{"id":"https://openalex.org/W7160191849","doi":"https://doi.org/10.1093/jcde/qwag044","title":"Attention-guided transformer architecture for fine-grained style representation in design systems","display_name":"Attention-guided transformer architecture for fine-grained style representation in design systems","publication_year":2026,"publication_date":"2026-05-01","ids":{"openalex":"https://openalex.org/W7160191849","doi":"https://doi.org/10.1093/jcde/qwag044"},"language":"en","primary_location":{"id":"doi:10.1093/jcde/qwag044","is_oa":true,"landing_page_url":"https://doi.org/10.1093/jcde/qwag044","pdf_url":null,"source":{"id":"https://openalex.org/S2485147958","display_name":"Journal of Computational Design and Engineering","issn_l":"2288-4300","issn":["2288-4300","2288-5048"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Design and Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1093/jcde/qwag044","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126803026","display_name":"Bao T. Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152658","display_name":"Active Technologies (Italy)","ror":"https://ror.org/03zp7nb85","country_code":"IT","type":"company","lineage":["https://openalex.org/I4210152658"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Bao T Nguyen","raw_affiliation_strings":["Institute of Intelligent and Interactive Technologies, University of Economics Ho Chi Minh City ,"],"raw_orcid":"https://orcid.org/0000-0001-8341-7319","affiliations":[{"raw_affiliation_string":"Institute of Intelligent and Interactive Technologies, University of Economics Ho Chi Minh City ,","institution_ids":["https://openalex.org/I4210152658"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126839999","display_name":"Thinh T. Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152658","display_name":"Active Technologies (Italy)","ror":"https://ror.org/03zp7nb85","country_code":"IT","type":"company","lineage":["https://openalex.org/I4210152658"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Thinh T Nguyen","raw_affiliation_strings":["Institute of Intelligent and Interactive Technologies, University of Economics Ho Chi Minh City ,"],"raw_orcid":"https://orcid.org/0000-0003-0526-0736","affiliations":[{"raw_affiliation_string":"Institute of Intelligent and Interactive Technologies, University of Economics Ho Chi Minh City ,","institution_ids":["https://openalex.org/I4210152658"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5126803026"],"corresponding_institution_ids":["https://openalex.org/I4210152658"],"apc_list":{"value":1650,"currency":"USD","value_usd":1650},"apc_paid":{"value":1650,"currency":"USD","value_usd":1650},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.52624079,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":"5","first_page":"183","last_page":"202"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.10329999774694443,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.10329999774694443,"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/T12496","display_name":"Color perception and design","score":0.07989999651908875,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social 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/T12650","display_name":"Aesthetic Perception and Analysis","score":0.07519999891519547,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5936999917030334},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5242999792098999},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5103999972343445},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5063999891281128},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4180999994277954},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.33869999647140503},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3246999979019165}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7427999973297119},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5936999917030334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5644000172615051},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5242999792098999},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5103999972343445},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5063999891281128},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4180999994277954},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34779998660087585},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.33869999647140503},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3246999979019165},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.30250000953674316},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.29440000653266907},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2849999964237213},{"id":"https://openalex.org/C138852830","wikidata":"https://www.wikidata.org/wiki/Q2292993","display_name":"Design methods","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.2549999952316284}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1093/jcde/qwag044","is_oa":true,"landing_page_url":"https://doi.org/10.1093/jcde/qwag044","pdf_url":null,"source":{"id":"https://openalex.org/S2485147958","display_name":"Journal of Computational Design and Engineering","issn_l":"2288-4300","issn":["2288-4300","2288-5048"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Design and