{"id":"https://openalex.org/W3207628370","doi":"https://doi.org/10.1145/3474085.3475415","title":"Cross-modal Self-Supervised Learning for Lip Reading: When Contrastive Learning meets Adversarial Training","display_name":"Cross-modal Self-Supervised Learning for Lip Reading: When Contrastive Learning meets Adversarial Training","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3207628370","doi":"https://doi.org/10.1145/3474085.3475415","mag":"3207628370"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475415","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475415","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","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/A5007427128","display_name":"Changchong Sheng","orcid":"https://orcid.org/0000-0001-6255-754X"},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Changchong Sheng","raw_affiliation_strings":["University of Oulu, Oulu, Finland"],"affiliations":[{"raw_affiliation_string":"University of Oulu, Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014611768","display_name":"Matti Pietik\u00e4inen","orcid":"https://orcid.org/0000-0003-2263-6731"},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Matti Pietik\u00e4inen","raw_affiliation_strings":["University of Oulu, Oulu, Finland"],"affiliations":[{"raw_affiliation_string":"University of Oulu, Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111504451","display_name":"Qi Tian","orcid":"https://orcid.org/0009-0003-2676-5300"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Tian","raw_affiliation_strings":["Xidian University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100418818","display_name":"Li Liu","orcid":"https://orcid.org/0000-0002-4497-0135"},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Li Liu","raw_affiliation_strings":["University of Oulu, Oulu, Finland"],"affiliations":[{"raw_affiliation_string":"University of Oulu, Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5007427128"],"corresponding_institution_ids":["https://openalex.org/I98381234"],"apc_list":null,"apc_paid":null,"fwci":1.2295,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.79753983,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2456","last_page":"2464"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/T11309","display_name":"Music and Audio Processing","score":0.9922999739646912,"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9805999994277954,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8156143426895142},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7689043879508972},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.674994707107544},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6341484785079956},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5347040891647339},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.523944616317749},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.4933148920536041},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4732430875301361},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.44226527214050293},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43963927030563354},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.198300302028656},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11135247349739075}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8156143426895142},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7689043879508972},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.674994707107544},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6341484785079956},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5347040891647339},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.523944616317749},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.4933148920536041},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4732430875301361},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.44226527214050293},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43963927030563354},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.198300302028656},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11135247349739075},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3474085.3475415","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475415","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:oulu.fi:nbnfi-fe2022030121341","is_oa":false,"landing_page_url":"http://urn.fi/urn:nbn:fi-fe2022030121341","pdf_url":null,"source":{"id":"https://openalex.org/S4306400284","display_name":"University of Oulu Repository (University of Oulu)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98381234","host_organization_name":"University of Oulu","host_organization_lineage":["https://openalex.org/I98381234"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G2443591357","display_name":"LESLearn: Label, Energy and Sample Efficient Feature Representation and Learning in Computer Vision","funder_award_id":"331883","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"},{"id":"https://openalex.org/G8008312880","display_name":null,"funder_award_id":"331883","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"}],"funders":[{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1731081199","https://openalex.org/W2015394094","https://openalex.org/W2108598243","https://openalex.org/W2127141656","https://openalex.org/W2138621090","https://openalex.org/W2143612262","https://openalex.org/W2152790380","https://openalex.org/W2166563626","https://openalex.org/W2194775991","https://openalex.org/W2551572271","https://openalex.org/W2594690981","https://openalex.org/W2792330714","https://openalex.org/W2796992393","https://openalex.org/W2798991696","https://openalex.org/W2949662773","https://openalex.org/W2949888546","https://openalex.org/W2952746495","https://openalex.org/W2962960500","https://openalex.org/W2963115079","https://openalex.org/W2963173190","https://openalex.org/W2963290645","https://openalex.org/W2963403868","https://openalex.org/W2963654155","https://openalex.org/W2963680395","https://openalex.org/W2964048159","https://openalex.org/W2964308564","https://openalex.org/W2981501041","https://openalex.org/W2988916019","https://openalex.org/W2998115938","https://openalex.org/W3005680577","https://openalex.org/W3015830103","https://openalex.org/W3016663370","https://openalex.org/W3035524453","https://openalex.org/W3104792420","https://openalex.org/W3176780013"],"related_works":["https://openalex.org/W3023351797","https://openalex.org/W3162567751","https://openalex.org/W4285260836","https://openalex.org/W4221088574","https://openalex.org/W3094076422","https://openalex.org/W3046775127","https://openalex.org/W4220686584","https://openalex.org/W4319309271","https://openalex.org/W2971361125","https://openalex.org/W3091943846"],"abstract_inverted_index":{"The":[0],"goal":[1],"of":[2,54,71],"this":[3],"work":[4],"is":[5],"to":[6,16,38,95,113],"learn":[7,39],"discriminative":[8,86],"visual":[9,41,82,122],"representations":[10,42,83,123],"for":[11,43,87],"lip":[12,44,88],"reading":[13,89],"without":[14,152],"access":[15],"manual":[17],"text":[18],"annotation.":[19],"Recent":[20],"advances":[21],"in":[22],"cross-modal":[23,138],"self-supervised":[24,104,139],"learning":[25,105],"have":[26],"shown":[27],"that":[28,63,132],"the":[29,51,55,58,81,96,121,133],"corresponding":[30,59],"audio":[31,67],"can":[32,147],"serve":[33],"as":[34],"a":[35,102,142],"supervisory":[36],"signal":[37],"effective":[40],"reading.":[45],"However,":[46],"existing":[47],"methods":[48,117],"only":[49],"exploit":[50],"natural":[52],"synchronization":[53],"video":[56,65],"and":[57,66,76,90,98],"audio.":[60],"We":[61],"find":[62],"both":[64],"are":[68],"actually":[69],"composed":[70],"speech-related":[72],"information,":[73,75],"identity-related":[74],"modal":[77],"information.":[78,127],"To":[79],"make":[80],"(i)":[84],"more":[85],"(ii)":[91],"indiscriminate":[92],"with":[93],"respect":[94],"identities":[97],"modals,":[99],"we":[100],"propose":[101],"novel":[103],"framework":[106],"called":[107],"Adversarial":[108],"Dual-Contrast":[109],"Self-Supervised":[110],"Learning":[111],"(ADC-SSL),":[112],"go":[114],"beyond":[115],"previous":[116],"by":[118,141],"explicitly":[119],"forcing":[120],"disentangled":[124],"from":[125],"speech-unrelated":[126],"Experimental":[128],"results":[129],"clearly":[130],"show":[131],"proposed":[134],"method":[135],"outperforms":[136],"state-of-the-art":[137],"baselines":[140],"large":[143],"margin.":[144],"Besides,":[145],"ADC-SSL":[146],"outperform":[148],"its":[149],"supervised":[150],"counterpart":[151],"any":[153],"finetune.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-03T08:47:05.690250","created_date":"2025-10-10T00:00:00"}