{"id":"https://openalex.org/W4415141449","doi":"https://doi.org/10.1145/3746027.3754939","title":"InstructFLIP: Exploring Unified Vision-Language Model for Face Anti-spoofing","display_name":"InstructFLIP: Exploring Unified Vision-Language Model for Face Anti-spoofing","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415141449","doi":"https://doi.org/10.1145/3746027.3754939"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3754939","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754939","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.12060","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112560382","display_name":"Kun\u2010Hsiang Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Kun-Hsiang Lin","raw_affiliation_strings":["National Taiwan University, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0009-0009-8040-979X","affiliations":[{"raw_affiliation_string":"National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yu-Wen Tseng","orcid":"https://orcid.org/0009-0001-8332-8444"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Wen Tseng","raw_affiliation_strings":["National Taiwan University, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0009-0001-8332-8444","affiliations":[{"raw_affiliation_string":"National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032931636","display_name":"Kang-Yang Huang","orcid":"https://orcid.org/0000-0003-1268-5214"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kang-Yang Huang","raw_affiliation_strings":["National Taiwan University, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0000-0003-1268-5214","affiliations":[{"raw_affiliation_string":"National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071442349","display_name":"Jhih-Ciang Wu","orcid":"https://orcid.org/0000-0003-4071-3980"},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jhih-Ciang Wu","raw_affiliation_strings":["National Taiwan Normal University, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0000-0003-4071-3980","affiliations":[{"raw_affiliation_string":"National Taiwan Normal University, Taipei, Taiwan","institution_ids":["https://openalex.org/I134161618"]}]},{"author_position":"last","author":{"id":null,"display_name":"Wen-Huang Cheng","orcid":"https://orcid.org/0000-0002-4662-7875"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wen-Huang Cheng","raw_affiliation_strings":["National Taiwan University, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-4662-7875","affiliations":[{"raw_affiliation_string":"National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5112560382"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":1.2753,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83776174,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2987","last_page":"2996"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10828","display_name":"Biometric Identification and Security","score":0.9994999766349792,"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/T10828","display_name":"Biometric Identification and Security","score":0.9994999766349792,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9937000274658203,"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/T11800","display_name":"User Authentication and Security Systems","score":0.9925000071525574,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/redundancy","display_name":"Redundancy (engineering)","score":0.6495000123977661},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5497999787330627},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5430999994277954},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4959999918937683},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.47380000352859497},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.46810001134872437}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7699999809265137},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6495000123977661},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5521000027656555},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5497999787330627},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5430999994277954},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4959999918937683},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.47380000352859497},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.46810001134872437},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39640000462532043},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.39259999990463257},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36890000104904175},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.33559998869895935},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2856000065803528},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.265500009059906}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3754939","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754939","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.12060","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.12060","pdf_url":"https://arxiv.org/pdf/2507.12060","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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:2507.12060","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.12060","pdf_url":"https://arxiv.org/pdf/2507.12060","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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/G4097663906","display_name":null,"funder_award_id":"114L900901,114L900902,114L900903","funder_id":"https://openalex.org/F4320323900","funder_display_name":"National Taiwan University"}],"funders":[{"id":"https://openalex.org/F4320323900","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Face":[0],"anti-spoofing":[1],"(FAS)":[2],"aims":[3],"to":[4,47,63,85,125],"construct":[5],"a":[6,60,65,78,94],"robust":[7],"system":[8],"that":[9,68,82],"can":[10],"withstand":[11],"diverse":[12,150],"attacks.":[13],"While":[14],"recent":[15],"efforts":[16],"have":[17],"concentrated":[18],"mainly":[19],"on":[20,93,113],"cross-domain":[21],"generalization,":[22],"two":[23],"significant":[24],"challenges":[25],"persist:":[26],"limited":[27],"semantic":[28],"understanding":[29],"of":[30,51,117,136],"attack":[31],"types":[32],"and":[33,106,119,128,144],"training":[34,147],"redundancy":[35,148],"across":[36,71,149],"domains.":[37,73],"We":[38],"address":[39],"the":[40,49,55,114,126,134],"first":[41],"by":[42,138],"integrating":[43],"vision-language":[44],"models":[45,141],"(VLMs)":[46],"enhance":[48,86],"perception":[50],"visual":[52],"input.":[53],"For":[54],"second":[56],"challenge,":[57],"we":[58],"employ":[59],"meta-domain":[61],"strategy":[62],"learn":[64],"unified":[66],"model":[67],"generalizes":[69],"well":[70],"multiple":[72],"Our":[74],"proposed":[75],"InstructFLIP":[76,100,137],"is":[77,157],"novel":[79],"instruction-tuned":[80],"framework":[81],"leverages":[83],"VLMs":[84],"generalization":[87],"via":[88],"textual":[89],"guidance":[90],"trained":[91],"solely":[92],"single":[95],"domain.":[96],"At":[97],"its":[98],"core,":[99],"explicitly":[101],"decouples":[102],"instructions":[103,111,121],"into":[104],"content":[105],"style":[107],"components,":[108],"where":[109],"content-based":[110],"focus":[112],"essential":[115],"semantics":[116],"spoofing,":[118],"style-based":[120],"consider":[122],"variations":[123],"related":[124],"environment":[127],"camera":[129],"characteristics.":[130],"Extensive":[131],"experiments":[132],"demonstrate":[133],"effectiveness":[135],"outperforming":[139],"SOTA":[140],"in":[142,152],"accuracy":[143],"substantially":[145],"reducing":[146],"domains":[151],"FAS.":[153],"The":[154],"project":[155],"website":[156],"available":[158],"at":[159],"https://kunkunlin1221.github.io/InstructFLIP.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-14T00:00:00"}