{"id":"https://openalex.org/W4408780318","doi":"https://doi.org/10.1109/tcds.2025.3554477","title":"AVTENet: A Human-Cognition-Inspired Audio-Visual Transformer-Based Ensemble Network for Video Deepfake Detection","display_name":"AVTENet: A Human-Cognition-Inspired Audio-Visual Transformer-Based Ensemble Network for Video Deepfake Detection","publication_year":2025,"publication_date":"2025-03-24","ids":{"openalex":"https://openalex.org/W4408780318","doi":"https://doi.org/10.1109/tcds.2025.3554477"},"language":"en","primary_location":{"id":"doi:10.1109/tcds.2025.3554477","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2025.3554477","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"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 Cognitive and Developmental Systems","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/A5016272627","display_name":"Ammarah Hashmi","orcid":"https://orcid.org/0000-0002-1973-6902"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Ammarah Hashmi","raw_affiliation_strings":["Social Networks and Human-Centered Computing Program, Taiwan International Graduate Program, Academia Sinica, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-1973-6902","affiliations":[{"raw_affiliation_string":"Social Networks and Human-Centered Computing Program, Taiwan International Graduate Program, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018523027","display_name":"Sahibzada Adil Shahzad","orcid":"https://orcid.org/0009-0000-5591-8423"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Sahibzada Adil Shahzad","raw_affiliation_strings":["Social Networks and Human-Centered Computing Program, Taiwan International Graduate Program, Academia Sinica, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0009-0000-5591-8423","affiliations":[{"raw_affiliation_string":"Social Networks and Human-Centered Computing Program, Taiwan International Graduate Program, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051264473","display_name":"Chia\u2010Wen Lin","orcid":"https://orcid.org/0000-0002-9097-2318"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chia Wen Lin","raw_affiliation_strings":["Department of Electrical Engineering and the Institute of Communications Engineering, National Tsing Hua University, Hsinchu, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-9097-2318","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and the Institute of Communications Engineering, National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0000-0001-6956-0418","affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taipei, Taiwan","Social Networks and Human-Centered Computing Program, Taiwan International Graduate Program, Academia Sinica, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0000-0003-3599-5071","affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]},{"raw_affiliation_string":"Social Networks and Human-Centered Computing Program, Taiwan International Graduate Program, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5016272627"],"corresponding_institution_ids":["https://openalex.org/I4210098366"],"apc_list":null,"apc_paid":null,"fwci":9.066,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.97858913,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"17","issue":"6","first_page":"1360","last_page":"1376"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9940999746322632,"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":0.9940999746322632,"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":0.965399980545044,"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":0.9635000228881836,"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":0.8910038471221924},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6908372044563293},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.65449458360672},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.5844793915748596},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4425346255302429},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3893295228481293},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3825448155403137},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3512241244316101},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.08146876096725464},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.06517311930656433}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8910038471221924},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6908372044563293},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.65449458360672},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.5844793915748596},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4425346255302429},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3893295228481293},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3825448155403137},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3512241244316101},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.08146876096725464},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.06517311930656433},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcds.2025.3554477","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2025.3554477","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"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 Cognitive and Developmental Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5799999833106995}],"awards":[{"id":"https://openalex.org/G7023690765","display_name":null,"funder_award_id":"NSTC 113-2634-F-002-003","funder_id":"https://openalex.org/F4320331164","funder_display_name":"National