{"id":"https://openalex.org/W4387885896","doi":"https://doi.org/10.1109/tcsvt.2023.3326694","title":"Audio-Visual Temporal Forgery Detection Using Embedding-Level Fusion and Multi-Dimensional Contrastive Loss","display_name":"Audio-Visual Temporal Forgery Detection Using Embedding-Level Fusion and Multi-Dimensional Contrastive Loss","publication_year":2023,"publication_date":"2023-10-23","ids":{"openalex":"https://openalex.org/W4387885896","doi":"https://doi.org/10.1109/tcsvt.2023.3326694"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2023.3326694","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3326694","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-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/A5045241725","display_name":"Miao Liu","orcid":"https://orcid.org/0000-0002-2039-2051"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Miao Liu","raw_affiliation_strings":["School of Information and Electronics, Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100378497","display_name":"Jing Wang","orcid":"https://orcid.org/0000-0002-3653-9951"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Wang","raw_affiliation_strings":["School of Information and Electronics, Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056495776","display_name":"Xinyuan Qian","orcid":"https://orcid.org/0000-0002-9511-6713"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyuan Qian","raw_affiliation_strings":["School of Computer and Communication, University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Communication, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I180437899","display_name":"University of Bremen","ror":"https://ror.org/04ers2y35","country_code":"DE","type":"education","lineage":["https://openalex.org/I180437899"]},{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN","DE","SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Guangdong Provincial Key Laboratory of Big Data Computing, The Chinese University of Hong Kong, Shenzhen, China","Shenzhen Research Institute of Big data, Shenzhen, China","University of Bremen, Bremen, Germany","Department Electrical and Computer Engineering, National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Big Data Computing, The Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]},{"raw_affiliation_string":"Shenzhen Research Institute of Big data, Shenzhen, China","institution_ids":["https://openalex.org/I4210099586"]},{"raw_affiliation_string":"University of Bremen, Bremen, Germany","institution_ids":["https://openalex.org/I180437899"]},{"raw_affiliation_string":"Department Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5045241725"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":1.8981,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.88224011,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"34","issue":"8","first_page":"6937","last_page":"6948"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9998999834060669,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9968000054359436,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9929999709129333,"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":0.8523163199424744},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7507526874542236},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6731433868408203},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6103112697601318},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5419401526451111},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5127545595169067},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5021750926971436},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47756749391555786},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.45550939440727234},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4381028413772583},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4247822165489197},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.42365968227386475},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4196047782897949},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34453949332237244},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.0901222825050354}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8523163199424744},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7507526874542236},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6731433868408203},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6103112697601318},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5419401526451111},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5127545595169067},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5021750926971436},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47756749391555786},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.45550939440727234},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4381028413772583},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4247822165489197},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.42365968227386475},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4196047782897949},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34453949332237244},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0901222825050354},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2023.3326694","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3326694","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6700000166893005,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1772702119","display_name":null,"funder_award_id":"L223033","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"},{"id":"https://openalex.org/G6471985988","display_name":null,"funder_award_id":"62071039","