{"id":"https://openalex.org/W4312732149","doi":"https://doi.org/10.1109/lsp.2022.3214768","title":"Transformer-Based Feature Compensation and Aggregation for DeepFake Detection","display_name":"Transformer-Based Feature Compensation and Aggregation for DeepFake Detection","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4312732149","doi":"https://doi.org/10.1109/lsp.2022.3214768"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2022.3214768","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2022.3214768","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","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/A5040257967","display_name":"Zichang Tan","orcid":"https://orcid.org/0000-0002-8501-4123"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zichang Tan","raw_affiliation_strings":["Institute of Deep Learning, Baidu Research, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8501-4123","affiliations":[{"raw_affiliation_string":"Institute of Deep Learning, Baidu Research, Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101448608","display_name":"Zhichao Yang","orcid":"https://orcid.org/0009-0008-3398-1286"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhichao Yang","raw_affiliation_strings":["Institute of Deep Learning, Baidu Research, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Deep Learning, Baidu Research, Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077867418","display_name":"Changtao Miao","orcid":"https://orcid.org/0000-0002-7634-9992"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changtao Miao","raw_affiliation_strings":["Institute of Deep Learning, Baidu Research, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7634-9992","affiliations":[{"raw_affiliation_string":"Institute of Deep Learning, Baidu Research, Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085022758","display_name":"Guodong Guo","orcid":"https://orcid.org/0000-0001-9583-0055"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guodong Guo","raw_affiliation_strings":["Institute of Deep Learning, Baidu Research, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9583-0055","affiliations":[{"raw_affiliation_string":"Institute of Deep Learning, Baidu Research, Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.8736,"has_fulltext":false,"cited_by_count":51,"citation_normalized_percentile":{"value":0.96389451,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"29","issue":null,"first_page":"2183","last_page":"2187"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9993000030517578,"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":0.9904999732971191,"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":0.7459908723831177},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6080834865570068},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.581097424030304},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.5158997774124146},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5140601396560669},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5022289752960205},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.46368661522865295},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.44238829612731934},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.340446412563324}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7459908723831177},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6080834865570068},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.581097424030304},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.5158997774124146},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5140601396560669},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5022289752960205},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.46368661522865295},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.44238829612731934},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.340446412563324},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2022.3214768","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2022.3214768","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2486034530","https://openalex.org/W2899663614","https://openalex.org/W2904573504","https://openalex.org/W2942074357","https://openalex.org/W2963684180","https://openalex.org/W2982058372","https://openalex.org/W2987809008","https://openalex.org/W3034196597","https://openalex.org/W3034214108","https://openalex.org/W3034713808","https://openalex.org/W3048932886","https://openalex.org/W3094502228","https://openalex.org/W3094728142","https://openalex.org/W3102988878","https://openalex.org/W3108854358","https://openalex.org/W3137963805","https://openalex.org/W3154326567","https://openalex.org/W3158353280","https://openalex.org/W3160694286","https://openalex.org/W3174508664","https://openalex.org/W3174656926","https://openalex.org/W3176241004","https://openalex.org/W3183999072","https://openalex.org/W3192932902","https://openalex.org/W3196204467","https://openalex.org/W3207353304","https://openalex.org/W3213601271","https://openalex.org/W4206742848","https://openalex.org/W4226024856","https://openalex.org/W4285044753","https://openalex.org/W4287888931","https://openalex.org/W4290994941","https://openalex.org/W4312967678","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6755977528","https://openalex.org/W6757599822","https://openalex.org/W6769920582","https://openalex.org/W6784333009","https://openalex.org/W6791705549","https://openalex.org/W6797578546"],"related_works":["https://openalex.org/W2811390910","https://openalex.org/W2146076056","https://openalex.org/W2144059113","https://openalex.org/W3003836766","https://openalex.org/W2136054869","https://openalex.org/W1964120219","https://openalex.org/W2000165426","https://openalex.org/W2695951553","https://openalex.org/W2151515990","https://openalex.org/W2806155925"],"abstract_inverted_index":{"Deepfake":[0],"detection":[1],"has":[2],"attracted":[3],"increasing":[4],"attention":[5],"in":[6],"recent":[7],"years.":[8],"In":[9,108],"this":[10],"paper,":[11],"we":[12,37,72],"propose":[13,38,73],"a":[14,39,45,91],"transformer-based":[15],"framework":[16],"with":[17],"feature":[18],"compensation":[19,130],"and":[20,55,68,78,95,119,131,145,154],"aggregation":[21],"(Trans-FCA)":[22],"to":[23,49],"extract":[24],"rich":[25,120],"forgery":[26,121],"cues":[27,112],"for":[28,35,65,166],"deepfake":[29,167],"detection.":[30,168],"To":[31,59],"compensate":[32],"local":[33,56,117],"features":[34,54,61,89,101],"transformers,":[36],"Locality":[40],"Compensation":[41],"Block":[42],"(LCB)":[43],"containing":[44],"Global-Local":[46],"Cross-Attention":[47],"(GLCA)":[48],"attentively":[50,86],"fuse":[51],"global":[52,111],"transformer":[53,115],"convolutional":[57],"features.":[58],"aggregate":[60],"of":[62,105,150,163],"all":[63,99],"layers":[64],"capturing":[66],"comprehensive":[67],"various":[69],"fake":[70],"flaws,":[71],"Multi-head":[74],"Clustering":[75],"Projection":[76],"(MCP)":[77],"Frequency-guided":[79],"Fusion":[80],"Module":[81],"(FFM),":[82],"where":[83],"the":[84,96,103,127,139,161],"MCP":[85],"reduces":[87],"redundant":[88],"into":[90],"few":[92],"concentrated":[93],"clusters,":[94],"FFM":[97],"interacts":[98],"clustered":[100],"under":[102],"guidance":[104],"frequency":[106],"cues.":[107],"Trans-FCA,":[109],"besides":[110],"captured":[113,125],"by":[114],"architecture,":[116],"details":[118],"defects":[122],"are":[123],"also":[124],"using":[126],"proposed":[128],"fetaure":[129],"aggregation.":[132],"Extensive":[133],"experiments":[134],"show":[135],"our":[136,164],"method":[137],"outperforms":[138],"state-of-the-art":[140],"methods":[141],"on":[142,152,156],"both":[143],"intra-dataset":[144],"cross-dataset":[146],"testings":[147],"(with":[148],"AUCs":[149],"99.85%":[151],"FaceForensics++":[153],"78.57%":[155],"Celeb-DF),":[157],"which":[158],"clearly":[159],"demonstrates":[160],"superiority":[162],"Trans-FCA":[165]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":25},{"year":2024,"cited_by_count":21},{"year":2023,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}