{"id":"https://openalex.org/W4404295298","doi":"https://doi.org/10.1109/mmsp61759.2024.10743671","title":"A Multi-Stream Fusion Approach with One-Class Learning for Audio-Visual Deepfake Detection","display_name":"A Multi-Stream Fusion Approach with One-Class Learning for Audio-Visual Deepfake Detection","publication_year":2024,"publication_date":"2024-10-02","ids":{"openalex":"https://openalex.org/W4404295298","doi":"https://doi.org/10.1109/mmsp61759.2024.10743671"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp61759.2024.10743671","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp61759.2024.10743671","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 26th International Workshop on Multimedia Signal Processing (MMSP)","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/A5106083359","display_name":"Kyung\u2010Bok Lee","orcid":"https://orcid.org/0000-0003-1495-3462"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kyungbok Lee","raw_affiliation_strings":["Department of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101904472","display_name":"You Zhang","orcid":"https://orcid.org/0000-0002-9599-2676"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"You Zhang","raw_affiliation_strings":["University of Rochester,Department of Electrical and Computer Engineering,Rochester,NY,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester,Department of Electrical and Computer Engineering,Rochester,NY,USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102749436","display_name":"Zhiyao Duan","orcid":"https://orcid.org/0000-0002-8334-9974"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiyao Duan","raw_affiliation_strings":["University of Rochester,Department of Electrical and Computer Engineering,Rochester,NY,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester,Department of Electrical and Computer Engineering,Rochester,NY,USA","institution_ids":["https://openalex.org/I5388228"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5776,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.88370099,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9860000014305115,"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":0.9860000014305115,"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":0.9603000283241272,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9485999941825867,"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":0.7571934461593628},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.7111102938652039},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6857558488845825},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.581275224685669},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5328571796417236},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3960004448890686},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32559674978256226},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.2271234393119812}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7571934461593628},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7111102938652039},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6857558488845825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.581275224685669},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5328571796417236},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3960004448890686},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32559674978256226},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2271234393119812},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmsp61759.2024.10743671","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp61759.2024.10743671","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 26th International Workshop on Multimedia Signal Processing (MMSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W2126143605","https://openalex.org/W2194775991","https://openalex.org/W2558151185","https://openalex.org/W2950864153","https://openalex.org/W3081492798","https://openalex.org/W3093077034","https://openalex.org/W3098557217","https://openalex.org/W3101631197","https://openalex.org/W3127781933","https://openalex.org/W3158663310","https://openalex.org/W3174758275","https://openalex.org/W3197123936","https://openalex.org/W3205798727","https://openalex.org/W3207531490","https://openalex.org/W4214691743","https://openalex.org/W4283817039","https://openalex.org/W4287758545","https://openalex.org/W4312090574","https://openalex.org/W4312095900","https://openalex.org/W4312095999","https://openalex.org/W4312319640","https://openalex.org/W4312933868","https://openalex.org/W4360993864","https://openalex.org/W4372347465","https://openalex.org/W4386071653","https://openalex.org/W4387891232","https://openalex.org/W4392780157","https://openalex.org/W4392903665","https://openalex.org/W4392904345","https://openalex.org/W4398789263","https://openalex.org/W6779059831","https://openalex.org/W6781662123","https://openalex.org/W6784810453","https://openalex.org/W6796730497","https://openalex.org/W6799942944","https://openalex.org/W6855532776","https://openalex.org/W6857699132","https://openalex.org/W6869871790"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731","https://openalex.org/W2393726419"],"abstract_inverted_index":{"This":[0,35],"paper":[1],"addresses":[2],"the":[3,30,38,42,47,56,63,90,106,138,154],"challenge":[4],"of":[5,32,41,49,93,115],"developing":[6],"a":[7,76,84,99,142],"robust":[8],"audio-visual":[9,94],"deepfake":[10,95],"detection":[11,33,50,96],"model.":[12],"In":[13],"practical":[14],"use":[15],"cases,":[16],"new":[17,100],"generation":[18],"algorithms":[19,25],"are":[20,26],"continually":[21],"emerging,":[22],"and":[23,104,127],"these":[24,71],"not":[27],"encountered":[28],"during":[29],"development":[31],"methods.":[34],"calls":[36],"for":[37,55],"generalization":[39,91],"ability":[40],"method.":[43],"Additionally,":[44],"to":[45,58,160],"ensure":[46],"credibility":[48],"methods,":[51],"it":[52,66],"is":[53,67,166],"beneficial":[54],"model":[57,155],"interpret":[59],"which":[60,152],"cues":[61],"from":[62],"video":[64],"indicate":[65],"fake.":[68,162],"Motivated":[69],"by":[70,97,102,141],"considerations,":[72],"we":[73],"then":[74],"propose":[75],"multi-stream":[77],"fusion":[78],"approach":[79,136],"with":[80],"one-class":[81],"learning":[82],"as":[83,157],"representation-level":[85],"regularization":[86],"technique.":[87],"We":[88],"study":[89],"problem":[92],"creating":[98],"benchmark":[101,111],"extending":[103],"re-splitting":[105],"existing":[107],"FakeAVCeleb":[108],"dataset.":[109],"The":[110,130,163],"con-tains":[112],"four":[113],"categories":[114],"fake":[116],"videos":[117],"(Real":[118],"Audio-Fake":[119,122],"Visual,":[120,123,126],"Fake":[121,124],"Audio-Real":[125],"Unsynchronized":[128],"videos).":[129],"experimental":[131],"results":[132],"demonstrate":[133],"that":[134],"our":[135,146],"surpasses":[137],"previous":[139],"models":[140],"large":[143],"margin.":[144],"Furthermore,":[145],"proposed":[147],"framework":[148],"offers":[149],"interpretability,":[150],"indicating":[151],"modality":[153],"identifies":[156],"more":[158],"likely":[159],"be":[161],"source":[164],"code":[165],"released":[167],"at":[168],"https://github.com/bok-bok/MSOC.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}