{"id":"https://openalex.org/W7160271654","doi":"https://doi.org/10.1109/wacv61042.2026.00692","title":"AuViRe: Audio-visual Speech Representation Reconstruction for Deepfake Temporal Localization","display_name":"AuViRe: Audio-visual Speech Representation Reconstruction for Deepfake Temporal Localization","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160271654","doi":"https://doi.org/10.1109/wacv61042.2026.00692"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00692","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00692","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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/A5024874767","display_name":"Christos Koutlis","orcid":"https://orcid.org/0000-0003-3682-408X"},"institutions":[{"id":"https://openalex.org/I4210093649","display_name":"Information Technologies Institute","ror":"https://ror.org/0069akp70","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210093649"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Christos Koutlis","raw_affiliation_strings":["Information Technologies Institute @ CERTH,Thessaloniki,Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technologies Institute @ CERTH,Thessaloniki,Greece","institution_ids":["https://openalex.org/I4210093649"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135295487","display_name":"Symeon Papadopoulos","orcid":null},"institutions":[{"id":"https://openalex.org/I4210093649","display_name":"Information Technologies Institute","ror":"https://ror.org/0069akp70","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210093649"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Symeon Papadopoulos","raw_affiliation_strings":["Information Technologies Institute @ CERTH,Thessaloniki,Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technologies Institute @ CERTH,Thessaloniki,Greece","institution_ids":["https://openalex.org/I4210093649"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210093649"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7168","last_page":"7177"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.8586000204086304,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.8586000204086304,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.03500000014901161,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.022600000724196434,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/representation","display_name":"Representation (politics)","score":0.492900013923645},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3276999890804291},{"id":"https://openalex.org/keywords/noisy-data","display_name":"Noisy data","score":0.28780001401901245},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.27549999952316284},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.2732999920845032}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6147000193595886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5468000173568726},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.492900013923645},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3276999890804291},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3041999936103821},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28519999980926514},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.28380000591278076},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2732999920845032},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00692","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00692","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W2891145043","https://openalex.org/W2963351448","https://openalex.org/W2964121718","https://openalex.org/W2982058372","https://openalex.org/W2990763144","https://openalex.org/W3034196597","https://openalex.org/W3034713808","https://openalex.org/W3093077034","https://openalex.org/W3094728142","https://openalex.org/W3173161217","https://openalex.org/W3175342695","https://openalex.org/W3179508259","https://openalex.org/W4242246215","https://openalex.org/W4307286264","https://openalex.org/W4312388562","https://openalex.org/W4312472072","https://openalex.org/W4312508181","https://openalex.org/W4312753047","https://openalex.org/W4319978495","https://openalex.org/W4386057769","https://openalex.org/W4386102876","https://openalex.org/W4386272941","https://openalex.org/W4387968020","https://openalex.org/W4389519587","https://openalex.org/W4389897623","https://openalex.org/W4390872880","https://openalex.org/W4390873305","https://openalex.org/W4390874333","https://openalex.org/W4402772264","https://openalex.org/W4403757505","https://openalex.org/W4403791323","https://openalex.org/W4413144443","https://openalex.org/W4413147607","https://openalex.org/W4413157058"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,15,55,86,89],"rapid":[2],"advancement":[3],"of":[4,17,32,88],"sophisticated":[5],"synthetic":[6],"audio-visual":[7],"content,":[8],"e.g.,":[9],"for":[10,79],"subtle":[11],"malicious":[12],"manipulations,":[13],"ensuring":[14],"integrity":[16],"digital":[18],"media":[19],"has":[20],"become":[21],"paramount.":[22],"This":[23],"work":[24],"presents":[25],"a":[26],"novel":[27],"approach":[28,43],"to":[29,71],"temporal":[30,81],"localization":[31],"deepfakes":[33],"by":[34,91],"leveraging":[35],"Audio-Visual":[36],"Speech":[37],"Representation":[38],"Reconstruction":[39],"(AuViRe).":[40],"Specifically,":[41],"our":[42],"reconstructs":[44],"speech":[45],"representations":[46],"from":[47],"one":[48],"modality":[49],"(e.g.,":[50,57],"lip":[51],"movements)":[52],"based":[53],"on":[54,94,98,103],"other":[56],"audio":[58],"waveform).":[59],"Cross-modal":[60],"reconstruction":[61],"is":[62],"significantly":[63],"more":[64],"challenging":[65],"in":[66],"manipulated":[67],"video":[68],"segments,":[69],"leading":[70],"amplified":[72],"discrepancies,":[73],"thereby":[74],"providing":[75],"robust":[76],"discriminative":[77],"cues":[78],"precise":[80],"forgery":[82],"localization.":[83],"AuViRe":[84],"outperforms":[85],"state":[87],"art":[90],"+8.9":[92],"AP@0.95":[93],"LAV-DF,":[95],"+9.6":[96],"AP@0.5":[97],"AV-Deepfake1M,":[99],"and":[100],"+5.1":[101],"AUC":[102],"an":[104],"in-the-wild":[105],"experiment.":[106],"Code":[107],"at":[108],"https://github.com/mever-team/auvire.":[109]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-05-06T00:00:00"}