{"id":"https://openalex.org/W4285736196","doi":"https://doi.org/10.24963/ijcai.2022/863","title":"Text/Speech-Driven Full-Body Animation","display_name":"Text/Speech-Driven Full-Body Animation","publication_year":2022,"publication_date":"2022-07-01","ids":{"openalex":"https://openalex.org/W4285736196","doi":"https://doi.org/10.24963/ijcai.2022/863"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2022/863","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/863","pdf_url":"https://www.ijcai.org/proceedings/2022/0863.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.ijcai.org/proceedings/2022/0863.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046754672","display_name":"Wenlin Zhuang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenlin Zhuang","raw_affiliation_strings":["Alibaba Group","XR Lab, Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]},{"raw_affiliation_string":"XR Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026142528","display_name":"Jinwei Qi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jinwei Qi","raw_affiliation_strings":["Alibaba Group","XR Lab, Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]},{"raw_affiliation_string":"XR Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100364185","display_name":"Peng Zhang","orcid":"https://orcid.org/0000-0002-8403-8289"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peng Zhang","raw_affiliation_strings":["Alibaba","XR Lab, Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba","institution_ids":[]},{"raw_affiliation_string":"XR Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102795236","display_name":"Bang Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY","US"],"is_corresponding":false,"raw_author_name":"Bang Zhang","raw_affiliation_strings":["Damo Academy Alibaba","XR Lab, Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Damo Academy Alibaba","institution_ids":["https://openalex.org/I4210086143"]},{"raw_affiliation_string":"XR Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100757137","display_name":"Ping Tan","orcid":"https://orcid.org/0000-0002-3327-5532"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ping Tan","raw_affiliation_strings":["Alibaba","XR Lab, Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba","institution_ids":[]},{"raw_affiliation_string":"XR Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5026142528"],"corresponding_institution_ids":["https://openalex.org/I4210095624"],"apc_list":null,"apc_paid":null,"fwci":2.4795,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.90577599,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"5956","last_page":"5959"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.998199999332428,"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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9980000257492065,"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/avatar","display_name":"Avatar","score":0.8997561931610107},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.8875008821487427},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.8363195657730103},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8234935998916626},{"id":"https://openalex.org/keywords/skeletal-animation","display_name":"Skeletal animation","score":0.6842941045761108},{"id":"https://openalex.org/keywords/viseme","display_name":"Viseme","score":0.5544695258140564},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.49127835035324097},{"id":"https://openalex.org/keywords/facial-motion-capture","display_name":"Facial motion capture","score":0.43258345127105713},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.425988107919693},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.3645913004875183},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3619682490825653},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.34757497906684875},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.34595802426338196},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3437475562095642},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2647589445114136},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.1242329478263855},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.08242034912109375},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.07190403342247009},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.05836471915245056}],"concepts":[{"id":"https://openalex.org/C2777365542","wikidata":"https://www.wikidata.org/wiki/Q83090","display_name":"Avatar","level":2,"score":0.8997561931610107},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.8875008821487427},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.8363195657730103},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8234935998916626},{"id":"https://openalex.org/C44710944","wikidata":"https://www.wikidata.org/wiki/Q1813564","display_name":"Skeletal animation","level":5,"score":0.6842941045761108},{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.5544695258140564},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.49127835035324097},{"id":"https://openalex.org/C98907195","wikidata":"https://www.wikidata.org/wiki/Q5428562","display_name":"Facial motion capture","level":5,"score":0.43258345127105713},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.425988107919693},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3645913004875183},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3619682490825653},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34757497906684875},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.34595802426338196},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3437475562095642},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2647589445114136},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.1242329478263855},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.08242034912109375},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.07190403342247009},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.05836471915245056},{"id":"https://openalex.org/C4641261","wikidata":"https://www.wikidata.org/wiki/Q11681085","display_name":"Face detection","level":4,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2022/863","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/863","pdf_url":"https://www.ijcai.org/proceedings/2022/0863.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2022/863","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/863","pdf_url":"https://www.ijcai.org/proceedings/2022/0863.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285736196.pdf","grobid_xml":"https://content.openalex.org/works/W4285736196.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W2191779130","https://openalex.org/W2739192055","https://openalex.org/W2884460600","https://openalex.org/W2944294033","https://openalex.org/W2962795401","https://openalex.org/W2979157532","https://openalex.org/W3009042479","https://openalex.org/W3172764674","https://openalex.org/W3205510305","https://openalex.org/W3207299135"],"related_works":["https://openalex.org/W1544039745","https://openalex.org/W615219140","https://openalex.org/W2295574089","https://openalex.org/W2139716748","https://openalex.org/W2130702999","https://openalex.org/W2040366276","https://openalex.org/W2188148675","https://openalex.org/W2401874398","https://openalex.org/W4211065946","https://openalex.org/W2196799208"],"abstract_inverted_index":{"Due":[0],"to":[1,50,69],"the":[2,31,71,84],"increasing":[3],"demand":[4],"in":[5],"films":[6],"and":[7,33,40,48,65,79,91],"games,":[8],"synthesizing":[9,62],"3D":[10],"avatar":[11,76,86],"animation":[12,27,64,77],"has":[13],"attracted":[14],"much":[15],"attention":[16],"recently.":[17],"In":[18],"this":[19],"work,":[20],"we":[21],"present":[22],"a":[23,52,58,66],"production-ready":[24],"text/speech-driven":[25],"full-body":[26],"synthesis":[28],"system.":[29],"Given":[30],"text":[32],"corresponding":[34],"speech,":[35],"our":[36],"system":[37],"synthesizes":[38],"face":[39],"body":[41],"animations":[42,87],"simultaneously,":[43],"which":[44,73],"are":[45,88],"then":[46],"skinned":[47],"rendered":[49],"obtain":[51],"video":[53],"stream":[54],"output.":[55],"We":[56],"adopt":[57],"learning-based":[59],"approach":[60,68],"for":[61],"facial":[63],"graph-based":[67],"animate":[70],"body,":[72],"generates":[74],"high-quality":[75],"efficiently":[78],"robustly.":[80],"Our":[81],"results":[82],"demonstrate":[83],"generated":[85],"realistic,":[89],"diverse":[90],"highly":[92],"text/speech-correlated.":[93]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}