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/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":86,"referenced_works":["https://openalex.org/W1927052826","https://openalex.org/W2176804518","https://openalex.org/W2194775991","https://openalex.org/W2738406145","https://openalex.org/W2745896134","https://openalex.org/W2752782242","https://openalex.org/W2766402183","https://openalex.org/W2798158991","https://openalex.org/W2890952074","https://openalex.org/W2890964092","https://openalex.org/W2891145043","https://openalex.org/W2898877033","https://openalex.org/W2904573504","https://openalex.org/W2936802426","https://openalex.org/W2946508582","https://openalex.org/W2962677524","https://openalex.org/W2962960500","https://openalex.org/W2964121718","https://openalex.org/W2967606780","https://openalex.org/W2983918066","https://openalex.org/W2989851933","https://openalex.org/W2990074387","https://openalex.org/W2999905431","https://openalex.org/W3005939059","https://openalex.org/W3016011581","https://openalex.org/W3016138785","https://openalex.org/W3034658206","https://openalex.org/W3034713808","https://openalex.org/W3034815696","https://openalex.org/W3034900344","https://openalex.org/W3048939150","https://openalex.org/W3049446265","https://openalex.org/W3081492798","https://openalex.org/W3092879151","https://openalex.org/W3093010840","https://openalex.org/W3093077034","https://openalex.org/W3093578014","https://openalex.org/W3095990227","https://openalex.org/W3099638501","https://openalex.org/W3100481960","https://openalex.org/W3101631197","https://openalex.org/W3113824005","https://openalex.org/W3123394884","https://openalex.org/W3123940584","https://openalex.org/W3128609017","https://openalex.org/W3137574511","https://openalex.org/W3160833014","https://openalex.org/W3162322471","https://openalex.org/W3163596559","https://openalex.org/W3166279462","https://openalex.org/W3166490340","https://openalex.org/W3173161217","https://openalex.org/W3176444885","https://openalex.org/W3178572954","https://openalex.org/W3188946793","https://openalex.org/W3194230325","https://openalex.org/W3197694255","https://openalex.org/W3198123200","https://openalex.org/W3200167423","https://openalex.org/W3200319900","https://openalex.org/W3201016147","https://openalex.org/W3206008172","https://openalex.org/W4213449918","https://openalex.org/W4214691743","https://openalex.org/W4221138880","https://openalex.org/W4221161777","https://openalex.org/W4224932929","https://openalex.org/W4285230750","https://openalex.org/W4287026043","https://openalex.org/W4287758545","https://openalex.org/W4293055826","https://openalex.org/W4317796367","https://openalex.org/W4317987748","https://openalex.org/W4319978495","https://openalex.org/W4320882980","https://openalex.org/W4360993864","https://openalex.org/W6748588790","https://openalex.org/W6756046522","https://openalex.org/W6757599822","https://openalex.org/W6784810453","https://openalex.org/W6789619165","https://openalex.org/W6790220185","https://openalex.org/W6797216054","https://openalex.org/W6799942944","https://openalex.org/W6800767084","https://openalex.org/W6810495895"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2566616303","https://openalex.org/W2159052453","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W4386815338","https://openalex.org/W2145836866","https://openalex.org/W2803255133"],"abstract_inverted_index":{"Audio-visual":[0],"deepfake":[1,135,189],"detection":[2,90,136],"is":[3,122],"the":[4,30,35,87,126,146,152,157,182,185],"process":[5],"of":[6,37,95,184],"identifying":[7],"and":[8,18,65,98,107,173],"detecting":[9],"deepfakes":[10],"that":[11,156],"have":[12],"been":[13],"generated":[14],"using":[15],"both":[16],"audio":[17,97],"visual":[19,99],"content":[20],"with":[21,101,112],"AI":[22],"algorithms.":[23],"Most":[24],"existing":[25],"methods":[26,166],"primarily":[27],"focus":[28],"on":[29,151,171,175,188],"overall":[31],"authenticity":[32],"while":[33],"neglecting":[34],"position":[36],"forgeries":[38],"in":[39,51],"time.":[40],"This":[41],"can":[42,54],"be":[43],"particularly":[44],"problematic,":[45],"as":[46],"even":[47],"a":[48,52,80,118],"small":[49],"alteration":[50],"clip":[53],"significantly":[55],"impact":[56],"its":[57],"meaning.":[58],"Such":[59],"brand":[60],"new":[61,96],"attacks":[62,70],"are":[63],"dangerous":[64],"how":[66],"to":[67,85,130,139,169],"tackle":[68,86],"such":[69],"remains":[71],"an":[72,108],"open":[73],"question.":[74],"In":[75,177],"this":[76],"paper,":[77],"we":[78,179],"present":[79],"novel":[81],"neural":[82],"network-based":[83],"model":[84,127,187],"temporal":[88,141,163],"forgery":[89,115,164],"(TFD)":[91],"problem.":[92],"It":[93],"consists":[94],"encoders":[100],"cross-modal":[102],"attention":[103],"for":[104,114,134],"embedding":[105],"extraction,":[106],"embedding-level":[109],"fusion":[110],"mechanism":[111],"self-attention":[113],"localization.":[116],"Besides,":[117],"multi-dimensional":[119],"contrastive":[120],"loss":[121],"proposed":[123,186],"which":[124],"helps":[125],"not":[128],"only":[129],"capture":[131],"audio-visual":[132],"inconsistency":[133,142],"but":[137],"also":[138,180],"exploit":[140],"by":[143,167],"coherently":[144],"constraining":[145],"extracted":[147],"embeddings.":[148],"Extensive":[149],"experiments":[150],"LAV-DF":[153],"dataset":[154],"show":[155,181],"presented":[158],"method":[159],"outperforms":[160],"several":[161],"state-of-the-art":[162],"localization":[165],"up":[168],"23.4%":[170],"AP@0.5":[172],"13.8%":[174],"AR@100.":[176],"addition,":[178],"effectiveness":[183],"detection.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":5}],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-10-10T00:00:00"}