynamic":[130],"refinement":[131],"utilization,":[135],"striking":[136],"balance":[138],"between":[139],"quality":[141],"learned":[144],"representation":[146],"accuracy":[149],"phase.":[153],"Experiments":[154],"Trinity":[157],"BEAT":[159],"datasets":[160],"demonstrate":[161],"EGGesture's":[162],"state-of-the-art":[163],"performance":[164],"both":[165],"qualitatively":[166],"quantitatively.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}