Science and Technology Council"},{"id":"https://openalex.org/G7340088035","display_name":null,"funder_award_id":"NSTC 112-2221-E-001-009-MY3","funder_id":"https://openalex.org/F4320331164","funder_display_name":"National Science and Technology Council"},{"id":"https://openalex.org/G86985246","display_name":null,"funder_award_id":"AS-GC-111-M01","funder_id":"https://openalex.org/F4320321041","funder_display_name":"Academia Sinica"}],"funders":[{"id":"https://openalex.org/F4320321041","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784"},{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W2301937176","https://openalex.org/W2531409750","https://openalex.org/W2558151185","https://openalex.org/W2726515241","https://openalex.org/W2731516742","https://openalex.org/W2806833697","https://openalex.org/W2808631503","https://openalex.org/W2891145043","https://openalex.org/W2913399670","https://openalex.org/W2914447220","https://openalex.org/W2963684180","https://openalex.org/W2984529706","https://openalex.org/W2984700035","https://openalex.org/W2990452356","https://openalex.org/W2999634272","https://openalex.org/W3016011581","https://openalex.org/W3019200173","https://openalex.org/W3081492798","https://openalex.org/W3093010840","https://openalex.org/W3093077034","https://openalex.org/W3096831136","https://openalex.org/W3135085786","https://openalex.org/W3135413014","https://openalex.org/W3135785775","https://openalex.org/W3159301005","https://openalex.org/W3172737781","https://openalex.org/W3175342695","https://openalex.org/W3176193246","https://openalex.org/W3196974791","https://openalex.org/W3197123936","https://openalex.org/W3206817819","https://openalex.org/W3215112182","https://openalex.org/W4200240631","https://openalex.org/W4214612132","https://openalex.org/W4214691743","https://openalex.org/W4226494101","https://openalex.org/W4285230750","https://openalex.org/W4285263298","https://openalex.org/W4295046123","https://openalex.org/W4298126018","https://openalex.org/W4303444960","https://openalex.org/W4311719620","https://openalex.org/W4312095900","https://openalex.org/W4312095999","https://openalex.org/W4320882980","https://openalex.org/W4360993864","https://openalex.org/W4372260514","https://openalex.org/W4385270415","https://openalex.org/W4385801058","https://openalex.org/W4385805162","https://openalex.org/W4387917764","https://openalex.org/W4391128508","https://openalex.org/W4391252582","https://openalex.org/W4392942875","https://openalex.org/W4393405305","https://openalex.org/W4398789263","https://openalex.org/W4402666392","https://openalex.org/W4402915519"],"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":{"The":[0,223],"recent":[1],"proliferation":[2],"of":[3,13,55,96,116,130,186,209],"hyper-realistic":[4],"deepfake":[5,56,117],"videos":[6,26,57],"has":[7],"drawn":[8],"attention":[9],"to":[10,42,88,126,151],"the":[11,94,104,114,128,135,161,187,194,210],"threat":[12],"audio":[14,32,38,84],"and":[15,39,60,63,85,90,93,123,147,178,201,207],"visual":[16,29,40,61,86,124],"forgeries.":[17],"Most":[18],"previous":[19],"studies":[20],"on":[21,52,67,182,205],"detecting":[22,220],"artificial":[23],"intelligence-generated":[24],"fake":[25],"only":[27],"utilize":[28],"modality":[30],"or":[31],"modality.":[33],"While":[34],"some":[35],"methods":[36,181,200],"exploit":[37],"modalities":[41],"detect":[43],"forged":[44],"videos,":[45],"they":[46],"have":[47],"not":[48],"been":[49],"comprehensively":[50],"evaluated":[51],"multimodal":[53,165],"datasets":[54],"involving":[58],"acoustic":[59,122],"manipulations,":[62],"are":[64],"mostly":[65],"based":[66],"convolutional":[68],"neural":[69],"networks":[70],"with":[71],"low":[72],"detection":[73],"accuracy.":[74],"Considering":[75],"that":[76,143,193,226],"human":[77],"cognition":[78],"instinctively":[79],"integrates":[80,138],"multisensory":[81],"information":[82],"including":[83],"cues":[87,150],"perceive":[89],"interpret":[91],"content":[92],"success":[95],"transformer":[97],"in":[98,155,219],"various":[99],"fields,":[100],"this":[101],"study":[102],"introduces":[103],"audio-visual":[105,148],"transformer-based":[106,141],"ensemble":[107],"network":[108],"(AVTENet).":[109],"This":[110],"innovative":[111],"framework":[112],"tackles":[113],"complexities":[115],"technology":[118],"by":[119],"integrating":[120],"both":[121],"manipulations":[125],"enhance":[127],"accuracy":[129],"video":[131,221],"forgery":[132],"detection.":[133],"Specifically,":[134],"proposed":[136,195],"model":[137,196],"several":[139,179],"purely":[140],"variants":[142],"capture":[144],"video,":[145],"audio,":[146],"salient":[149],"reach":[152],"a":[153,170],"consensus":[154],"prediction.":[156],"For":[157,169],"evaluation,":[158],"we":[159,173],"use":[160],"recently":[162],"released":[163],"benchmark":[164],"audio-video":[166],"FakeAVCeleb":[167,188,211],"dataset.":[168,189,212],"detailed":[171],"analysis,":[172],"evaluate":[174],"AVTENet,":[175],"its":[176],"variants,":[177],"existing":[180,199],"multiple":[183],"test":[184],"sets":[185],"Experimental":[190],"results":[191,224],"show":[192,225],"outperforms":[197,229],"all":[198],"achieves":[202],"state-of-the-art":[203],"performance":[204],"Testset-I":[206],"Testset-II":[208],"We":[213],"also":[214],"compare":[215],"AVTENet":[216,227],"against":[217],"humans":[218],"forgery.":[222],"significantly":[228],"humans.":[230]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":3}],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}
