{"id":"https://openalex.org/W4392904345","doi":"https://doi.org/10.1109/icassp48485.2024.10447248","title":"Cross-Modality and Within-Modality Regularization for Audio-Visual Deepfake Detection","display_name":"Cross-Modality and Within-Modality Regularization for Audio-Visual Deepfake Detection","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904345","doi":"https://doi.org/10.1109/icassp48485.2024.10447248"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447248","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447248","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5023152132","display_name":"Heqing Zou","orcid":"https://orcid.org/0000-0003-0038-2822"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Heqing Zou","raw_affiliation_strings":["Nanyang Technological University,Singapore","Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047030842","display_name":"Meng Shen","orcid":"https://orcid.org/0000-0002-1867-0972"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Meng Shen","raw_affiliation_strings":["Nanyang Technological University,Singapore","Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074544822","display_name":"Yu\u2010Chen Hu","orcid":"https://orcid.org/0000-0002-5055-3645"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yuchen Hu","raw_affiliation_strings":["Nanyang Technological University,Singapore","Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418553","display_name":"Chen Chen","orcid":"https://orcid.org/0000-0003-2541-6283"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chen Chen","raw_affiliation_strings":["Nanyang Technological University,Singapore","Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["Nanyang Technological University,Singapore","Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009372982","display_name":"Deepu Rajan","orcid":"https://orcid.org/0000-0001-7788-8368"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Deepu Rajan","raw_affiliation_strings":["Nanyang Technological University,Singapore","Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4900","last_page":"4904"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9959999918937683,"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":0.9958999752998352,"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/modality","display_name":"Modality (human\u2013computer interaction)","score":0.8453707695007324},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6904129385948181},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5968724489212036},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5934960842132568},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5384238958358765},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3286891579627991},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.10984855890274048}],"concepts":[{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.8453707695007324},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6904129385948181},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5968724489212036},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5934960842132568},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5384238958358765},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3286891579627991},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.10984855890274048}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447248","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447248","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":26,"referenced_works":["https://openalex.org/W2808706139","https://openalex.org/W2984700035","https://openalex.org/W3093077034","https://openalex.org/W3096831136","https://openalex.org/W3162293946","https://openalex.org/W3197123936","https://openalex.org/W3199125932","https://openalex.org/W3205798727","https://openalex.org/W4214691743","https://openalex.org/W4221138880","https://openalex.org/W4283817039","https://openalex.org/W4287758545","https://openalex.org/W4297841258","https://openalex.org/W4312095999","https://openalex.org/W4320882980","https://openalex.org/W4360993864","https://openalex.org/W4385571742","https://openalex.org/W4385801058","https://openalex.org/W4385805162","https://openalex.org/W4386928847","https://openalex.org/W6640963894","https://openalex.org/W6752888775","https://openalex.org/W6784810453","https://openalex.org/W6791353385","https://openalex.org/W6799942944","https://openalex.org/W6810168380"],"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/W2385859805","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731"],"abstract_inverted_index":{"Audio-visual":[0],"deepfake":[1,39],"detection":[2],"scrutinizes":[3],"manipulations":[4,37],"in":[5,30,38],"public":[6,100],"video":[7],"using":[8],"complementary":[9],"multimodal":[10,18,21,55],"cues.":[11],"Current":[12],"methods,":[13],"which":[14],"train":[15],"on":[16,98],"fused":[17],"data":[19],"for":[20,65],"targets":[22,91],"face":[23],"challenges":[24],"due":[25],"to":[26,50,73,92],"uncertainties":[27],"and":[28,47,68,107],"inconsistencies":[29],"learned":[31],"representations":[32,88],"caused":[33],"by":[34],"independent":[35],"modality":[36,52,66,79],"videos.":[40],"To":[41],"address":[42],"this,":[43],"we":[44],"propose":[45],"cross-modality":[46,70],"within-modality":[48,83],"regularization":[49,71,84],"preserve":[51],"distinctions":[53],"during":[54],"representation":[56],"learning.":[57],"Our":[58],"approach":[59],"includes":[60],"an":[61],"audio-visual":[62,76,101],"transformer":[63],"module":[64,72,85],"correspondence":[67],"a":[69,82],"align":[74],"paired":[75],"signals,":[77],"preserving":[78],"distinctions.":[80],"Simultaneously,":[81],"refines":[86],"unimodal":[87],"with":[89],"modality-specific":[90],"retain":[93],"modal-specific":[94],"details.":[95],"Experimental":[96],"results":[97],"the":[99,105],"dataset,":[102],"FakeAVCeleb,":[103],"demonstrate":[104],"effectiveness":[106],"competitiveness":[108],"of":[109],"our":[110],"approach.":[111]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
