{"id":"https://openalex.org/W4414818221","doi":"https://doi.org/10.1109/wacv61042.2026.00232","title":"Discrete Facial Encoding: A Framework for Data-driven Facial Display Discovery","display_name":"Discrete Facial Encoding: A Framework for Data-driven Facial Display Discovery","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4414818221","doi":"https://doi.org/10.1109/wacv61042.2026.00232"},"language":"en","primary_location":{"id":"doi:10.1109/wacv61042.2026.00232","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00232","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":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.01662","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101612317","display_name":"Minh Tr\u1ea7n","orcid":"https://orcid.org/0000-0003-4637-6081"},"institutions":[{"id":"https://openalex.org/I4210087747","display_name":"Creative Technologies (United States)","ror":"https://ror.org/001qkb777","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087747"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Minh Tran","raw_affiliation_strings":["University of Southern California,Institute for Creative Technologies,Los Angeles,CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Institute for Creative Technologies,Los Angeles,CA","institution_ids":["https://openalex.org/I4210087747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027304898","display_name":"Maksim Siniukov","orcid":"https://orcid.org/0000-0001-8529-2281"},"institutions":[{"id":"https://openalex.org/I4210087747","display_name":"Creative Technologies (United States)","ror":"https://ror.org/001qkb777","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087747"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maksim Siniukov","raw_affiliation_strings":["University of Southern California,Institute for Creative Technologies,Los Angeles,CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Institute for Creative Technologies,Los Angeles,CA","institution_ids":["https://openalex.org/I4210087747"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhangyu Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087747","display_name":"Creative Technologies (United States)","ror":"https://ror.org/001qkb777","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087747"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhangyu Jin","raw_affiliation_strings":["University of Southern California,Institute for Creative Technologies,Los Angeles,CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Institute for Creative Technologies,Los Angeles,CA","institution_ids":["https://openalex.org/I4210087747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024169758","display_name":"Mohammad Soleymani","orcid":"https://orcid.org/0000-0002-5873-1434"},"institutions":[{"id":"https://openalex.org/I4210087747","display_name":"Creative Technologies (United States)","ror":"https://ror.org/001qkb777","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087747"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Soleymani","raw_affiliation_strings":["University of Southern California,Institute for Creative Technologies,Los Angeles,CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Institute for Creative Technologies,Los Angeles,CA","institution_ids":["https://openalex.org/I4210087747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101612317"],"corresponding_institution_ids":["https://openalex.org/I4210087747"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00495036,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2348","last_page":"2358"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9804999828338623,"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":0.9804999828338623,"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/facial-action-coding-system","display_name":"Facial Action Coding System","score":0.7348999977111816},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.7206000089645386},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5674999952316284},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5425999760627747},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.5400999784469604},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5199000239372253},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4957999885082245},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.478300005197525},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4339999854564667}],"concepts":[{"id":"https://openalex.org/C40346341","wikidata":"https://www.wikidata.org/wiki/Q1391629","display_name":"Facial Action Coding System","level":3,"score":0.7348999977111816},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.7206000089645386},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6919000148773193},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.657800018787384},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5674999952316284},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5425999760627747},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.5400999784469604},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5199000239372253},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4957999885082245},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.478300005197525},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4339999854564667},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41670000553131104},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4052000045776367},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.335999995470047},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.325300008058548},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.32199999690055847},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.27900001406669617},{"id":"https://openalex.org/C2780905192","wikidata":"https://www.wikidata.org/wiki/Q2341604","display_name":"Facial muscles","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2639999985694885}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00232","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00232","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"},{"id":"pmh:oai:arXiv.org:2510.01662","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.01662","pdf_url":"https://arxiv.org/pdf/2510.01662","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.01662","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.01662","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.01662","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.01662","pdf_url":"https://arxiv.org/pdf/2510.01662","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320316514","display_name":"Arm","ror":"https://ror.org/04mmhzs81"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414818221.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Facial":[0,16,36,130],"expression":[1,69],"analysis":[2,195],"is":[3],"central":[4],"to":[5,119,216],"understanding":[6],"human":[7],"behavior,":[8],"yet":[9],"existing":[10],"coding":[11],"systems":[12],"such":[13,82,190],"as":[14,83,191,210],"the":[15,120,146,172,226],"Action":[17],"Coding":[18],"System":[19],"(FACS)":[20],"are":[21],"constrained":[22],"by":[23],"limited":[24],"coverage":[25],"and":[26,45,86,139,160,182,185,213,220,229],"costly":[27],"manual":[28],"annotation.":[29],"In":[30],"this":[31],"work,":[32],"we":[33,126],"introduce":[34],"Discrete":[35,129],"Encoding":[37,131],"(DFE),":[38],"an":[39,95],"unsupervised,":[40],"data-driven":[41],"alternative":[42,215],"of":[43,48,100,148,171,204],"compact":[44],"interpretable":[46],"dictionary":[47],"facial":[49,87,114,135,141,205],"expressions":[50],"from":[51,71,103],"3D":[52,75],"mesh":[53],"sequences":[54],"learned":[55,173],"through":[56],"a":[57,74,98,104,111,164,201,211],"Residual":[58],"Vector":[59],"Quantized":[60],"Variational":[61],"Autoencoder":[62],"(RVQ-VAE).":[63],"Our":[64],"approach":[65],"first":[66],"extracts":[67],"identity-invariant":[68],"features":[70,93],"images":[72],"using":[73,94],"Morphable":[76],"Model":[77],"(3DMM),":[78],"effectively":[79],"disentangling":[80],"factors":[81],"head":[84],"pose":[85],"geometry.":[88],"We":[89,144,224],"then":[90],"encode":[91],"these":[92],"RVQ-VAE,":[96],"producing":[97],"sequence":[99],"discrete":[101],"tokens":[102],"shared":[105],"codebook,":[106],"where":[107],"each":[108],"token":[109],"captures":[110,132],"specific,":[112],"reusable":[113],"deformation":[115],"pattern":[116],"that":[117,128,197],"contributes":[118],"overall":[121],"expression.":[122],"Through":[123],"extensive":[124],"experiments,":[125],"demonstrate":[127],"more":[133],"precise":[134],"behaviors":[136],"than":[137],"FACS":[138,217],"other":[140],"encoding":[142],"alternatives.":[143],"evaluate":[145],"utility":[147],"our":[149,175,198],"representation":[150,187,199],"across":[151],"three":[152],"high-level":[153],"psychological":[154,219],"tasks:":[155],"stress":[156],"detection,":[157],"personality":[158],"prediction,":[159],"depression":[161],"detection.":[162],"Using":[163],"simple":[165],"Bag-of-Words":[166],"model":[167,230],"built":[168],"on":[169],"top":[170],"tokens,":[174],"system":[176],"consistently":[177],"outperforms":[178],"both":[179],"FACS-based":[180],"pipelines":[181],"strong":[183],"image":[184],"video":[186],"learning":[188],"models":[189],"Masked":[192],"Autoencoders.":[193],"Further":[194],"reveals":[196],"covers":[200],"wider":[202],"variety":[203],"displays,":[206],"highlighting":[207],"its":[208],"potential":[209],"scalable":[212],"effective":[214],"for":[218],"affective":[221],"computing":[222],"applications.":[223],"released":[225],"source":[227],"code":[228],"weights":[231],"at":[232],"https://github.com/ihp-lab/vqface.":[233]},"counts_by_year":[],"updated_date":"2026-05-07T06:04:25.777469","created_date":"2025-10-10T00:00:00"}