{"id":"https://openalex.org/W7131908978","doi":"https://doi.org/10.1109/tmm.2026.3668541","title":"MambaGesture2: Co-Speech Gesture Generation via Hierarchical Fusion and Spatiotemporal Aggregation","display_name":"MambaGesture2: Co-Speech Gesture Generation via Hierarchical Fusion and Spatiotemporal Aggregation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7131908978","doi":"https://doi.org/10.1109/tmm.2026.3668541"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2026.3668541","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3668541","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/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"],"raw_orcid":"https://orcid.org/0009-0005-3732-3035","affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yabiao Wang","orcid":"https://orcid.org/0000-0002-6592-8411"},"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":"Yabiao Wang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":"https://orcid.org/0000-0002-6592-8411","affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126979755","display_name":"Haoyang He","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":"Haoyang He","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":"https://orcid.org/0009-0003-2771-5196","affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shuo Wang","orcid":"https://orcid.org/0009-0008-3437-3565"},"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":"Shuo Wang","raw_affiliation_strings":["YouTu Lab, Tencent"],"raw_orcid":"https://orcid.org/0009-0008-3437-3565","affiliations":[{"raw_affiliation_string":"YouTu Lab, Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127195901","display_name":"Chengjie Wang","orcid":null},"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":["YouTu Lab, Tencent"],"raw_orcid":"https://orcid.org/0000-0003-4216-8090","affiliations":[{"raw_affiliation_string":"YouTu Lab, Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121717547","display_name":"Ying Tai","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Tai","raw_affiliation_strings":["Nanjing University"],"raw_orcid":"https://orcid.org/0000-0002-4665-6852","affiliations":[{"raw_affiliation_string":"Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127379373","display_name":"Yong Liu","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":"Yong Liu","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":"https://orcid.org/0000-0003-4822-8939","affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","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":["YouTu Lab, Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"YouTu Lab, Tencent","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18122195,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"6266","last_page":"6274"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.5016999840736389,"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":0.5016999840736389,"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":0.17679999768733978,"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":0.07419999688863754,"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/gesture","display_name":"Gesture","score":0.6696000099182129},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4878999888896942},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.45989999175071716},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45320001244544983},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.4399999976158142},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.43050000071525574},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.42559999227523804},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4101000130176544},{"id":"https://openalex.org/keywords/hierarchical-database-model","display_name":"Hierarchical database model","score":0.3734999895095825}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.880299985408783},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.6696000099182129},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.541100025177002},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4878999888896942},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.45989999175071716},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45320001244544983},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.4399999976158142},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.43050000071525574},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.42559999227523804},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4101000130176544},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.3734999895095825},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3684999942779541},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3361999988555908},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3276999890804291},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.28519999980926514},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.26179999113082886},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.2578999996185303}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2026.3668541","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3668541","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G475776987","display_name":null,"funder_award_id":"2025YFF0511302","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W3002310794","https://openalex.org/W3014641072","https://openalex.org/W3083173864","https://openalex.org/W3204221554","https://openalex.org/W4221142137","https://openalex.org/W4230429791","https://openalex.org/W4283712710","https://openalex.org/W4296031724","https://openalex.org/W4308222684","https://openalex.org/W4312462635","https://openalex.org/W4385764101","https://openalex.org/W4386075984","https://openalex.org/W4386270206","https://openalex.org/W4389471039","https://openalex.org/W4390423544","https://openalex.org/W4396768801","https://openalex.org/W4399039789","https://openalex.org/W4399206662","https://openalex.org/W4400822426","https://openalex.org/W4402703119","https://openalex.org/W4402727140","https://openalex.org/W4402727590","https://openalex.org/W4402753998","https://openalex.org/W4402951640","https://openalex.org/W4402979917","https://openalex.org/W4403445354","https://openalex.org/W4403791724","https://openalex.org/W4403792047","https://openalex.org/W4404966690","https://openalex.org/W4405908078","https://openalex.org/W4407449402","https://openalex.org/W4409262261","https://openalex.org/W4410991821","https://openalex.org/W4413155986","https://openalex.org/W4414085253","https://openalex.org/W4415797137","https://openalex.org/W4415798278"],"related_works":[],"abstract_inverted_index":{"Co-speech":[0],"gesture":[1,69],"generation":[2],"plays":[3],"a":[4,50,78,83,93],"vital":[5],"role":[6],"in":[7,20,66,188],"producing":[8],"synchronized":[9],"and":[10,68,120,139,157,176,192],"natural":[11],"human":[12],"gestures,":[13],"thereby":[14],"enhancing":[15],"the":[16,43,101,109,113,126,140,154,182],"realism":[17],"of":[18,46,105,112,184],"avatars":[19],"virtual":[21],"environments.":[22],"Although":[23],"diffusion":[24],"models":[25],"have":[26],"shown":[27],"strong":[28],"generative":[29],"capabilities,":[30],"their":[31],"combination":[32],"with":[33,92,108],"transformer-based":[34],"architectures":[35],"often":[36],"incurs":[37],"high":[38],"computational":[39,121],"costs":[40],"due":[41],"to":[42,59,131,146],"quadratic":[44],"complexity":[45,175],"self-attention.":[47],"Moreover,":[48],"as":[49],"temporal":[51,63,118,134],"sequence":[52],"modeling":[53,104],"task,":[54],"existing":[55],"methods":[56],"frequently":[57],"struggle":[58],"effectively":[60],"capture":[61,132],"multi-scale":[62,137],"dynamics":[64],"inherent":[65],"speech":[67],"signals.":[70],"To":[71],"address":[72],"these":[73],"challenges,":[74],"we":[75],"propose":[76],"MambaGesture2,":[77],"novel":[79],"framework":[80],"that":[81,161],"integrates":[82],"Mamba-based":[84],"denoising":[85],"network,":[86],"Hierarchical":[87],"U-Net":[88,114],"Gesture":[89],"Mamba":[90,106],"(HUG-Mamba),":[91],"multimodal":[94],"feature":[95,149],"fusion":[96],"module,":[97],"SEAD.":[98],"HUG-Mamba":[99],"combines":[100],"efficient":[102],"state-space":[103],"blocks":[107],"hierarchical":[110],"sampling":[111],"architecture,":[115],"significantly":[116],"improving":[117],"coherence":[119],"efficiency.":[122],"We":[123],"further":[124],"introduce":[125],"Temporal-Stratified":[127],"Fusion":[128],"(TSF)":[129],"module":[130,145],"diverse":[133],"scales":[135],"via":[136],"learning,":[138],"Spatial-Temporal":[141],"Cascaded":[142],"Aggregation":[143],"(STCA)":[144],"enhance":[147],"spatial-temporal":[148],"aggregation.":[150],"Extensive":[151],"experiments":[152],"on":[153],"multi-modal":[155],"BEAT2":[156],"SHOW":[158],"datasets":[159],"demonstrate":[160],"our":[162,185],"approach":[163],"achieves":[164],"state-of-the-art":[165],"performance":[166],"across":[167],"multiple":[168],"quantitative":[169],"metrics,":[170],"while":[171],"substantially":[172],"reducing":[173],"model":[174],"inference":[177],"time.":[178],"The":[179],"results":[180],"validate":[181],"effectiveness":[183],"architectural":[186],"innovations":[187],"generating":[189],"diverse,":[190],"realistic,":[191],"temporally":[193],"consistent":[194],"co-speech":[195],"gestures.":[196],"Project":[197],"page:https://fcchit.github.io/mambagesture2.":[198]},"counts_by_year":[],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2026-02-28T00:00:00"}