{"id":"https://openalex.org/W4392761692","doi":"https://doi.org/10.1145/3651311","title":"Audio-Visual Contrastive Pre-train for Face Forgery Detection","display_name":"Audio-Visual Contrastive Pre-train for Face Forgery Detection","publication_year":2024,"publication_date":"2024-03-13","ids":{"openalex":"https://openalex.org/W4392761692","doi":"https://doi.org/10.1145/3651311"},"language":"en","primary_location":{"id":"doi:10.1145/3651311","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3651311","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3651311","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3651311","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101622213","display_name":"Hanqing Zhao","orcid":"https://orcid.org/0009-0003-0171-9543"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanqing Zhao","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0003-0171-9543","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101821261","display_name":"Wenbo Zhou","orcid":"https://orcid.org/0000-0002-4703-4641"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenbo Zhou","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-4703-4641","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100364587","display_name":"Dongdong Chen","orcid":"https://orcid.org/0000-0002-4642-4373"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dongdong Chen","raw_affiliation_strings":["Microsoft Cloud & AI, Seattle, United States","Microsoft Cloud AI, Seattle, USA"],"raw_orcid":"https://orcid.org/0000-0002-4642-4373","affiliations":[{"raw_affiliation_string":"Microsoft Cloud & AI, Seattle, United States","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Cloud AI, Seattle, USA","institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I58610484"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067689180","display_name":"Weiming Zhang","orcid":"https://orcid.org/0000-0001-5576-6108"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiming Zhang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-5576-6108","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ying Guo","orcid":"https://orcid.org/0000-0002-6429-9297"},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Guo","raw_affiliation_strings":["Meituan, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6429-9297","affiliations":[{"raw_affiliation_string":"Meituan, Beijing, China","institution_ids":["https://openalex.org/I4210087373"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhen Cheng","orcid":"https://orcid.org/0009-0002-1982-1522"},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Cheng","raw_affiliation_strings":["Meituan, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-1982-1522","affiliations":[{"raw_affiliation_string":"Meituan, Beijing, China","institution_ids":["https://openalex.org/I4210087373"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Pengfei Yan","orcid":"https://orcid.org/0009-0008-3438-8994"},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengfei Yan","raw_affiliation_strings":["Meituan, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-3438-8994","affiliations":[{"raw_affiliation_string":"Meituan, Beijing, China","institution_ids":["https://openalex.org/I4210087373"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064573190","display_name":"Nenghai Yu","orcid":"https://orcid.org/0000-0003-4417-9316"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nenghai Yu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-4417-9316","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.647,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.63411869,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"21","issue":"2","first_page":"1","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9994000196456909,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9994000196456909,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9987999796867371,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9970999956130981,"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":0.8673662543296814},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6534522175788879},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6141279935836792},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5211891531944275},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4764140844345093},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.4138699173927307},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40411537885665894},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3748213052749634},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3267638683319092}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8673662543296814},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6534522175788879},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6141279935836792},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5211891531944275},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4764140844345093},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.4138699173927307},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40411537885665894},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3748213052749634},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3267638683319092},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3651311","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3651311","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3651311","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3651311","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3651311","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3651311","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G2482769721","display_name":null,"funder_award_id":"U20B2047, 