{"id":"https://openalex.org/W7160329074","doi":"https://doi.org/10.1007/s12559-026-10582-x","title":"Enhancing Facial Beauty Prediction with a Cross-Attention Vision Transformer and Attention-Guided Augmentation","display_name":"Enhancing Facial Beauty Prediction with a Cross-Attention Vision Transformer and Attention-Guided Augmentation","publication_year":2026,"publication_date":"2026-05-02","ids":{"openalex":"https://openalex.org/W7160329074","doi":"https://doi.org/10.1007/s12559-026-10582-x"},"language":"en","primary_location":{"id":"doi:10.1007/s12559-026-10582-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s12559-026-10582-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s12559-026-10582-x.pdf","source":{"id":"https://openalex.org/S133078663","display_name":"Cognitive Computation","issn_l":"1866-9956","issn":["1866-9956","1866-9964"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cognitive Computation","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s12559-026-10582-x.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135380848","display_name":"D. E. Boukhari","orcid":null},"institutions":[{"id":"https://openalex.org/I4210140819","display_name":"CRSTRA","ror":"https://ror.org/056ahff07","country_code":"DZ","type":"facility","lineage":["https://openalex.org/I4210140819"]},{"id":"https://openalex.org/I4210154551","display_name":"Centre Hospitalo-Universitaire Bab El Oued","ror":"https://ror.org/05qf3bt68","country_code":"DZ","type":"healthcare","lineage":["https://openalex.org/I4210154551"]},{"id":"https://openalex.org/I4210157185","display_name":"University of Eloued","ror":"https://ror.org/05416s909","country_code":"DZ","type":"education","lineage":["https://openalex.org/I4210157185"]}],"countries":["DZ"],"is_corresponding":false,"raw_author_name":"D. E. Boukhari","raw_affiliation_strings":["LGEERE Laboratory Department of Electrical Engineering, El-Oued Algeria, University of El Oued, El-Oued, 39000, El-Oued, Algeria","Scientific and Technical Research Centre for Arid Areas, CRSTRA, Biskra, 07000, Biskra, Algeria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LGEERE Laboratory Department of Electrical Engineering, El-Oued Algeria, University of El Oued, El-Oued, 39000, El-Oued, Algeria","institution_ids":["https://openalex.org/I4210154551","https://openalex.org/I4210157185"]},{"raw_affiliation_string":"Scientific and Technical Research Centre for Arid Areas, CRSTRA, Biskra, 07000, Biskra, Algeria","institution_ids":["https://openalex.org/I4210140819"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135369033","display_name":"F. Dornaika","orcid":null},"institutions":[{"id":"https://openalex.org/I110594554","display_name":"Ikerbasque","ror":"https://ror.org/01cc3fy72","country_code":"ES","type":"other","lineage":["https://openalex.org/I110594554"]},{"id":"https://openalex.org/I169108374","display_name":"University of the Basque Country","ror":"https://ror.org/000xsnr85","country_code":"ES","type":"education","lineage":["https://openalex.org/I169108374"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"F. Dornaika","raw_affiliation_strings":["IKERBASQUE, Basque Foundation for Science, San Sebastian, Spain","University of the Basque Country, San Sebastian, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IKERBASQUE, Basque Foundation for Science, San Sebastian, Spain","institution_ids":["https://openalex.org/I110594554"]},{"raw_affiliation_string":"University of the Basque Country, San Sebastian, Spain","institution_ids":["https://openalex.org/I169108374"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5135369033"],"corresponding_institution_ids":["https://openalex.org/I110594554","https://openalex.org/I169108374"],"apc_list":{"value":2790,"currency":"USD","value_usd":2790},"apc_paid":{"value":2790,"currency":"USD","value_usd":2790},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.56051176,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"18","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.35839998722076416,"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":0.35839998722076416,"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/T11118","display_name":"Evolutionary Psychology and Human Behavior","score":0.17910000681877136,"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"}},{"id":"https://openalex.org/T11322","display_name":"Facial Rejuvenation and Surgery