{"id":"https://openalex.org/W4387967971","doi":"https://doi.org/10.1145/3581783.3611734","title":"SelfTalk: A Self-Supervised Commutative Training Diagram to Comprehend 3D Talking Faces","display_name":"SelfTalk: A Self-Supervised Commutative Training Diagram to Comprehend 3D Talking Faces","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387967971","doi":"https://doi.org/10.1145/3581783.3611734"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611734","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611734","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st 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/A5062816933","display_name":"Ziqiao Peng","orcid":"https://orcid.org/0009-0000-1341-9618"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziqiao Peng","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-1341-9618","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102944157","display_name":"Yihao Luo","orcid":"https://orcid.org/0009-0002-1169-2930"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yihao Luo","raw_affiliation_strings":["Imperial College London, London, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0002-1169-2930","affiliations":[{"raw_affiliation_string":"Imperial College London, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101758309","display_name":"Yue Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue Shi","raw_affiliation_strings":["Psyche AI Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-4212-8236","affiliations":[{"raw_affiliation_string":"Psyche AI Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103221551","display_name":"Hao Xu","orcid":"https://orcid.org/0000-0002-2438-8906"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hao Xu","raw_affiliation_strings":["HKUST, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-2438-8906","affiliations":[{"raw_affiliation_string":"HKUST, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100632822","display_name":"Xiangyu Zhu","orcid":"https://orcid.org/0000-0002-4636-9677"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyu Zhu","raw_affiliation_strings":["Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4636-9677","affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100332465","display_name":"Hongyan Liu","orcid":"https://orcid.org/0000-0002-4902-1078"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyan Liu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4902-1078","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100766741","display_name":"Jun He","orcid":"https://orcid.org/0000-0003-1511-7554"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun He","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1511-7554","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021141988","display_name":"Zhaoxin Fan","orcid":"https://orcid.org/0000-0002-6324-1712"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaoxin Fan","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6324-1712","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":48,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5292","last_page":"5301"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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/T11448","display_name":"Face recognition and analysis","score":0.9993000030517578,"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/T10057","display_name":"Face and Expression Recognition","score":0.9865000247955322,"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":0.8132994174957275},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.5912257432937622},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5388104319572449},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.5228500962257385},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.486275315284729},{"id":"https://openalex.org/keywords/interpreter","display_name":"Interpreter","score":0.4174676835536957},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40176621079444885},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38168445229530334},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.20961815118789673},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.10205748677253723}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8132994174957275},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.5912257432937622},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5388104319572449},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.5228500962257385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.486275315284729},{"id":"https://openalex.org/C122783720","wikidata":"https://www.wikidata.org/wiki/Q183065","display_name":"Interpreter","level":2,"score":0.4174676835536957},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40176621079444885},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38168445229530334},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.20961815118789673},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.10205748677253723},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3581783.3611734","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611734","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-139101","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-139101","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8299999833106995}],"awards":[{"id":"https://openalex.org/G1016671922","display_name":"\u8003\u8651\u5fc3\u7406\u56e0\u7d20\u7684\u7528\u6237\u5728\u7ebf\u884c\u4e3a\u9884\u6d4b\u53ca\u5176\u5728\u63a8\u8350\u7cfb\u7edf\u4e2d\u7684\u5e94\u7528\u7814\u7a76","funder_award_id":"71771131","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G228593745","display_name":null,"funder_award_id":"Nos. 