62072421, 62002334, 62102386 and 62121002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8366119194","display_name":null,"funder_award_id":"WK5290000003 and WK2100000011","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G8716439342","display_name":null,"funder_award_id":"2022k07020008","funder_id":"https://openalex.org/F4320336578","funder_display_name":"Anhui Provincial Key Research and Development Plan"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null},{"id":"https://openalex.org/F4320336578","display_name":"Anhui Provincial Key Research and Development Plan","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392761692.pdf","grobid_xml":"https://content.openalex.org/works/W4392761692.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W2884460600","https://openalex.org/W2891547264","https://openalex.org/W2898877033","https://openalex.org/W2902266071","https://openalex.org/W2942074357","https://openalex.org/W2945262873","https://openalex.org/W2963626105","https://openalex.org/W2982058372","https://openalex.org/W2999135330","https://openalex.org/W3011288915","https://openalex.org/W3020933450","https://openalex.org/W3034196597","https://openalex.org/W3034552680","https://openalex.org/W3034577585","https://openalex.org/W3034900344","https://openalex.org/W3035574324","https://openalex.org/W3083246145","https://openalex.org/W3092709185","https://openalex.org/W3104792420","https://openalex.org/W3108281670","https://openalex.org/W3108854358","https://openalex.org/W3120602499","https://openalex.org/W3123599388","https://openalex.org/W3135925326","https://openalex.org/W3145450063","https://openalex.org/W3153595700","https://openalex.org/W3159663901","https://openalex.org/W3162322471","https://openalex.org/W3162707322","https://openalex.org/W3170837227","https://openalex.org/W3174171554","https://openalex.org/W3174508664","https://openalex.org/W3175342695","https://openalex.org/W3176241004","https://openalex.org/W4214680478","https://openalex.org/W4281632540","https://openalex.org/W4382237564","https://openalex.org/W4386590516","https://openalex.org/W6767264202","https://openalex.org/W6845577938","https://openalex.org/W6990316778"],"related_works":["https://openalex.org/W3162204513","https://openalex.org/W2366906938","https://openalex.org/W2371138613","https://openalex.org/W2349391998","https://openalex.org/W4205655149","https://openalex.org/W2048963458","https://openalex.org/W43109613","https://openalex.org/W2359952343","https://openalex.org/W2239445980","https://openalex.org/W2000775715"],"abstract_inverted_index":{"The":[0,98,125],"highly":[1],"realistic":[2],"avatar":[3],"in":[4,104,175],"the":[5,20,43,95,105,110,129,149],"metaverse":[6],"may":[7],"lead":[8],"to":[9,29,50,116,122],"deepfakes":[10],"of":[11,23,153],"facial":[12,39],"identity.":[13],"Malicious":[14],"users":[15],"can":[16,146],"more":[17],"easily":[18],"obtain":[19],"three-dimensional":[21],"structure":[22],"faces,":[24],"thus":[25],"using":[26],"deepfake":[27,47,72,78,96,126,136,155,165],"technology":[28],"create":[30],"counterfeit":[31],"videos":[32,40],"with":[33,42,86,163],"higher":[34],"realism.":[35],"To":[36],"automatically":[37],"discern":[38],"forged":[41],"advancing":[44],"generation":[45],"techniques,":[46],"detectors":[48],"need":[49],"achieve":[51],"stronger":[52],"generalization":[53,173],"abilities.":[54],"Inspired":[55],"by":[56,108],"transfer":[57],"learning,":[58],"neural":[59],"networks":[60],"pre-trained":[61,130],"on":[62,82,135],"other":[63],"large-scale":[64],"face-related":[65],"tasks":[66],"would":[67],"provide":[68],"fundamental":[69],"features":[70],"for":[71,93],"detection.":[73],"We":[74],"propose":[75],"a":[76,83,87],"video-level":[77],"detection":[79,156,166],"method":[80,100,145,170],"based":[81],"temporal":[84],"transformer":[85],"self-supervised":[88,143],"audio\u2013visual":[89],"contrastive":[90],"learning":[91],"approach":[92],"pre-training":[94,144],"detector.":[97],"proposed":[99,169],"learns":[101],"motion":[102],"representations":[103,115],"mouth":[106],"region":[107],"encouraging":[109],"paired":[111],"video":[112],"and":[113,132,151],"audio":[114],"be":[117,123],"close":[118],"while":[119],"unpaired":[120],"ones":[121],"diverse.":[124],"detector":[127],"adopts":[128],"weights":[131],"partially":[133],"fine-tunes":[134],"datasets.":[137],"Extensive":[138],"experiments":[139],"show":[140],"that":[141],"our":[142,154,168],"effectively":[147],"improve":[148],"accuracy":[150],"robustness":[152],"model":[157],"without":[158],"extra":[159],"human":[160],"efforts.":[161],"Compared":[162],"existing":[164],"methods,":[167],"achieves":[171],"better":[172],"ability":[174],"cross-dataset":[176],"evaluations.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}