Techniques","score":0.08410000056028366,"subfield":{"id":"https://openalex.org/subfields/2708","display_name":"Dermatology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.6305000185966492},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.590499997138977},{"id":"https://openalex.org/keywords/beauty","display_name":"Beauty","score":0.5351999998092651},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.48910000920295715},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.477400004863739},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.41179999709129333},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.4016999900341034},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.39149999618530273}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7347999811172485},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6477000117301941},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.6305000185966492},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.590499997138977},{"id":"https://openalex.org/C2780620123","wikidata":"https://www.wikidata.org/wiki/Q7242","display_name":"Beauty","level":2,"score":0.5351999998092651},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.48910000920295715},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.477400004863739},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.41179999709129333},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.4016999900341034},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.39149999618530273},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.35580000281333923},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35280001163482666},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.34950000047683716},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.33799999952316284},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3370000123977661},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3091999888420105},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29750001430511475},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.28519999980926514},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2849000096321106},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s12559-026-10582-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s12559-026-10582-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s12559-026-10582-x.pdf","source":{"id":"https://openalex.org/S133078663","display_name":"Cognitive Computation","issn_l":"1866-9956","issn":["1866-9956","1866-9964"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cognitive Computation","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s12559-026-10582-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s12559-026-10582-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s12559-026-10582-x.pdf","source":{"id":"https://openalex.org/S133078663","display_name":"Cognitive Computation","issn_l":"1866-9956","issn":["1866-9956","1866-9964"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cognitive Computation","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7721491456031799,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321919","display_name":"Euskal Herriko Unibertsitatea","ror":"https://ror.org/000xsnr85"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7160329074.pdf","grobid_xml":"https://content.openalex.org/works/W7160329074.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1994835217","https://openalex.org/W2112987325","https://openalex.org/W2170804235","https://openalex.org/W2194775991","https://openalex.org/W2231999017","https://openalex.org/W2503043390","https://openalex.org/W2549139847","https://openalex.org/W2620075774","https://openalex.org/W2938982646","https://openalex.org/W2962769166","https://openalex.org/W2964118336","https://openalex.org/W2965131684","https://openalex.org/W2992308087","https://openalex.org/W3048043446","https://openalex.org/W4206706211","https://openalex.org/W4210566286","https://openalex.org/W4213018848","https://openalex.org/W4312747676","https://openalex.org/W4324381405","https://openalex.org/W4327846218","https://openalex.org/W4353100291","https://openalex.org/W4388812647","https://openalex.org/W4389519489","https://openalex.org/W4391378989","https://openalex.org/W4391867272","https://openalex.org/W4404792820","https://openalex.org/W4407125963","https://openalex.org/W4407901675","https://openalex.org/W4408180925","https://openalex.org/W4409917222","https://openalex.org/W4410229616","https://openalex.org/W4413755662","https://openalex.org/W4415297524"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Facial":[1],"Beauty":[2],"Prediction":[3],"(FBP)":[4],"is":[5,30,365],"a":[6,33,98,123,129,196,232,249,280,347,371],"long-standing":[7],"and":[8,20,42,108,149,172,189,266,302,328,356,384,389,402],"inherently":[9],"challenging":[10,209,403],"task":[11],"in":[12,333],"computer":[13],"vision,":[14],"primarily":[15],"due":[16],"to":