{"id":"https://openalex.org/W4408352990","doi":"https://doi.org/10.1109/icassp49660.2025.10887985","title":"C3D-VIT: Consistency-Aware 3D Vision Transformer for Face Forgery Detection","display_name":"C3D-VIT: Consistency-Aware 3D Vision Transformer for Face Forgery Detection","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352990","doi":"https://doi.org/10.1109/icassp49660.2025.10887985"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887985","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887985","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5100458628","display_name":"Jingyi Zhang","orcid":"https://orcid.org/0000-0002-8172-5104"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingyi Zhang","raw_affiliation_strings":["Hikvision Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100364062","display_name":"Peng Zhang","orcid":"https://orcid.org/0000-0001-9428-9340"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng Zhang","raw_affiliation_strings":["Hikvision Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100426898","display_name":"Jingjing Wang","orcid":"https://orcid.org/0000-0003-3170-8952"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingjing Wang","raw_affiliation_strings":["Hikvision Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9966999888420105,"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/T11448","display_name":"Face recognition and analysis","score":0.9966999888420105,"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/T10828","display_name":"Biometric Identification and Security","score":0.9842000007629395,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9599999785423279,"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":0.6449161767959595},{"id":"https://openalex.org/keywords/face-detection","display_name":"Face detection","score":0.5842322111129761},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5659676790237427},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5111835598945618},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.48746776580810547},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48345646262168884},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.44428879022598267},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4413920044898987},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.2287643551826477},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11027917265892029},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.06367206573486328}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6449161767959595},{"id":"https://openalex.org/C4641261","wikidata":"https://www.wikidata.org/wiki/Q11681085","display_name":"Face detection","level":4,"score":0.5842322111129761},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5659676790237427},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5111835598945618},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.48746776580810547},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48345646262168884},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.44428879022598267},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4413920044898987},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2287643551826477},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11027917265892029},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.06367206573486328},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887985","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887985","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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":22,"referenced_works":["https://openalex.org/W2531409750","https://openalex.org/W2982058372","https://openalex.org/W3034196597","https://openalex.org/W3034577585","https://openalex.org/W3034713808","https://openalex.org/W3034900344","https://openalex.org/W3196204467","https://openalex.org/W3207531490","https://openalex.org/W4214680478","https://openalex.org/W4283802557","https://openalex.org/W4312472072","https://openalex.org/W4312830050","https://openalex.org/W4313007769","https://openalex.org/W4313127140","https://openalex.org/W4313177092","https://openalex.org/W4372342732","https://openalex.org/W4386075957","https://openalex.org/W4390873305","https://openalex.org/W4390874333","https://openalex.org/W6762480454","https://openalex.org/W6779607597","https://openalex.org/W6846486739"],"related_works":["https://openalex.org/W1967587236","https://openalex.org/W2384651879","https://openalex.org/W2336272890","https://openalex.org/W2151699605","https://openalex.org/W4308999381","https://openalex.org/W4312238398","https://openalex.org/W3211418293","https://openalex.org/W4308999963","https://openalex.org/W2133653344","https://openalex.org/W4312081214"],"abstract_inverted_index":{"Recently,":[0],"spatial":[1,37,106,127],"and":[2,27,41,69,107,123,128],"temporal":[3,39,108,129],"inconsistencies":[4,23],"have":[5],"been":[6],"shown":[7],"to":[8,48,62,87,131,156],"effectively":[9],"enhance":[10],"the":[11,118],"generalization":[12],"performance":[13],"of":[14],"face":[15,25],"forgery":[16,20,60,140],"detection,":[17],"as":[18],"common":[19],"strategies":[21],"create":[22],"among":[24],"regions":[26],"across":[28],"frames.":[29],"However,":[30],"current":[31,73],"methods":[32,75],"often":[33],"focus":[34],"on":[35,77],"either":[36],"or":[38,59,139],"modeling":[40,102,110],"involve":[42],"complex":[43],"modules":[44],"that":[45,104],"are":[46],"difficult":[47],"integrate":[49],"into":[50,148],"other":[51],"frameworks.":[52],"Some":[53],"approaches":[54],"require":[55],"extra":[56,136],"training":[57,137],"data":[58,138],"masks":[61],"learn":[63],"consistency":[64,101,109,134],"features,":[65],"limiting":[66],"their":[67],"applicability":[68],"performance.":[70],"Additionally,":[71],"most":[72],"spatio-temporal":[74],"rely":[76],"CNNs,":[78],"with":[79],"few":[80],"designed":[81],"for":[82,90],"transformers,":[83],"making":[84],"it":[85],"challenging":[86],"adapt":[88],"them":[89],"transformer":[91,113,150],"use.":[92],"To":[93],"address":[94],"these":[95],"issues,":[96],"we":[97,116],"propose":[98],"an":[99],"efficient":[100],"block":[103,143],"unifies":[105],"within":[111],"a":[112,149],"framework.":[114],"Specifically,":[115],"calculate":[117],"reconstruction":[119],"error":[120],"between":[121],"features":[122],"predictions":[124],"via":[125],"neighboring":[126],"dimensions":[130],"explicitly":[132],"model":[133],"without":[135],"masks.":[141],"This":[142],"can":[144],"be":[145],"seamlessly":[146],"integrated":[147],"framework,":[151],"adding":[152],"less":[153],"than":[154],"1%":[155],"computing":[157],"costs.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}