{"id":"https://openalex.org/W7151598350","doi":"https://doi.org/10.1007/s00138-026-01809-w","title":"Cross-dataset video deepfake detection using Transformer and CNN architectures","display_name":"Cross-dataset video deepfake detection using Transformer and CNN architectures","publication_year":2026,"publication_date":"2026-04-07","ids":{"openalex":"https://openalex.org/W7151598350","doi":"https://doi.org/10.1007/s00138-026-01809-w"},"language":"en","primary_location":{"id":"doi:10.1007/s00138-026-01809-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00138-026-01809-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00138-026-01809-w.pdf","source":{"id":"https://openalex.org/S27728525","display_name":"Machine Vision and Applications","issn_l":"0932-8092","issn":["0932-8092","1432-1769"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Vision and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s00138-026-01809-w.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075090284","display_name":"\u0393\u03b5\u03ce\u03c1\u03b3\u03b9\u03bf\u03c2 \u03a0\u03b5\u03c4\u03bc\u03b5\u03b6\u03ac\u03c2","orcid":"https://orcid.org/0000-0002-3371-569X"},"institutions":[{"id":"https://openalex.org/I89506807","display_name":"University of Western Macedonia","ror":"https://ror.org/00a5pe906","country_code":"GR","type":"education","lineage":["https://openalex.org/I89506807"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Georgios Petmezas","raw_affiliation_strings":["University of Western Macedonia, 52100, Kastoria, Greece"],"raw_orcid":"https://orcid.org/0000-0002-3371-569X","affiliations":[{"raw_affiliation_string":"University of Western Macedonia, 52100, Kastoria, Greece","institution_ids":["https://openalex.org/I89506807"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5075090284"],"corresponding_institution_ids":["https://openalex.org/I89506807"],"apc_list":{"value":3090,"currency":"USD","value_usd":3090},"apc_paid":{"value":3090,"currency":"USD","value_usd":3090},"fwci":19.5073,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.99328064,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"37","issue":"3","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.8409000039100647,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.8409000039100647,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.0471000000834465,"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/T11448","display_name":"Face recognition and analysis","score":0.012500000186264515,"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/software-deployment","display_name":"Software deployment","score":0.6711999773979187},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5665000081062317},{"id":"https://openalex.org/keywords/sophistication","display_name":"Sophistication","score":0.49639999866485596},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4740999937057495},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.46650001406669617},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.34709998965263367},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.33399999141693115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8374999761581421},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6711999773979187},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5665000081062317},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5602999925613403},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5353000164031982},{"id":"https://openalex.org/C168725872","wikidata":"https://www.wikidata.org/wiki/Q991663","display_name":"Sophistication","level":2,"score":0.49639999866485596},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4740999937057495},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.46650001406669617},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.34709998965263367},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.33399999141693115},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3257000148296356},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.313400000333786},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.29249998927116394},{"id":"https://openalex.org/C140547941","wikidata":"https://www.wikidata.org/wiki/Q7797194","display_name":"Threat model","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.250900000333786},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s00138-026-01809-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00138-026-01809-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00138-026-01809-w.pdf","source":{"id":"https://openalex.org/S27728525","display_name":"Machine Vision and Applications","issn_l":"0932-8092","issn":["0932-8092","1432-1769"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Vision and Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s00138-026-01809-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00138-026-01809-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00138-026-01809-w.pdf","source":{"id":"https://openalex.org/S27728525","display_name":"Machine Vision and