{"id":"https://openalex.org/W4403791724","doi":"https://doi.org/10.1145/3664647.3680625","title":"MambaGesture: Enhancing Co-Speech Gesture Generation with Mamba and Disentangled Multi-Modality Fusion","display_name":"MambaGesture: Enhancing Co-Speech Gesture Generation with Mamba and Disentangled Multi-Modality Fusion","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791724","doi":"https://doi.org/10.1145/3664647.3680625"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680625","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3680625","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3664647.3680625?download=true","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":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3664647.3680625?download=true","any_repository_has_fulltext":null},"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":true,"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/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/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/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/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":false,"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/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/A5113233271","display_name":"Weijian Cao","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":"Weijian Cao","raw_affiliation_strings":["Tencent Youtu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0006-2554-1294","affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"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/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"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":["Shanghai Jiao Tong University & Tencent Youtu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-4216-8090","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University & Tencent Youtu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659","https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032461971","display_name":"Yanhao Ge","orcid":"https://orcid.org/0000-0002-5650-5118"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanhao Ge","raw_affiliation_strings":["VIVO, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-5650-5118","affiliations":[{"raw_affiliation_string":"VIVO, Shanghai, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100724297","display_name":"Yong Liu","orcid":"https://orcid.org/0000-0003-4822-8939"},"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, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4822-8939","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5111284194"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":3.7478,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.9337659,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"10794","last_page":"10803"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11285","display_name":"Hearing Impairment and Communication","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T11285","display_name":"Hearing Impairment and Communication","score":0.9990000128746033,"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"}},{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9976999759674072,"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":0.996999979019165,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.7592830657958984},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5950286388397217},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5223320722579956},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5213881134986877},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.44523248076438904},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22373908758163452},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11776399612426758}],"concepts":[{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.7592830657958984},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5950286388397217},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5223320722579956},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5213881134986877},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.44523248076438904},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22373908758163452},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11776399612426758},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3680625","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3680625","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3664647.3680625?download=true","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":{"id":"doi:10.1145/3664647.3680625","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3680625","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3664647.3680625?download=true","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"},"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403791724.pdf"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W114912394","https://openalex.org/W2008208299","https://openalex.org/W2024536104","https://openalex.org/W2126822690","https://openalex.org/W2133826714","https://openalex.org/W2135431835","https://openalex.org/W2612649659","https://openalex.org/W3106624279","https://openalex.org/W3204221554","https://openalex.org/W4214544731","https://openalex.org/W4221142137","https://openalex.org/W4230429791","https://openalex.org/W4304080460","https://openalex.org/W4312674262","https://openalex.org/W4382457661","https://openalex.org/W4385764101","https://openalex.org/W4386075984","https://openalex.org/W4386076103","https://openalex.org/W4386270206","https://openalex.org/W4386755513","https://openalex.org/W4388505252","https://openalex.org/W4390872470","https://openalex.org/W4391305822","https://openalex.org/W4392904562","https://openalex.org/W4402703119","https://openalex.org/W4402741610"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2537963312","https://openalex.org/W2066003895","https://openalex.org/W2537762514","https://openalex.org/W2349788282","https://openalex.org/W577271088","https://openalex.org/W2120801881","https://openalex.org/W1982853263"],"abstract_inverted_index":{"Co-speech":[0],"gesture":[1,152],"generation":[2],"is":[3],"crucial":[4],"for":[5],"producing":[6],"synchronized":[7],"and":[8,40,47,107,117,123,144],"realistic":[9],"human":[10],"gestures":[11,119],"that":[12],"accompany":[13],"speech,":[14],"enhancing":[15,94],"the":[16,78,84,88,95,114,130],"animation":[17],"of":[18,38,83,91,98],"lifelike":[19],"avatars":[20],"in":[21,44,137,150],"virtual":[22],"environments.":[23],"While":[24],"diffusion":[25],"models":[26],"have":[27],"shown":[28],"impressive":[29],"capabilities,":[30],"current":[31],"approaches":[32],"often":[33],"overlook":[34],"a":[35,58,62,68],"wide":[36],"range":[37],"modalities":[39],"their":[41],"interactions,":[42],"resulting":[43],"less":[45],"dynamic":[46],"contextually":[48],"varied":[49],"gestures.":[50,100],"To":[51],"address":[52],"these":[53],"challenges,":[54],"we":[55],"present":[56],"MambaGesture,":[57],"novel":[59],"framework":[60],"integrating":[61],"Mamba-based":[63],"attention":[64,92],"block,":[65],"MambaAttn,":[66],"with":[67,87,120],"multi-modality":[69],"feature":[70],"fusion":[71,115],"module,":[72],"SEAD.":[73],"The":[74],"MambaAttn":[75],"block":[76],"combines":[77],"sequential":[79],"data":[80],"processing":[81],"strengths":[82],"Mamba":[85],"model":[86],"contextual":[89],"richness":[90],"mechanisms,":[93],"temporal":[96],"coherence":[97],"generated":[99],"SEAD":[101],"adeptly":[102],"fuses":[103],"audio,":[104],"text,":[105],"style,":[106],"emotion":[108],"modalities,":[109],"employing":[110],"disentanglement":[111],"to":[112],"deepen":[113],"process":[116],"yield":[118],"greater":[121],"realism":[122],"diversity.":[124],"Our":[125],"approach,":[126],"rigorously":[127],"evaluated":[128],"on":[129],"multi-modal":[131],"BEAT":[132],"dataset,":[133],"demonstrates":[134],"significant":[135],"improvements":[136],"Fr\u00e9chet":[138],"Gesture":[139],"Distance":[140],"(FGD),":[141],"diversity":[142],"scores,":[143],"beat":[145],"alignment,":[146],"achieving":[147],"state-of-the-art":[148],"performance":[149],"co-speech":[151],"generation.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}