{"id":"https://openalex.org/W4403445354","doi":"https://doi.org/10.1145/3664647.3680684","title":"MDT-A2G: Exploring Masked Diffusion Transformers for Co-Speech Gesture Generation","display_name":"MDT-A2G: Exploring Masked Diffusion Transformers for Co-Speech Gesture Generation","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403445354","doi":"https://doi.org/10.1145/3664647.3680684"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680684","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680684","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":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2408.03312","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111968616","display_name":"Xiaofeng Mao","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaofeng Mao","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0004-2666-753X","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101637347","display_name":"Zhengkai Jiang","orcid":"https://orcid.org/0000-0003-4064-994X"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengkai Jiang","raw_affiliation_strings":["Tencent Youtu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-4064-994X","affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081181176","display_name":"Qilin Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qilin Wang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0002-0788-3259","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111284194","display_name":"Chencan Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chencan Fu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0005-3732-3035","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021861529","display_name":"Jiangning Zhang","orcid":"https://orcid.org/0000-0001-8891-6766"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangning Zhang","raw_affiliation_strings":["Tencent Youtu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-8891-6766","affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025002931","display_name":"Jiafu Wu","orcid":"https://orcid.org/0000-0002-1036-5076"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiafu Wu","raw_affiliation_strings":["Tencent Youtu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1036-5076","affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028731909","display_name":"Yabiao Wang","orcid":"https://orcid.org/0000-0002-6592-8411"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yabiao Wang","raw_affiliation_strings":["Zhejiang University & Tencent Youtu Lab, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-6592-8411","affiliations":[{"raw_affiliation_string":"Zhejiang University & Tencent Youtu Lab, Hangzhou, China","institution_ids":["https://openalex.org/I2250653659","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023834700","display_name":"Chengjie Wang","orcid":"https://orcid.org/0000-0003-4216-8090"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengjie Wang","raw_affiliation_strings":["Tencent Youtu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-4216-8090","affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wei Li","orcid":"https://orcid.org/0009-0004-8308-6360"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Li","raw_affiliation_strings":["Vivo Communication Technology Co. Ltd, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0004-8308-6360","affiliations":[{"raw_affiliation_string":"Vivo Communication Technology Co. Ltd, Shanghai, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057267422","display_name":"Mingmin Chi","orcid":"https://orcid.org/0000-0003-2650-4146"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingmin Chi","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-2650-4146","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5111968616"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":1.6249,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.84746033,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3266","last_page":"3274"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9984999895095825,"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":0.9984999895095825,"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/T10860","display_name":"Speech and Audio Processing","score":0.9980000257492065,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9973999857902527,"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/computer-science","display_name":"Computer science","score":0.7600868940353394},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6664285063743591},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.6505401134490967},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5256391763687134},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5248363614082336},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.524422287940979},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4835905432701111},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4776628911495209},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4361017942428589},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10416573286056519},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.08059561252593994},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.06697279214859009}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7600868940353394},