{"id":"https://openalex.org/W7131219525","doi":"https://doi.org/10.1109/icta-atsn68371.2025.11398227","title":"Adaptive Facial Expression Recognition in the Wild with a CNN-Swin Transformer","display_name":"Adaptive Facial Expression Recognition in the Wild with a CNN-Swin Transformer","publication_year":2025,"publication_date":"2025-12-07","ids":{"openalex":"https://openalex.org/W7131219525","doi":"https://doi.org/10.1109/icta-atsn68371.2025.11398227"},"language":null,"primary_location":{"id":"doi:10.1109/icta-atsn68371.2025.11398227","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icta-atsn68371.2025.11398227","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 10th International Conference on ICT & Accessibility (ICTA) co-located with 2025 2nd International Conference and Forum on Assistive Technologies for Special Needs (ATSN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051136903","display_name":"A\u00efda Rouissi","orcid":null},"institutions":[{"id":"https://openalex.org/I108714496","display_name":"Tunis University","ror":"https://ror.org/02q1spa57","country_code":"TN","type":"education","lineage":["https://openalex.org/I108714496"]},{"id":"https://openalex.org/I4210145739","display_name":"Time Universit\u00e9","ror":"https://ror.org/03y2yf271","country_code":"TN","type":"education","lineage":["https://openalex.org/I4210145739"]}],"countries":["TN"],"is_corresponding":true,"raw_author_name":"A\u00efda Rouissi","raw_affiliation_strings":["University of Tunis,ENSIT-LaTICE Lab,Tunis,Tunisia"],"raw_orcid":"https://orcid.org/0009-0005-3457-869X","affiliations":[{"raw_affiliation_string":"University of Tunis,ENSIT-LaTICE Lab,Tunis,Tunisia","institution_ids":["https://openalex.org/I4210145739","https://openalex.org/I108714496"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126676459","display_name":"Afef Kacem Echi","orcid":null},"institutions":[{"id":"https://openalex.org/I108714496","display_name":"Tunis University","ror":"https://ror.org/02q1spa57","country_code":"TN","type":"education","lineage":["https://openalex.org/I108714496"]},{"id":"https://openalex.org/I4210145739","display_name":"Time Universit\u00e9","ror":"https://ror.org/03y2yf271","country_code":"TN","type":"education","lineage":["https://openalex.org/I4210145739"]}],"countries":["TN"],"is_corresponding":false,"raw_author_name":"Afef Kacem Echi","raw_affiliation_strings":["University of Tunis,ENSIT-LaTICE Lab,Tunis,Tunisia"],"raw_orcid":"https://orcid.org/0000-0001-9219-5228","affiliations":[{"raw_affiliation_string":"University of Tunis,ENSIT-LaTICE Lab,Tunis,Tunisia","institution_ids":["https://openalex.org/I4210145739","https://openalex.org/I108714496"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5051136903"],"corresponding_institution_ids":["https://openalex.org/I108714496","https://openalex.org/I4210145739"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.77099222,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.8155999779701233,"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"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.8155999779701233,"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/T11448","display_name":"Face recognition and analysis","score":0.03319999948143959,"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/T10057","display_name":"Face and Expression Recognition","score":0.02160000056028366,"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-expression","display_name":"Facial expression","score":0.5913000106811523},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5471000075340271},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5404999852180481},{"id":"https://openalex.org/keywords/grayscale","display_name":"Grayscale","score":0.5343000292778015},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5235999822616577},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.45179998874664307},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.4300999939441681},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42100000381469727}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7193999886512756},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6481999754905701},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.5913000106811523},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5471000075340271},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5404999852180481},{"id":"https://openalex.org/C78201319","wikidata":"https://www.wikidata.org/wiki/Q685727","display_name":"Grayscale","level":3