{"id":"https://openalex.org/W7160290918","doi":"https://doi.org/10.1109/wacv61042.2026.00735","title":"SVD-Det: A Lightweight Framework for Video Forgery Detection Using Semantic and Visual Defect Cues","display_name":"SVD-Det: A Lightweight Framework for Video Forgery Detection Using Semantic and Visual Defect Cues","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160290918","doi":"https://doi.org/10.1109/wacv61042.2026.00735"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00735","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00735","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":"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/A5048462101","display_name":"Tsung-Shan Yang","orcid":"https://orcid.org/0000-0003-2157-5498"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tsung-Shan Yang","raw_affiliation_strings":["University of Southern California,Los Angeles,CA,90089"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Los Angeles,CA,90089","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135416569","display_name":"Tianyu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I173632517","display_name":"MediaTek (China)","ror":"https://ror.org/05xvgy636","country_code":"CN","type":"company","lineage":["https://openalex.org/I173632517","https://openalex.org/I4210148979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyu Zhang","raw_affiliation_strings":["ByteDance Ltd.,San Jose,CA,95110"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Ltd.,San Jose,CA,95110","institution_ids":["https://openalex.org/I173632517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135411193","display_name":"Feng Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I173632517","display_name":"MediaTek (China)","ror":"https://ror.org/05xvgy636","country_code":"CN","type":"company","lineage":["https://openalex.org/I173632517","https://openalex.org/I4210148979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Qian","raw_affiliation_strings":["ByteDance Ltd.,San Jose,CA,95110"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Ltd.,San Jose,CA,95110","institution_ids":["https://openalex.org/I173632517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135350129","display_name":"Bing Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I173632517","display_name":"MediaTek (China)","ror":"https://ror.org/05xvgy636","country_code":"CN","type":"company","lineage":["https://openalex.org/I173632517","https://openalex.org/I4210148979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Yan","raw_affiliation_strings":["ByteDance Ltd.,San Jose,CA,95110"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Ltd.,San Jose,CA,95110","institution_ids":["https://openalex.org/I173632517"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135307801","display_name":"C.-C. Jay Kuo","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C.-C. Jay Kuo","raw_affiliation_strings":["University of Southern California,Los Angeles,CA,90089"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Los Angeles,CA,90089","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5048462101"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.92900066,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7616","last_page":"7625"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.5192000269889832,"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":0.5192000269889832,"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":0.23430000245571136,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.04699999839067459,"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/visualization","display_name":"Visualization","score":0.3443000018596649},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3230000138282776},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.30070000886917114},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.2964000105857849},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.2606000006198883}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6492000222206116},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5737000107765198},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5605999827384949},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3443000018596649},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3230000138282776},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.30070000886917114},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2515999972820282},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.24490000307559967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00735","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00735","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":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2963351448","https://openalex.org/W3034577585","https://openalex.org/W3094728142","https://openalex.org/W3174508664","https://openalex.org/W3175342695","https://openalex.org/W3196204467","https://openalex.org/W3196551054","https://openalex.org/W4214612132","https://openalex.org/W4308237189","https://openalex.org/W4312299780","https://openalex.org/W4312560592","https://openalex.org/W4312933868","https://openalex.org/W4375869427","https://openalex.org/W4385245566","https://openalex.org/W4386071953","https://openalex.org/W4386075856","https://openalex.org/W4386075957","https://openalex.org/W4386215278","https://openalex.org/W4388858946","https://openalex.org/W4390873235","https://openalex.org/W4390874333","https://openalex.org/W4394625735","https://openalex.org/W4402716164","https://openalex.org/W4402727598","https://openalex.org/W4402915976","https://openalex.org/W4402915983","https://openalex.org/W4404124961","https://openalex.org/W7133218093"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,145],"rapid":[2],"proliferation":[3],"of":[4,149],"AI-generated":[5],"content":[6],"(AIGC)":[7],"on":[8,25],"multimedia":[9],"platforms,":[10],"efficient":[11,52],"and":[12,51,58,74,81,106,129,135,147],"reliable":[13],"video":[14,112],"forgery":[15],"detection":[16,122,154],"has":[17],"become":[18],"increasingly":[19],"important.":[20],"Existing":[21],"approaches":[22],"often":[23],"rely":[24],"either":[26],"visual":[27],"artifacts":[28],"or":[29],"semantic":[30,83],"inconsistencies,":[31],"but":[32,124],"suffer":[33],"from":[34,70],"high":[35],"computational":[36],"costs,":[37],"limiting":[38],"their":[39],"deployment":[40],"at":[41],"scale.":[42],"In":[43],"this":[44],"work,":[45],"we":[46,93],"propose":[47],"SVD-Det,":[48],"a":[49,78,98],"lightweight":[50],"pipeline":[53],"that":[54,102,116],"leverages":[55],"both":[56],"Semantic":[57],"Visual":[59],"Defect":[60],"cues":[61],"to":[62,139],"detect":[63],"forged":[64],"videos.":[65],"SVD-Det":[66,117,150],"fuses":[67],"spatiotemporal":[68],"representations":[69],"raw":[71],"RGB":[72],"frames":[73],"compression-induced":[75],"distortions":[76],"using":[77],"3D-Swin":[79],"Transformer,":[80],"augments":[82],"understanding":[84],"via":[85],"CLIP-based":[86],"embeddings.":[87],"To":[88],"integrate":[89],"these":[90],"heterogeneous":[91],"modalities,":[92],"introduce":[94],"Domain-Query":[95],"Attention":[96],"(DoQA),":[97],"novel":[99],"attention":[100],"mechanism":[101],"hierarchically":[103],"aggregates":[104],"spatial":[105],"temporal":[107],"features.":[108],"Experiments":[109],"across":[110],"seven":[111],"generation":[113],"domains":[114],"demonstrate":[115],"not":[118],"only":[119],"achieves":[120],"state-of-the-art":[121],"performance":[123],"also":[125],"reduces":[126],"model":[127],"size":[128],"inference":[130],"time":[131],"by":[132],"over":[133],"97%":[134],"98%,":[136],"respectively,":[137],"compared":[138],"LMM-based":[140],"baselines.":[141],"Our":[142],"results":[143],"highlight":[144],"practicality":[146],"robustness":[148],"for":[151],"scalable":[152],"AIGC":[153],"in":[155],"real-world":[156],"scenarios.":[157]},"counts_by_year":[],"updated_date":"2026-05-07T06:04:25.777469","created_date":"2026-05-06T00:00:00"}