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6664285063743591},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.6505401134490967},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5256391763687134},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5248363614082336},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.524422287940979},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4835905432701111},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4776628911495209},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4361017942428589},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10416573286056519},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.08059561252593994},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.06697279214859009},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3664647.3680684","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680684","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"},{"id":"pmh:oai:arXiv.org:2408.03312","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.03312","pdf_url":"https://arxiv.org/pdf/2408.03312","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:2408.03312","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.03312","pdf_url":"https://arxiv.org/pdf/2408.03312","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/G2728175297","display_name":null,"funder_award_id":"62171139","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":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403445354.pdf"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W2612649659","https://openalex.org/W2962795401","https://openalex.org/W3083173864","https://openalex.org/W3125775899","https://openalex.org/W3204221554","https://openalex.org/W3209984917","https://openalex.org/W4221142137","https://openalex.org/W4230429791","https://openalex.org/W4285483774","https://openalex.org/W4304080460","https://openalex.org/W4312674262","https://openalex.org/W4313156423","https://openalex.org/W4377010269","https://openalex.org/W4382457661","https://openalex.org/W4385284180","https://openalex.org/W4385764101","https://openalex.org/W4386075984","https://openalex.org/W4386076103","https://openalex.org/W4386270206","https://openalex.org/W4386755513","https://openalex.org/W4390872297","https://openalex.org/W4390873332","https://openalex.org/W4391305822","https://openalex.org/W4392904562","https://openalex.org/W4402741610","https://openalex.org/W6840200333"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2027972911","https://openalex.org/W2157978810","https://openalex.org/W2597809628","https://openalex.org/W2111089054"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,29,181],"the":[3,11,23,26,30,45,82,90,125,159,205],"field":[4],"of":[5,13,25,32,94],"Diffusion":[6,69,104],"Transformers":[7],"have":[8,42],"substantially":[9],"improved":[10],"generation":[12,35],"high-quality":[14],"2D":[15],"images,":[16],"3D":[17,20],"videos,":[18],"and":[19,128,132,148,197],"shapes.":[21],"However,":[22],"effectiveness":[24],"Transformer":[27,70],"architecture":[28],"domain":[31],"co-speech":[33,72],"gesture":[34,73,86,182],"remains":[36],"relatively":[37],"unexplored,":[38],"as":[39,77],"prior":[40],"methodologies":[41],"predominantly":[43],"employed":[44],"Convolutional":[46],"Neural":[47],"Network":[48],"(CNNs)":[49],"or":[50],"simple":[51],"a":[52,66,101,109,169,185],"few":[53],"transformer":[54],"layers.":[55],"In":[56],"an":[57,153,198],"attempt":[58],"to":[59,76,115,130],"bridge":[60],"this":[61],"research":[62],"gap,":[63],"we":[64,99,151],"introduce":[65],"novel":[67,102],"Masked":[68,103],"for":[71],"generation,":[74,183],"referred":[75],"MDT-A2G,":[78],"which":[79],"directly":[80],"implements":[81],"denoising":[83,160],"process":[84,127],"on":[85],"sequences.":[87],"To":[88],"enhance":[89],"contextual":[91],"reasoning":[92],"capability":[93],"temporally":[95],"aligned":[96],"speech-driven":[97],"gestures,":[98,122],"incorporate":[100],"Transformer.":[105],"This":[106],"model":[107,140],"employs":[108],"mask":[110],"modeling":[111],"scheme":[112],"specifically":[113],"designed":[114],"strengthen":[116],"temporal":[117],"relation":[118],"learning":[119,126,186],"among":[120],"sequence":[121],"thereby":[123,167],"expediting":[124],"leading":[129],"coherent":[131],"realistic":[133],"motions.":[134],"Apart":[135],"from":[136],"audio,":[137],"Our":[138,209],"MDT-A2G":[139,179],"also":[141],"integrates":[142],"multi-modal":[143],"information,":[144],"encompassing":[145],"text,":[146],"emotion,":[147],"identity.":[149],"Furthermore,":[150],"propose":[152],"efficient":[154],"inference":[155,199],"strategy":[156],"that":[157,178,188,201],"diminishes":[158],"computation":[161],"by":[162],"leveraging":[163],"previously":[164],"calculated":[165],"results,":[166],"achieving":[168],"speedup":[170],"with":[171],"negligible":[172],"performance":[173],"degradation.":[174],"Experimental":[175],"results":[176],"demonstrate":[177],"excels":[180],"boasting":[184],"speed":[187,200],"is":[189,202,211],"over":[190],"6\u00d7":[191],"faster":[192],"than":[193,204],"traditional":[194],"diffusion":[195,207],"transformers":[196],"5.7\u00d7":[203],"standard":[206],"model.":[208],"code":[210],"available":[212],"at":[213],"https://xiaofenmao.github.io/web-project/MDT-A2G/":[214]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}