[17,51,78,135,161,186,227,247,378],"the":[18,62,80,133,139,146,159,169,182,203,206,220,225,237,240,260,273,296,307,317,322,354,376,381],"subjective":[19],"multifaceted":[21],"nature":[22],"of":[23,35,219,286,298,309,358],"human":[24],"aesthetic":[25,89,183,234,334],"judgment.":[26],"Perceived":[27],"facial":[28,37,85,110,143,174,359,387],"beauty":[29,111,221,360],"influenced":[31],"by":[32,212,367,398],"combination":[34],"global":[36],"harmony,":[38],"local":[39,73],"feature":[40],"attractiveness,":[41],"cultural":[43],"or":[44,53],"individual":[45],"biases\u2014factors":[46],"that":[47,71,87,126,259,351],"are":[48,245],"often":[49],"difficult":[50],"quantify":[52],"model":[54,115,160,226,377],"explicitly.":[55],"While":[56],"deep":[57],"learning":[58],"has":[59],"significantly":[60],"advanced":[61],"field,":[63],"existing":[64,289],"approaches":[65],"frequently":[66],"rely":[67],"on":[68,138,164,272],"convolutional":[69],"backbones":[70],"emphasize":[72],"texture":[74],"details":[75],"but":[76],"fail":[77],"capture":[79],"subtle,":[81],"holistic":[82],"relationships":[83],"among":[84],"components":[86],"define":[88],"perception.":[90],"To":[91],"address":[92],"these":[93],"limitations,":[94],"we":[95,121,192],"introduce":[96],"TransFBP,":[97,346],"novel":[99,348],"Vision":[100],"Transformer":[101],"(ViT)-based":[102],"framework":[103,350],"specifically":[104],"designed":[105],"for":[106,254,324],"interpretable":[107,177],"human-aligned":[109],"assessment.":[112],"The":[113,291,337,362],"proposed":[114,363],"incorporates":[116],"two":[117,368],"major":[118],"innovations.":[119],"First,":[120],"develop":[122],"Cross-Attention":[124,372],"Head":[125],"acts":[127],"as":[128,145,168],"dynamic":[130],"filter,":[131],"enabling":[132],"network":[134],"automatically":[136],"focus":[137,162],"most":[140,382],"visually":[141],"meaningful":[142,166,265],"areas\u2014such":[144,167],"eyes,":[147,170],"lips,":[148,171],"overall":[150,173],"symmetry\u2014while":[151],"suppressing":[152],"irrelevant":[153],"background":[154],"information.":[155],"This":[156],"design":[157],"enables":[158,375],"adaptively":[163],"semantically":[165,250,400],"symmetry\u2014thereby":[175],"offering":[176],"insights":[178],"into":[179,316],"what":[180],"drives":[181],"predictions.":[184],"Second,":[185],"mitigate":[187],"overfitting":[188],"enhance":[190],"generalization,":[191],"propose":[193],"Attention-Guided":[194,391],"TransMix,":[195],"two-stage":[197],"semantic":[198],"data":[199],"augmentation":[200,304,393],"strategy.":[201,305],"In":[202,236],"first":[204],"stage,":[205,239],"method":[207,278],"generates":[208],"hybrid":[210],"samples":[211,262],"conditionally":[213],"mixing":[214],"images":[215],"from":[216],"opposite":[217],"ends":[218],"score":[222,253],"distribution,":[223],"encouraging":[224],"learn":[228],"discriminative":[229],"features":[230],"across":[231],"wide":[233],"spectrum.":[235],"second":[238],"model\u2019s":[241,318],"own":[242],"attention":[243,311],"maps":[244,312],"leveraged":[246],"generate":[248],"grounded":[251],"supervisory":[252],"each":[255],"mixed":[256],"image,":[257],"ensuring":[258],"augmented":[261],"remain":[263],"perceptually":[264],"score-consistent.":[267],"We":[268,344],"comprehensively":[269],"evaluate":[270],"TransFBP":[271],"FBP5500":[274],"dataset,":[275],"where":[276],"our":[277,299,310],"achieves":[279],"state-of-the-art":[281],"Pearson":[282],"Correlation":[283],"Coefficient":[284],"(PCC)":[285],"0.9291,":[287],"surpassing":[288],"approaches.":[290],"strong":[292],"empirical":[293],"results":[294],"validate":[295],"effectiveness":[297],"cross-attention":[300],"mechanism":[301],"attention-guided":[303],"Moreover,":[306],"interpretability":[308,357],"provides":[313],"valuable":[314],"transparency":[315],"decision":[319],"process,":[320],"paving":[321],"way":[323],"more":[325],"explainable,":[326],"reliable,":[327],"ethically":[329],"aligned":[330],"AI":[331],"systems":[332],"perception":[335],"tasks.":[336],"code":[338],"will":[339],"be":[340],"available":[341],"at":[342],"https://github.com/DjameleddineBoukhari/transFBP":[343],"introduced":[345],"Transformer-based":[349],"advances":[352],"both":[353],"performance":[355],"prediction.":[361],"approach":[364],"characterized":[366],"key":[369],"innovations:":[370],"Head,":[373],"which":[374,395],"dynamically":[379],"integrate":[380],"salient":[383],"contextually":[385],"relevant":[386],"features,":[388],"an":[390],"TransMix":[392],"strategy,":[394],"enhances":[396],"regularization":[397],"generating":[399],"consistent":[401],"training":[404],"samples.":[405]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2026-05-06T00:00:00"}