{"id":"https://openalex.org/W4399418417","doi":"https://doi.org/10.1145/3652583.3657625","title":"CLTalk: Speech-Driven 3D Facial Animation with Contrastive Learning","display_name":"CLTalk: Speech-Driven 3D Facial Animation with Contrastive Learning","publication_year":2024,"publication_date":"2024-05-30","ids":{"openalex":"https://openalex.org/W4399418417","doi":"https://doi.org/10.1145/3652583.3657625"},"language":"en","primary_location":{"id":"doi:10.1145/3652583.3657625","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3657625","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3657625","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","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/10.1145/3652583.3657625","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xitie Zhang","orcid":"https://orcid.org/0000-0002-8114-9119"},"institutions":[{"id":"https://openalex.org/I21642278","display_name":"Ningxia University","ror":"https://ror.org/04j7b2v61","country_code":"CN","type":"education","lineage":["https://openalex.org/I21642278"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xitie Zhang","raw_affiliation_strings":["School of Information Engineering, Ningxia University, Yinchuan, Ningxia, China"],"raw_orcid":"https://orcid.org/0000-0002-8114-9119","affiliations":[{"raw_affiliation_string":"School of Information Engineering, Ningxia University, Yinchuan, Ningxia, China","institution_ids":["https://openalex.org/I21642278"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101865021","display_name":"Suping Wu","orcid":"https://orcid.org/0000-0001-5207-1802"},"institutions":[{"id":"https://openalex.org/I21642278","display_name":"Ningxia University","ror":"https://ror.org/04j7b2v61","country_code":"CN","type":"education","lineage":["https://openalex.org/I21642278"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Suping Wu","raw_affiliation_strings":["School of Information Engineering, Ningxia University, Yinchuan, Ningxia, China"],"raw_orcid":"https://orcid.org/0000-0001-5207-1802","affiliations":[{"raw_affiliation_string":"School of Information Engineering, Ningxia University, Yinchuan, Ningxia, China","institution_ids":["https://openalex.org/I21642278"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I21642278"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06945801,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1175","last_page":"1179"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9991000294685364,"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"}},"topics":[{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9991000294685364,"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/T10860","display_name":"Speech and Audio Processing","score":0.9988999962806702,"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/T12301","display_name":"Facial Nerve Paralysis Treatment and Research","score":0.9735000133514404,"subfield":{"id":"https://openalex.org/subfields/2728","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8134422898292542},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7865310907363892},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5786063075065613},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.5326076745986938},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5164411067962646},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.4519840478897095},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32585465908050537},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.24872982501983643}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8134422898292542},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7865310907363892},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5786063075065613},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.5326076745986938},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5164411067962646},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.4519840478897095},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32585465908050537},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.24872982501983643},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3652583.3657625","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3657625","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3657625","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3652583.3657625","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3657625","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3657625","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.47999998927116394}],"awards":[{"id":"https://openalex.org/G511557708","display_name":null,"funder_award_id":"62062056","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"},{"id":"https://openalex.org/F4320337368","display_name":"Division of Graduate Education","ror":"https://ror.org/00whkrf32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399418417.pdf","grobid_xml":"https://content.openalex.org/works/W4399418417.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1990883837","https://openalex.org/W2154961933","https://openalex.org/W2737658251","https://openalex.org/W2739192055","https://openalex.org/W2745771616","https://openalex.org/W2769666294","https://openalex.org/W2981263323","https://openalex.org/W3035524453","https://openalex.org/W3154411171","https://openalex.org/W3175779516","https://openalex.org/W4200630629","https://openalex.org/W4386076250","https://openalex.org/W4387967971","https://openalex.org/W4390872742"],"related_works":["https://openalex.org/W1544039745","https://openalex.org/W2404514746","https://openalex.org/W1652783584","https://openalex.org/W2532377291","https://openalex.org/W2082783427","https://openalex.org/W2121378366","https://openalex.org/W2999276620","https://openalex.org/W2617644139","https://openalex.org/W2535923857","https://openalex.org/W4400097232"],"abstract_inverted_index":{"Speech-driven":[0],"3D":[1,10],"facial":[2,11,53],"animation":[3],"aims":[4],"to":[5,26,50,131],"generate":[6],"realistic":[7],"and":[8,20,62,121,124],"vivid":[9],"animations":[12],"from":[13,44,104],"speech.However,":[14],"the":[15,21,45,64,99,116,134,142,148,155,158],"scarcity":[16],"of":[17,23,41,66,101,118,136,150,157],"labeled":[18,73],"data":[19],"tendency":[22],"existing":[24],"methods":[25],"treat":[27],"this":[28],"cross-modal":[29],"mapping":[30],"problem":[31],"as":[32],"a":[33,78,82,91,108,125],"regression":[34],"task":[35],"can":[36],"result":[37],"in":[38,56],"inadequate":[39],"learning":[40,84,95,100,110],"discriminative":[42,102],"features":[43,103,120],"speech.This":[46],"deficiency":[47],"often":[48],"leads":[49],"excessively":[51],"smooth":[52],"movements,":[54],"particularly":[55],"lip":[57,67,137],"movements.To":[58],"address":[59],"these":[60],"issues":[61],"enhance":[63],"accuracy":[65,135],"generation":[68],"while":[69],"reducing":[70],"reliance":[71],"on":[72,81,141],"data,":[74],"we":[75],"propose":[76],"CLTalk,":[77],"framework":[79,86],"based":[80],"contrastive":[83,94],"strategy.This":[85],"comprises":[87],"three":[88],"main":[89],"parts:":[90],"temporal":[92],"domain":[93],"strategy":[96],"that":[97,112],"facilitates":[98],"different":[105],"audio":[106,119],"frames,":[107],"correlation":[109],"method":[111,130,152],"ensures":[113],"consistency":[114],"between":[115],"distribution":[117],"Mesh":[122],"labels,":[123],"mouth":[126],"opening":[127],"angle":[128],"constraint":[129],"further":[132],"improve":[133],"generation.Extensive":[138],"experimental":[139],"results":[140],"challenging,":[143],"widely":[144],"evaluated":[145],"datasets":[146],"indicate":[147],"effectiveness":[149],"our":[151],"compared":[153],"with":[154],"state":[156],"arts.":[159]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}