{"id":"https://openalex.org/W4403791249","doi":"https://doi.org/10.1145/3664647.3680892","title":"Emphasizing Semantic Consistency of Salient Posture for Speech-Driven Gesture Generation","display_name":"Emphasizing Semantic Consistency of Salient Posture for Speech-Driven Gesture Generation","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791249","doi":"https://doi.org/10.1145/3664647.3680892"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680892","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680892","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":"conference-paper","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/A5034807446","display_name":"Fengqi Liu","orcid":"https://orcid.org/0000-0002-1919-2167"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengqi Liu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1919-2167","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035451668","display_name":"Hexiang Wang","orcid":"https://orcid.org/0009-0000-0969-8167"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hexiang Wang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0000-0969-8167","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074868631","display_name":"Jingyu Gong","orcid":"https://orcid.org/0000-0002-4536-0953"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyu Gong","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-4536-0953","affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054879013","display_name":"Ran Yi","orcid":"https://orcid.org/0000-0003-1858-3358"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ran Yi","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-1858-3358","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031210225","display_name":"Qianyu Zhou","orcid":"https://orcid.org/0000-0002-5331-050X"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianyu Zhou","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-5331-050X","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019288783","display_name":"Xuequan Lu","orcid":"https://orcid.org/0000-0003-0959-408X"},"institutions":[{"id":"https://openalex.org/I196829312","display_name":"La Trobe University","ror":"https://ror.org/01rxfrp27","country_code":"AU","type":"education","lineage":["https://openalex.org/I196829312"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xuequan Lu","raw_affiliation_strings":["La Trobe University, Melbourne, Australia"],"raw_orcid":"https://orcid.org/0000-0003-0959-408X","affiliations":[{"raw_affiliation_string":"La Trobe University, Melbourne, Australia","institution_ids":["https://openalex.org/I196829312"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084252480","display_name":"Jiangbo Lu","orcid":"https://orcid.org/0000-0002-0048-3140"},"institutions":[{"id":"https://openalex.org/I4210089559","display_name":"Shenzhen Metro (China)","ror":"https://ror.org/008hpge95","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210089559"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangbo Lu","raw_affiliation_strings":["SmartMore Corporation, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-0048-3140","affiliations":[{"raw_affiliation_string":"SmartMore Corporation, Shenzhen, China","institution_ids":["https://openalex.org/I4210089559"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084218062","display_name":"Lizhuang Ma","orcid":"https://orcid.org/0000-0003-1653-4341"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lizhuang Ma","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-1653-4341","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7027","last_page":"7035"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9994000196456909,"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":0.9994000196456909,"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/T11285","display_name":"Hearing Impairment and Communication","score":0.993399977684021,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9911999702453613,"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":0.768212080001831},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.6528204679489136},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.6362961530685425},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6284621953964233},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4701806604862213},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4673025608062744},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4194180369377136},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3677805960178375}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.768212080001831},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.6528204679489136},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.6362961530685425},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6284621953964233},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4701806604862213},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4673025608062744},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4194180369377136},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3677805960178375}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3680892","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680892","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":[{"display_name":"Reduced inequalities","score":0.47999998927116394,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W639218804","https://openalex.org/W2007337857","https://openalex.org/W2008208299","https://openalex.org/W2110934250","https://openalex.org/W2132891289","https://openalex.org/W2135431835","https://openalex.org/W2138092272","https://openalex.org/W2151215842","https://openalex.org/W2164489414","https://openalex.org/W2341058432","https://openalex.org/W2539222059","https://openalex.org/W2604379605","https://openalex.org/W2766042539","https://openalex.org/W2777342313","https://openalex.org/W2780124704","https://openalex.org/W2943165117","https://openalex.org/W2945629925","https://openalex.org/W2962730651","https://openalex.org/W2962795401","https://openalex.org/W2963524571","https://openalex.org/W2963610939","https://openalex.org/W2967443589","https://openalex.org/W2982625143","https://openalex.org/W2991506670","https://openalex.org/W3083173864","https://openalex.org/W3102619627","https://openalex.org/W3107914916","https://openalex.org/W3110095664","https://openalex.org/W3115266783","https://openalex.org/W3125775899","https://openalex.org/W3134566480","https://openalex.org/W3194872882","https://openalex.org/W4200554356","https://openalex.org/W4226420613","https://openalex.org/W4312674262","https://openalex.org/W4312719027","https://openalex.org/W4386076103"],"related_works":["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","https://openalex.org/W1974473538","https://openalex.org/W2020010749","https://openalex.org/W2796116650"],"abstract_inverted_index":{"Speech-driven":[0],"gesture":[1,7,29,53,154,164],"generation":[2,54],"aims":[3],"at":[4],"synthesizing":[5],"a":[6,23,50,68,97,111],"sequence":[8],"synchronized":[9],"with":[10,42],"the":[11,28,32,58,73,83,103,120,128,134,170,176],"input":[12],"speech":[13,138],"signal.":[14],"Previous":[15],"methods":[16],"leverage":[17],"neural":[18],"networks":[19],"to":[20,27,40,81,92,114,123,144,149],"directly":[21],"map":[22],"compact":[24],"audio":[25,77,146],"representation":[26,75],"sequence,":[30],"ignoring":[31],"semantic":[33,59,85,94,104],"association":[34,86],"of":[35,61,76,106,137,172],"different":[36],"modalities":[37],"and":[38,78,90,118,133,152,156,162],"failing":[39],"deal":[41],"salient":[43,62,107,116,131],"gestures.":[44],"In":[45,140],"this":[46],"paper,":[47],"we":[48,65,101,142],"propose":[49,91,143],"novel":[51],"speech-driven":[52],"method":[55,174],"by":[56,109],"emphasizing":[57],"consistency":[60,95,98,105,121],"posture.":[63],"Specifically,":[64],"first":[66],"learn":[67],"joint":[69],"manifold":[70],"space":[71],"for":[72,160],"individual":[74],"body":[79,153,163],"pose":[80],"exploit":[82],"inherent":[84],"between":[87,130],"two":[88],"modalities,":[89],"enforce":[93],"via":[96],"loss.":[99],"Furthermore,":[100],"emphasize":[102],"postures":[108,132],"introducing":[110],"weakly-supervised":[112],"detector":[113],"identify":[115],"postures,":[117],"reweighting":[119],"loss":[122],"focus":[124],"more":[125],"on":[126],"learning":[127],"correspondence":[129],"high-level":[135],"semantics":[136],"content.":[139],"addition,":[141],"extract":[145],"features":[147],"dedicated":[148],"facial":[150],"expression":[151],"separately,":[155],"design":[157],"separate":[158],"branches":[159],"face":[161],"synthesis.":[165],"Extensive":[166],"experimental":[167],"results":[168],"demonstrate":[169],"superiority":[171],"our":[173],"over":[175],"state-of-the-art":[177],"approaches.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}