{"id":"https://openalex.org/W4402774452","doi":"https://doi.org/10.1109/cvpr52733.2024.02559","title":"AVFF: Audio-Visual Feature Fusion for Video Deepfake Detection","display_name":"AVFF: Audio-Visual Feature Fusion for Video Deepfake Detection","publication_year":2024,"publication_date":"2024-06-16","ids":{"openalex":"https://openalex.org/W4402774452","doi":"https://doi.org/10.1109/cvpr52733.2024.02559"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52733.2024.02559","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.02559","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5013393466","display_name":"Trevine Oorloff","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Trevine Oorloff","raw_affiliation_strings":["University of Maryland,College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092639627","display_name":"Surya Koppisetti","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119400","display_name":"Division of Public Defender Services","ror":"https://ror.org/02sksqx64","country_code":"US","type":"government","lineage":["https://openalex.org/I4210119400"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Surya Koppisetti","raw_affiliation_strings":["Reality Defender Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Reality Defender Inc","institution_ids":["https://openalex.org/I4210119400"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046125100","display_name":"Nicol\u00f2 Bonettini","orcid":"https://orcid.org/0000-0002-7500-8512"},"institutions":[{"id":"https://openalex.org/I4210119400","display_name":"Division of Public Defender Services","ror":"https://ror.org/02sksqx64","country_code":"US","type":"government","lineage":["https://openalex.org/I4210119400"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicol\u00f2 Bonettini","raw_affiliation_strings":["Reality Defender Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Reality Defender Inc","institution_ids":["https://openalex.org/I4210119400"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102684374","display_name":"Divyaraj Solanki","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119400","display_name":"Division of Public Defender Services","ror":"https://ror.org/02sksqx64","country_code":"US","type":"government","lineage":["https://openalex.org/I4210119400"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Divyaraj Solanki","raw_affiliation_strings":["Reality Defender Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Reality Defender Inc","institution_ids":["https://openalex.org/I4210119400"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092639628","display_name":"Ben Colman","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119400","display_name":"Division of Public Defender Services","ror":"https://ror.org/02sksqx64","country_code":"US","type":"government","lineage":["https://openalex.org/I4210119400"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ben Colman","raw_affiliation_strings":["Reality Defender Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Reality Defender Inc","institution_ids":["https://openalex.org/I4210119400"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088670059","display_name":"Yaser Yacoob","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yaser Yacoob","raw_affiliation_strings":["University of Maryland,College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109491559","display_name":"Ali Shahriyari","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119400","display_name":"Division of Public Defender Services","ror":"https://ror.org/02sksqx64","country_code":"US","type":"government","lineage":["https://openalex.org/I4210119400"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ali Shahriyari","raw_affiliation_strings":["Reality Defender Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Reality Defender Inc","institution_ids":["https://openalex.org/I4210119400"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036255713","display_name":"Gaurav Bharaj","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119400","display_name":"Division of Public Defender Services","ror":"https://ror.org/02sksqx64","country_code":"US","type":"government","lineage":["https://openalex.org/I4210119400"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gaurav Bharaj","raw_affiliation_strings":["Reality Defender Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Reality Defender Inc","institution_ids":["https://openalex.org/I4210119400"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":16.4348,"has_fulltext":false,"cited_by_count":65,"citation_normalized_percentile":{"value":0.99397105,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"27092","last_page":"27102"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9962999820709229,"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":0.9962999820709229,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9889000058174133,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9837999939918518,"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":0.7880723476409912},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.7711540460586548},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6023572087287903},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5825337171554565},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5609952211380005},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.48196837306022644},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.4322412610054016},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42408841848373413},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.23667198419570923}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7880723476409912},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7711540460586548},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6023572087287903},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5825337171554565},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5609952211380005},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.48196837306022644},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.4322412610054016},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42408841848373413},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.23667198419570923},{"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/cvpr52733.2024.02559","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.02559","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4755179400","display_name":null,"funder_award_id":"HR001120e0124","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"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/W2132659060","https://openalex.org/W2031992971","https://openalex.org/W3214791684","https://openalex.org/W2353265673","https://openalex.org/W2152662039"],"abstract_inverted_index":{"With":[0],"the":[1,32,35,41,44,48,57,85,88,110,143,184,188],"rapid":[2],"growth":[3],"in":[4,142,174],"deepfake":[5,95,147],"video":[6],"content,":[7],"we":[8,119],"re-quire":[9],"improved":[10,94],"and":[11,37,90,123,126,133,157,162,180,194],"generalizable":[12],"methods":[13,20],"to":[14,30,108],"detect":[15,67],"them.":[16],"Most":[17],"existing":[18],"detection":[19],"either":[21],"use":[22,120],"uni-modal":[23],"cues":[24,55],"or":[25],"rely":[26],"on":[27,52,105,154,183],"supervised":[28],"training":[29,58],"capture":[31,109],"dissonance":[33],"be-tween":[34],"audio":[36,89],"visual":[38,91],"modalities.":[39],"While":[40],"former":[42],"disregards":[43],"audio-visual":[45,54,112,130,190],"correspondences":[46,63],"entirely,":[47],"lat-ter":[49],"predominantly":[50],"focuses":[51],"discerning":[53],"within":[56],"corpus,":[59],"thereby":[60],"potentially":[61],"overlooking":[62],"that":[64,82,165],"can":[65],"help":[66],"unseen":[68],"deepfakes.":[69],"We":[70,176],"present":[71],"Audio-":[72],"Visual":[73],"Feature":[74],"Fusion":[75],"(AVFF),":[76],"a":[77,128],"two-stage":[78],"cross-modal":[79,117],"learning":[80,102,122,153,169],"method":[81],"explicitly":[83],"captures":[84],"correspondence":[86],"between":[87],"modalities":[92],"for":[93],"detection.":[96],"The":[97,137],"first":[98],"stage":[99],"pursues":[100],"representation":[101,168],"via":[103,151],"self-supervision":[104],"real":[106,156],"videos":[107],"intrinsic":[111],"correspondences.":[113],"To":[114],"extract":[115],"rich":[116],"representations,":[118],"contrastive":[121],"autoencoding":[124],"objectives,":[125],"introduce":[127],"novel":[129,167],"complementary":[131],"masking":[132],"feature":[134],"fusion":[135],"strategy.":[136],"learned":[138],"representations":[139],"are":[140],"tuned":[141],"second":[144],"stage,":[145],"where":[146],"classification":[148],"is":[149,171],"pursued":[150],"super-vised":[152],"both":[155],"fake":[158],"videos.":[159],"Extensive":[160],"exper-iments":[161],"analysis":[163],"suggest":[164],"our":[166],"paradigm":[170],"highly":[172],"discriminative":[173],"nature.":[175],"report":[177],"98.6%":[178],"accuracy":[179],"99.1%":[181],"AUC":[182],"FakeAVCeleb":[185],"dataset,":[186],"outperforming":[187],"current":[189],"state-of-the-art":[191],"by":[192],"14.9%":[193],"9.9%,":[195],"respectively.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":26},{"year":2025,"cited_by_count":35},{"year":2024,"cited_by_count":4}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}