62172421 62072459 and 71771131","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G5480676819","display_name":null,"funder_award_id":"62072459","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8151001889","display_name":null,"funder_award_id":"No. 2020YFB2104101","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G8845966520","display_name":null,"funder_award_id":"2020YFB2104101","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program 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/F4320322499","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92"},{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W2073413525","https://openalex.org/W2099257899","https://openalex.org/W2108033344","https://openalex.org/W2127141656","https://openalex.org/W2148226542","https://openalex.org/W2154961933","https://openalex.org/W2157827878","https://openalex.org/W2161669434","https://openalex.org/W2187089797","https://openalex.org/W2468212864","https://openalex.org/W2510642588","https://openalex.org/W2551572271","https://openalex.org/W2737658251","https://openalex.org/W2739192055","https://openalex.org/W2745771616","https://openalex.org/W2769666294","https://openalex.org/W2804619907","https://openalex.org/W2886945201","https://openalex.org/W2914165399","https://openalex.org/W2972756321","https://openalex.org/W2981263323","https://openalex.org/W2996970093","https://openalex.org/W3019952993","https://openalex.org/W3081492798","https://openalex.org/W3101631197","https://openalex.org/W3109114891","https://openalex.org/W3147719764","https://openalex.org/W3154411171","https://openalex.org/W3175779516","https://openalex.org/W3186090335","https://openalex.org/W3194357576","https://openalex.org/W3195529437","https://openalex.org/W3207299135","https://openalex.org/W3207849023","https://openalex.org/W3208601549","https://openalex.org/W3211147706","https://openalex.org/W4200174933","https://openalex.org/W4200630629","https://openalex.org/W4214540501","https://openalex.org/W4224319127","https://openalex.org/W4225305629","https://openalex.org/W4252332688","https://openalex.org/W4281730245","https://openalex.org/W4283818626","https://openalex.org/W4286611181","https://openalex.org/W4312473638","https://openalex.org/W4312638101"],"related_works":["https://openalex.org/W1544039745","https://openalex.org/W2532377291","https://openalex.org/W2121378366","https://openalex.org/W2999276620","https://openalex.org/W2535923857","https://openalex.org/W2617644139","https://openalex.org/W4255594734","https://openalex.org/W3020604125","https://openalex.org/W577858612","https://openalex.org/W3094080214"],"abstract_inverted_index":{"Speech-driven":[0],"3D":[1,89],"face":[2,33],"animation":[3],"technique,":[4],"extending":[5],"its":[6],"applications":[7],"to":[8,51,87,132,151],"various":[9],"multimedia":[10],"fields.Previous":[11],"research":[12],"has":[13],"generated":[14,63],"promising":[15],"realistic":[16],"lip":[17,64,127,155],"movements":[18],"and":[19,44,56,106,126,159,172],"facial":[20,102],"expressions":[21],"from":[22,147],"audio":[23],"signals.":[24],"However,":[25],"traditional":[26],"regression":[27],"models":[28,131],"solely":[29],"driven":[30],"by":[31,79],"data":[32],"several":[34],"essential":[35],"problems,":[36],"such":[37],"as":[38],"difficulties":[39],"in":[40,82],"accessing":[41],"precise":[42],"labels":[43],"domain":[45],"gaps":[46],"between":[47,137],"different":[48],"modalities,":[49],"leading":[50],"unsatisfactory":[52],"results":[53],"lacking":[54],"precision":[55],"coherence.To":[57],"enhance":[58],"the":[59,68,134,144,148,177],"visual":[60],"accuracy":[61],"of":[62,99,111],"movement":[65],"while":[66],"reducing":[67],"dependence":[69],"on":[70],"labeled":[71],"data,":[72],"we":[73],"propose":[74],"a":[75,83,95,114],"novel":[76],"framework":[77,93,142],"SelfTalk,":[78],"involving":[80],"self-supervision":[81],"cross-modals":[84],"network":[85,96],"system":[86,97],"learn":[88,133],"talking":[90],"faces.":[91],"The":[92,109,140],"constructs":[94],"consisting":[98],"three":[100],"modules:":[101],"animator,":[103],"speech":[104],"recognizer,":[105],"lip-reading":[107,149],"interpreter.":[108],"core":[110],"SelfTalk":[112],"is":[113],"commutative":[115],"training":[116],"diagram":[117],"that":[118,163],"facilitates":[119],"compatible":[120],"features":[121],"exchange":[122],"among":[123],"audio,":[124],"text,":[125],"shape,":[128],"enabling":[129],"our":[130,164],"intricate":[135],"connection":[136],"these":[138],"factors.":[139],"proposed":[141,165],"leverages":[143],"knowledge":[145],"learned":[146],"interpreter":[150],"generate":[152],"more":[153],"plausible":[154],"shapes.":[156],"Extensive":[157],"experiments":[158],"user":[160],"studies":[161],"demonstrate":[162],"approach":[166],"achieves":[167],"state-of-the-art":[168],"performance":[169],"both":[170],"qualitatively":[171],"quantitatively.":[173],"We":[174],"recommend":[175],"watching":[176],"supplementary":[178],"video.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":26},{"year":2024,"cited_by_count":17}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}