Engineering","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1093/jcde/qwag044","is_oa":true,"landing_page_url":"https://doi.org/10.1093/jcde/qwag044","pdf_url":null,"source":{"id":"https://openalex.org/S2485147958","display_name":"Journal of Computational Design and Engineering","issn_l":"2288-4300","issn":["2288-4300","2288-5048"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Design and Engineering","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","score":0.6757222414016724,"display_name":"Sustainable cities and communities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320319003","display_name":"\u0110\u1ea1i h\u1ecdc Kinh t\u1ebf Th\u00e0nh ph\u1ed1 H\u1ed3 Ch\u00ed Minh","ror":"https://ror.org/010yce376"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1953465585","https://openalex.org/W2586482892","https://openalex.org/W2732026016","https://openalex.org/W2884585870","https://openalex.org/W2906764864","https://openalex.org/W2911482505","https://openalex.org/W2919115771","https://openalex.org/W3034745255","https://openalex.org/W3035160371","https://openalex.org/W3209138359","https://openalex.org/W4213019189","https://openalex.org/W4224242217","https://openalex.org/W4239616001","https://openalex.org/W4281720633","https://openalex.org/W4289421474","https://openalex.org/W4360829898","https://openalex.org/W4382370835","https://openalex.org/W4386328365","https://openalex.org/W4388283528","https://openalex.org/W4391899226","https://openalex.org/W4403601668","https://openalex.org/W4408454369","https://openalex.org/W4411183478","https://openalex.org/W4417463635","https://openalex.org/W7138416327"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Interior":[1,155],"design":[2,29,54,58,95,105,203,212,294],"style":[3,96],"recognition":[4],"presents":[5],"a":[6,27,89,102,132,236,277],"challenging":[7],"computational":[8,28,278,293],"problem":[9],"due":[10],"to":[11,65,183],"fine-grained":[12,70,190],"inter-style":[13],"similarities,":[14],"complex":[15,81,211],"spatial":[16],"arrangements,":[17],"and":[18,24,30,51,139,172,241,249,256,289,295],"strong":[19,247],"variability":[20],"in":[21,80,292],"materials,":[22],"lighting,":[23],"layout.":[25],"From":[26],"engineering":[31,296],"perspective,":[32],"accurately":[33],"modelling":[34,75,198],"such":[35,284],"stylistic":[36,191],"variations":[37],"is":[38],"essential":[39],"not":[40],"only":[41],"for":[42,46,93,154,210,280],"classification,":[43],"but":[44],"also":[45],"enabling":[47,194],"semantic":[48],"representation,":[49],"retrieval,":[50,287],"analysis":[52,291],"of":[53,69,76,207,239,244,254,265],"cases":[55],"within":[56],"data-driven":[57,290],"systems.":[59,297],"However,":[60],"existing":[61],"approaches":[62],"often":[63],"struggle":[64],"balance":[66],"the":[67,74,186,205,222,263,266,273],"extraction":[68,167],"local":[71],"cues":[72,192],"with":[73,126,168,231],"global":[77,174],"contextual":[78],"relationships":[79],"interior":[82,94,104,200],"scenes.":[83,201],"In":[84],"this":[85],"study,":[86],"we":[87,99,149],"propose":[88,150],"unified":[90],"data-model":[91],"framework":[92],"recognition.":[97],"First,":[98],"introduce":[100],"InDes,":[101],"curated":[103],"image":[106],"data":[107,117,129,224],"set":[108,118,225],"comprising":[109],"3826":[110],"images":[111],"across":[112,199],"five":[113],"architectural":[114],"styles.":[115],"The":[116],"integrates":[119],"expert-labelled":[120],"real-world":[121],"samples":[122],"from":[123],"Vietnamese":[124],"studios,":[125],"additional":[127],"pseudo-labelled":[128],"generated":[130],"through":[131],"semisupervised":[133],"learning":[134],"strategy,":[135],"addressing":[136],"class":[137],"imbalance":[138],"supporting":[140],"robust":[141],"model":[142],"training":[143],"under":[144],"limited":[145],"annotation":[146],"conditions.":[147],"Second,":[148],"AT3":[151],"(Attention":[152],"Transformer":[153],"Style":[156],"Design":[157],"Classification),":[158],"an":[159,232,242],"attention-guided":[160,268],"transformer":[161,184],"architecture":[162,188],"that":[163,227],"combines":[164],"convolutional":[165,248],"feature":[166,180],"hierarchical":[169],"attention":[170],"mechanisms":[171],"transformer-based":[173,250],"context":[175],"modelling.":[176],"By":[177],"applying":[178],"attention-based":[179],"refinement":[181],"prior":[182],"tokenization,":[185],"proposed":[187,267],"preserves":[189],"while":[193],"effective":[195],"long-range":[196],"dependency":[197],"This":[202],"improves":[204],"quality":[206],"learned":[208,274],"representations":[209,275],"environments":[213],"characterized":[214],"by":[215,252],"subtle":[216],"visual":[217],"differences.":[218],"Extensive":[219],"experiments":[220],"on":[221],"InDes":[223],"demonstrate":[226],"AT3,":[228],"when":[229],"instantiated":[230],"Xception":[233],"backbone,":[234],"achieves":[235],"validation":[237],"accuracy":[238],"87.8%":[240],"F1-score":[243],"0.86,":[245],"outperforming":[246],"baselines":[251],"margins":[253],"5.2%":[255],"6.7%,":[257],"respectively.":[258],"Ablation":[259],"studies":[260],"further":[261],"validate":[262],"effectiveness":[264],"architecture.":[269],"Beyond":[270],"classification":[271],"performance,":[272],"provide":[276],"foundation":[279],"downstream":[281],"design-oriented":[282],"tasks":[283],"as":[285],"style-aware":[286],"clustering,":[288]},"counts_by_year":[],"updated_date":"2026-06-18T08:10:14.011955","created_date":"2026-05-05T00:00:00"}