{"id":"https://openalex.org/W4417432537","doi":"https://doi.org/10.1109/iccv51701.2025.01347","title":"Seeing Through Deepfakes: A Human-Inspired Framework for Multi-Face Detection","display_name":"Seeing Through Deepfakes: A Human-Inspired Framework for Multi-Face Detection","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417432537","doi":"https://doi.org/10.1109/iccv51701.2025.01347"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01347","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01347","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.14807","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102015291","display_name":"Juan Hu","orcid":"https://orcid.org/0000-0002-8856-2707"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Juan Hu","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100777508","display_name":"Shaojing Fan","orcid":"https://orcid.org/0000-0002-7744-1133"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shaojing Fan","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065478753","display_name":"Terence Sim","orcid":"https://orcid.org/0000-0002-0198-094X"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Terence Sim","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165932596"],"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":"14517","last_page":"14527"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.5740000009536743,"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":0.5740000009536743,"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":0.33180001378059387,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.02070000022649765,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.8646000027656555},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6421999931335449},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.515500009059906},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.45329999923706055},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.45159998536109924},{"id":"https://openalex.org/keywords/interpersonal-communication","display_name":"Interpersonal communication","score":0.37540000677108765}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8646000027656555},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7436000108718872},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6421999931335449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5587000250816345},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.515500009059906},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.45329999923706055},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.45159998536109924},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42329999804496765},{"id":"https://openalex.org/C164850336","wikidata":"https://www.wikidata.org/wiki/Q3685487","display_name":"Interpersonal communication","level":2,"score":0.37540000677108765},{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.36090001463890076},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.3553999960422516},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.34929999709129333},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.310699999332428},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2687999904155731},{"id":"https://openalex.org/C2988148770","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion detection","level":3,"score":0.2554999887943268}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iccv51701.2025.01347","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01347","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.14807","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.14807","pdf_url":"https://arxiv.org/pdf/2507.14807","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.14807","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.14807","pdf_url":"https://arxiv.org/pdf/2507.14807","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1795493338","display_name":null,"funder_award_id":"MOE-MOET32022-0001","funder_id":"https://openalex.org/F4320320751","funder_display_name":"Ministry of Education - Singapore"}],"funders":[{"id":"https://openalex.org/F4320320751","display_name":"Ministry of Education - Singapore","ror":"https://ror.org/01kcva023"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multi-face":[0],"deepfake":[1,58,72],"videos":[2],"are":[3],"becoming":[4],"increasingly":[5],"prevalent,":[6],"often":[7],"appearing":[8],"in":[9,27,74,114,130],"natural":[10],"social":[11,75],"settings":[12],"that":[13,48,123],"challenge":[14],"existing":[15,141],"detection":[16,24,132,167],"methods.":[17],"Most":[18],"current":[19],"approaches":[20],"excel":[21],"at":[22],"single-face":[23],"but":[25],"struggle":[26],"multi-face":[28,57,115],"scenarios,":[29],"due":[30],"to":[31,52,109,162,181],"a":[32,45,61,105],"lack":[33],"of":[34,36,63,151],"awareness":[35],"crucial":[37],"contextual":[38],"cues.":[39,153],"In":[40],"this":[41],"work,":[42],"we":[43,66,102],"develop":[44],"novel":[46,106],"approach":[47],"leverages":[49],"human":[50,64,179],"cognition":[51],"analyze":[53],"and":[54,95,133,171],"defend":[55],"against":[56,184],"videos.":[59],"Through":[60],"series":[62],"studies,":[65],"systematically":[67],"examine":[68],"how":[69],"people":[70],"detect":[71,110],"faces":[73],"settings.":[76],"Our":[77,173],"quantitative":[78],"analysis":[79],"reveals":[80],"four":[81],"key":[82],"cues":[83],"humans":[84],"rely":[85],"on:":[86],"scene-motion":[87],"coherence,":[88],"inter-face":[89],"appearance":[90],"compatibility,":[91],"interpersonal":[92],"gaze":[93],"alignment,":[94],"face-body":[96],"consistency.":[97],"Guided":[98],"by":[99,128,143,158],"these":[100],"insights,":[101],"introduce":[103],"\\textsf{HICOM},":[104],"framework":[107],"designed":[108],"every":[111],"fake":[112],"face":[113],"scenarios.":[116],"Extensive":[117],"experiments":[118],"on":[119,145,177],"benchmark":[120],"datasets":[121],"show":[122],"\\textsf{HICOM}":[124,154],"improves":[125],"average":[126],"accuracy":[127],"3.3\\%":[129],"in-dataset":[131],"2.8\\%":[134],"under":[135],"real-world":[136],"perturbations.":[137],"Moreover,":[138],"it":[139],"outperforms":[140],"methods":[142],"5.8\\%":[144],"unseen":[146],"datasets,":[147],"demonstrating":[148],"the":[149],"generalization":[150],"human-inspired":[152],"further":[155],"enhances":[156],"interpretability":[157],"incorporating":[159],"an":[160],"LLM":[161],"provide":[163],"human-readable":[164],"explanations,":[165],"making":[166],"results":[168],"more":[169],"transparent":[170],"convincing.":[172],"work":[174],"sheds":[175],"light":[176],"involving":[178],"factors":[180],"enhance":[182],"defense":[183],"deepfakes.":[185]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}