Applications","issn_l":"0932-8092","issn":["0932-8092","1432-1769"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Vision and Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320318628","display_name":"Hellenic Academic Libraries Link","ror":null},{"id":"https://openalex.org/F4320319174","display_name":"University of Western Macedonia","ror":"https://ror.org/00a5pe906"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7151598350.pdf","grobid_xml":"https://content.openalex.org/works/W7151598350.grobid-xml"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2891145043","https://openalex.org/W2963091558","https://openalex.org/W2963720850","https://openalex.org/W2982058372","https://openalex.org/W3034196597","https://openalex.org/W3034530968","https://openalex.org/W3034552680","https://openalex.org/W3034713808","https://openalex.org/W3084352865","https://openalex.org/W3094728142","https://openalex.org/W3155203878","https://openalex.org/W3175342695","https://openalex.org/W3178284600","https://openalex.org/W3188946793","https://openalex.org/W4210428539","https://openalex.org/W4213449918","https://openalex.org/W4307955901","https://openalex.org/W4312473638","https://openalex.org/W4312560592","https://openalex.org/W4385617675","https://openalex.org/W4387010739","https://openalex.org/W4387874311","https://openalex.org/W4388851105","https://openalex.org/W4396951962","https://openalex.org/W4399138486","https://openalex.org/W4401028289","https://openalex.org/W4401210768","https://openalex.org/W4401814887","https://openalex.org/W4402727609","https://openalex.org/W4403914979","https://openalex.org/W4405838418","https://openalex.org/W4406802589","https://openalex.org/W4406804129","https://openalex.org/W4407600083","https://openalex.org/W4408311646","https://openalex.org/W4408901929","https://openalex.org/W4409496318","https://openalex.org/W4409618198","https://openalex.org/W4410536721","https://openalex.org/W4410595226","https://openalex.org/W4410951336","https://openalex.org/W4411241923","https://openalex.org/W4411336894","https://openalex.org/W4412090121","https://openalex.org/W4412196232","https://openalex.org/W4412387456","https://openalex.org/W4412446713","https://openalex.org/W4412923398","https://openalex.org/W4416946943","https://openalex.org/W7125595419"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"The":[1],"growing":[2],"sophistication":[3],"of":[4,14,43,63,102,140,167,182,193],"deepfake":[5,70,197],"generation":[6],"techniques":[7],"poses":[8],"serious":[9],"challenges":[10],"to":[11,83],"the":[12,41,100,116,125,138,165,178],"authenticity":[13],"digital":[15],"media,":[16],"with":[17,76,89,131,150],"potential":[18],"risks":[19],"spanning":[20],"privacy,":[21],"security":[22],"and":[23,46,65,87,128,134,180,190,195],"misinformation.":[24],"Deep":[25],"learning":[26],"(DL)":[27],"methods":[28],"have":[29],"shown":[30],"significant":[31],"promise":[32],"in":[33,39,54],"detecting":[34],"such":[35],"manipulations;":[36],"however,":[37],"inconsistencies":[38],"application,":[40],"absence":[42],"standardized":[44],"pipelines":[45],"limited":[47,90],"cross-dataset":[48,85],"generalization":[49,86],"hinder":[50],"their":[51],"reliable":[52],"deployment":[53,192],"real-world":[55],"scenarios.":[56],"This":[57],"work":[58],"presents":[59],"a":[60,77],"comprehensive":[61],"evaluation":[62],"Transformer-":[64],"CNN-based":[66],"architectures":[67],"for":[68,160,187],"video":[69],"detection.":[71],"Multiple":[72],"benchmark":[73],"datasets,":[74],"along":[75],"novel":[78],"facial-reenactment":[79],"dataset,":[80],"are":[81],"used":[82],"investigate":[84],"pretraining":[88],"fine-tuning":[91],"on":[92,106],"small":[93],"target":[94],"subsets":[95],"(10\u201330%).":[96],"Additionally,":[97],"we":[98],"analyze":[99],"impact":[101],"temporal":[103,169],"window":[104],"length":[105,157],"detection":[107],"performance.":[108],"Experimental":[109],"results":[110],"demonstrate":[111],"that":[112],"TimeSformer":[113],"consistently":[114],"achieves":[115],"highest":[117],"performance,":[118],"reaching":[119],"78.4%":[120],"accuracy,":[121],"0.801":[122],"area":[123],"under":[124],"curve":[126],"(AUC)":[127],"77.0%":[129],"F1-score":[130],"96-frame":[132],"clips":[133],"30%":[135],"fine-tuning,":[136,149],"confirming":[137],"advantage":[139],"joint":[141],"spatiotemporal":[142],"modeling.":[143],"All":[144],"models":[145],"benefit":[146],"from":[147],"moderate":[148],"gains":[151],"plateauing":[152],"beyond":[153],"20%.":[154],"Increasing":[155],"clip":[156],"enhances":[158],"performance":[159],"temporally":[161],"aware":[162],"models,":[163],"highlighting":[164],"importance":[166],"extended":[168],"context.":[170],"Overall,":[171],"this":[172],"study":[173],"provides":[174],"empirical":[175],"evidence":[176],"into":[177],"strengths":[179],"limitations":[181],"current":[183],"architectures,":[184],"offering":[185],"guidance":[186],"future":[188],"research":[189],"practical":[191],"robust":[194],"generalizable":[196],"detectors.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":4}],"updated_date":"2026-08-16T07:02:28.622633","created_date":"2026-04-08T00:00:00"}