{"id":"https://openalex.org/W3154326567","doi":"https://doi.org/10.1145/3512527.3531415","title":"M2TR: Multi-modal Multi-scale Transformers for Deepfake Detection","display_name":"M2TR: Multi-modal Multi-scale Transformers for Deepfake Detection","publication_year":2022,"publication_date":"2022-06-23","ids":{"openalex":"https://openalex.org/W3154326567","doi":"https://doi.org/10.1145/3512527.3531415","mag":"3154326567"},"language":"en","primary_location":{"id":"doi:10.1145/3512527.3531415","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3512527.3531415","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Multimedia Retrieval","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/A5100772955","display_name":"Junke Wang","orcid":"https://orcid.org/0000-0002-9570-9973"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junke Wang","raw_affiliation_strings":["Fudan University, shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026167547","display_name":"Zuxuan Wu","orcid":"https://orcid.org/0000-0002-8689-5807"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zuxuan Wu","raw_affiliation_strings":["Fudan University, shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008108433","display_name":"Wenhao Ouyang","orcid":"https://orcid.org/0000-0002-2913-8527"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhao Ouyang","raw_affiliation_strings":["Fudan University, shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102997681","display_name":"Xintong Han","orcid":"https://orcid.org/0000-0003-2842-1803"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xintong Han","raw_affiliation_strings":["Huya Inc, shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huya Inc, shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100373492","display_name":"Jingjing Chen","orcid":"https://orcid.org/0000-0003-3148-264X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingjing Chen","raw_affiliation_strings":["Fudan University, shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047962986","display_name":"Yu\u2013Gang Jiang","orcid":"https://orcid.org/0000-0002-1907-8567"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Gang Jiang","raw_affiliation_strings":["Fudan University, shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109497841","display_name":"Ser-Nam Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ser-Nam Li","raw_affiliation_strings":["Meta AI, Newyork, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI, Newyork, NY, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":333,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"615","last_page":"623"},"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":0.9998000264167786,"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":0.9998000264167786,"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":0.9998000264167786,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9984999895095825,"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":0.808806300163269},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5994594693183899},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5651018619537354},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4937838017940521},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.4743698537349701},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40709006786346436},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.39154160022735596},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36243003606796265}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.808806300163269},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5994594693183899},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5651018619537354},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4937838017940521},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.4743698537349701},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40709006786346436},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39154160022735596},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36243003606796265},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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},{"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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3512527.3531415","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3512527.3531415","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W1995712965","https://openalex.org/W2009130368","https://openalex.org/W2108598243","https://openalex.org/W2115252128","https://openalex.org/W2129112648","https://openalex.org/W2187089797","https://openalex.org/W2301937176","https://openalex.org/W2344328033","https://openalex.org/W2603123944","https://openalex.org/W2603351312","https://openalex.org/W2604730366","https://openalex.org/W2626778328","https://openalex.org/W2726515241","https://openalex.org/W2735904389","https://openalex.org/W2738406145","https://openalex.org/W2740546229","https://openalex.org/W2761659801","https://openalex.org/W2797823148","https://openalex.org/W2883861033","https://openalex.org/W2891145043","https://openalex.org/W2896457183","https://openalex.org/W2904573504","https://openalex.org/W2906447902","https://openalex.org/W2907097116","https://openalex.org/W2912336782","https://openalex.org/W2942074357","https://openalex.org/W2946948417","https://openalex.org/W2952148331","https://openalex.org/W2952246410","https://openalex.org/W2962958939","https://openalex.org/W2963524571","https://openalex.org/W2963684180","https://openalex.org/W2963782415","https://openalex.org/W2966880194","https://openalex.org/W2979980060","https://openalex.org/W2981523288","https://openalex.org/W2982058372","https://openalex.org/W2987809008","https://openalex.org/W2990522196","https://openalex.org/W2991318208","https://openalex.org/W2991377405","https://openalex.org/W2998158928","https://openalex.org/W3004909676","https://openalex.org/W3008823916","https://openalex.org/W3024079478","https://openalex.org/W3027351130","https://openalex.org/W3030520226","https://openalex.org/W3034196597","https://openalex.org/W3034577585","https://openalex.org/W3034684802","https://openalex.org/W3034713808","https://openalex.org/W3035471785","https://openalex.org/W3042844210","https://openalex.org/W3048341421","https://openalex.org/W3082274269","https://openalex.org/W3083246145","https://openalex.org/W3086623482","https://openalex.org/W3092462694","https://openalex.org/W3092619908","https://openalex.org/W3094190932","https://openalex.org/W3094502228","https://openalex.org/W3094728142","https://openalex.org/W3095986900","https://openalex.org/W3096609285","https://openalex.org/W3102542372","https://openalex.org/W3128609017","https://openalex.org/W3134801097","https://openalex.org/W3158353280","https://openalex.org/W3174508664","https://openalex.org/W4312981036"],"related_works":["https://openalex.org/W2486460843","https://openalex.org/W2168109476","https://openalex.org/W1968121071","https://openalex.org/W2379392295","https://openalex.org/W3160965418","https://openalex.org/W2061647633","https://openalex.org/W613940353","https://openalex.org/W2020254986","https://openalex.org/W2686985752","https://openalex.org/W2320915480"],"abstract_inverted_index":{"The":[0],"widespread":[1],"dissemination":[2],"of":[3,45,97,118],"Deepfakes":[4],"demands":[5],"effective":[6],"approaches":[7],"that":[8],"can":[9],"detect":[10,49,62],"perceptually":[11],"convincing":[12],"forged":[13],"images.":[14],"In":[15,32,81],"this":[16],"paper,":[17],"we":[18,34,88],"aim":[19],"to":[20,48,61,69,83,114],"capture":[21],"the":[22,66,116,119],"subtle":[23],"manipulation":[24],"artifacts":[25,64],"at":[26,54],"different":[27,46,55],"scales":[28],"using":[29],"transformer":[30],"models.":[31],"particular,":[33],"introduce":[35,89],"a":[36,74,90],"Multi-modal":[37],"Multi-scale":[38],"TRansformer":[39],"(M2TR),":[40],"which":[41,95,122],"operates":[42],"on":[43],"patches":[44],"sizes":[47],"local":[50],"inconsistencies":[51],"in":[52,65],"images":[53],"spatial":[56],"levels.":[57],"M2TR":[58],"further":[59],"learns":[60],"forgery":[63],"frequency":[67],"domain":[68],"complement":[70],"RGB":[71],"information":[72],"through":[73],"carefully":[75],"designed":[76],"cross":[77],"modality":[78],"fusion":[79],"block.":[80],"addition,":[82],"stimulate":[84],"Deepfake":[85,92,125],"detection":[86,126],"research,":[87],"high-quality":[91],"dataset,":[93],"SR-DF,":[94],"consists":[96],"4,000":[98],"DeepFake":[99],"videos":[100],"generated":[101],"by":[102,128],"state-of-the-art":[103,124],"face":[104],"swapping":[105],"and":[106],"facial":[107],"reenactment":[108],"methods.":[109],"We":[110],"conduct":[111],"extensive":[112],"experiments":[113],"verify":[115],"effectiveness":[117],"proposed":[120],"method,":[121],"outperforms":[123],"methods":[127],"clear":[129],"margins.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":39},{"year":2025,"cited_by_count":108},{"year":2024,"cited_by_count":87},{"year":2023,"cited_by_count":66},{"year":2022,"cited_by_count":28},{"year":2021,"cited_by_count":5}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}