,"score":0.5343000292778015},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5235999822616577},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4887000024318695},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.45179998874664307},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.4300999939441681},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42100000381469727},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3749000132083893},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.35569998621940613},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.34380000829696655},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.33970001339912415},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3257000148296356},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.31040000915527344},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.28839999437332153},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.2612999975681305}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icta-atsn68371.2025.11398227","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icta-atsn68371.2025.11398227","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 10th International Conference on ICT & Accessibility (ICTA) co-located with 2025 2nd International Conference and Forum on Assistive Technologies for Special Needs (ATSN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Zero hunger","score":0.6855747699737549,"id":"https://metadata.un.org/sdg/2"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2041616772","https://openalex.org/W2103943262","https://openalex.org/W2243226955","https://openalex.org/W2325939864","https://openalex.org/W2587759925","https://openalex.org/W2738672149","https://openalex.org/W2745497104","https://openalex.org/W2773893004","https://openalex.org/W2899739544","https://openalex.org/W2938665958","https://openalex.org/W3003206535","https://openalex.org/W3112697499","https://openalex.org/W4213189310","https://openalex.org/W4280583458","https://openalex.org/W4319663643","https://openalex.org/W4319996317","https://openalex.org/W4360602654","https://openalex.org/W4380987832","https://openalex.org/W4391211169","https://openalex.org/W4400642556","https://openalex.org/W4405717318"],"related_works":[],"abstract_inverted_index":{"Real-time":[0],"understanding":[1],"of":[2,96],"facial":[3,26],"expressions":[4],"plays":[5],"a":[6,22,48,55,74],"crucial":[7],"role":[8],"in":[9,34,156],"enhancing":[10],"accessibility":[11],"and":[12,24,41,61,99,122,160],"communication":[13,144],"for":[14,64,78,145],"individuals":[15],"facing":[16],"interaction":[17],"challenges.":[18],"This":[19,91,140],"work":[20,141],"presents":[21],"robust":[23],"scalable":[25],"expression":[27],"recognition":[28],"system":[29,113],"designed":[30],"to":[31,58],"function":[32],"reliably":[33],"unconstrained":[35],"environments":[36],"with":[37,54,131,147,153],"varying":[38],"lighting,":[39],"occlusion,":[40],"head":[42],"pose":[43],"conditions.":[44],"Our":[45,112],"model":[46],"combines":[47],"custom":[49],"lightweight":[50],"Convolutional":[51],"Neural":[52],"Network":[53],"Swin":[56],"Transformer":[57,84],"fuse":[59],"local":[60],"global":[62],"features":[63],"more":[65,151],"accurate":[66],"emotional":[67],"interpretation.":[68],"The":[69],"CNN":[70],"branch":[71],"serves":[72],"as":[73],"compact":[75],"encoder":[76],"optimized":[77],"low-resolution":[79],"grayscale":[80,98],"inputs,":[81],"while":[82],"the":[83,127],"captures":[85],"long-range":[86],"dependencies":[87],"through":[88],"hierarchical":[89],"self-attention.":[90],"hybrid":[92,129],"design":[93],"enables":[94,142],"processing":[95],"both":[97],"high-resolution":[100],"RGB":[101],"images":[102],"without":[103],"intensive":[104],"preprocessing,":[105],"supporting":[106],"real-time":[107],"deployment":[108],"on":[109,117,120,124],"assistive":[110],"platforms.":[111],"achieves":[114],"83.63%":[115],"accuracy":[116],"FER2013,":[118],"93.48%":[119],"CK+,":[121],"88.85%":[123],"RAF-DB":[125],"using":[126],"same":[128],"strategy":[130],"emotion-specific":[132],"augmentation,":[133],"demonstrating":[134],"consistent":[135],"performance":[136],"across":[137],"diverse":[138],"scenarios.":[139],"nonverbal":[143],"people":[146],"disabilities,":[148],"making":[149],"technology":[150],"inclusive,":[152],"potential":[154],"applications":[155],"learning":[157],"tools,":[158],"healthcare,":[159],"emotion-aware":[161],"applications.":[162]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2026-02-25T00:00:00"}