{"id":"https://openalex.org/W4408354067","doi":"https://doi.org/10.1109/icassp49660.2025.10888031","title":"SDAFE: A Dual-filter Stable Diffusion Data Augmentation Method for Facial Expression Recognition","display_name":"SDAFE: A Dual-filter Stable Diffusion Data Augmentation Method for Facial Expression Recognition","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354067","doi":"https://doi.org/10.1109/icassp49660.2025.10888031"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888031","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5002117529","display_name":"Minghao Zhao","orcid":"https://orcid.org/0000-0001-9232-9185"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Minghao Zhao","raw_affiliation_strings":["Xi’an University of Technology,School of Computer Science and Engineering,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Xi’an University of Technology,School of Computer Science and Engineering,Xi’an,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000707990","display_name":"Yifei Chen","orcid":"https://orcid.org/0000-0003-1234-9966"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yifei Chen","raw_affiliation_strings":["Xi’an University of Technology,School of Computer Science and Engineering,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Xi’an University of Technology,School of Computer Science and Engineering,Xi’an,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002479762","display_name":"Jiahao Lyu","orcid":"https://orcid.org/0000-0001-6788-3942"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiahao Lyu","raw_affiliation_strings":["Xi’an University of Technology,School of Computer Science and Engineering,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Xi’an University of Technology,School of Computer Science and Engineering,Xi’an,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010696821","display_name":"Shuangli Du","orcid":"https://orcid.org/0000-0002-8897-0778"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuangli Du","raw_affiliation_strings":["Xi’an University of Technology,School of Computer Science and Engineering,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Xi’an University of Technology,School of Computer Science and Engineering,Xi’an,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082727540","display_name":"Zhiyong Lv","orcid":"https://orcid.org/0009-0005-6582-0338"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiyong Lv","raw_affiliation_strings":["Xi’an University of Technology,School of Computer Science and Engineering,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Xi’an University of Technology,School of Computer Science and Engineering,Xi’an,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035743241","display_name":"Lin Wang","orcid":"https://orcid.org/0000-0002-4761-2181"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin Wang","raw_affiliation_strings":["Xi’an University of Technology,School of Computer Science and Engineering,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Xi’an University of Technology,School of Computer Science and Engineering,Xi’an,China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5002117529"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8609,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.82435453,"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":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.5913000106811523,"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":0.5913000106811523,"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/T10057","display_name":"Face and Expression Recognition","score":0.5802000164985657,"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/T13731","display_name":"Advanced Computing and Algorithms","score":0.5695000290870667,"subfield":{"id":"https://openalex.org/subfields/3322","display_name":"Urban Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.6525182723999023},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6351221203804016},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5307756662368774},{"id":"https://openalex.org/keywords/facial-expression-recognition","display_name":"Facial expression recognition","score":0.48907047510147095},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.47001340985298157},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.46787402033805847},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.4614625573158264},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4493010938167572},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4409036636352539},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.4353233575820923},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.43125152587890625},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3221997618675232},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07569408416748047},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.06266120076179504}],"concepts":[{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.6525182723999023},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6351221203804016},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5307756662368774},{"id":"https://openalex.org/C2987714656","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Facial expression recognition","level":4,"score":0.48907047510147095},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.47001340985298157},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.46787402033805847},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.4614625573158264},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4493010938167572},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4409036636352539},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.4353233575820923},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.43125152587890625},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3221997618675232},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07569408416748047},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.06266120076179504},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888031","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324173","display_name":"Natural Science Foundation of Shaanxi Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2086161653","https://openalex.org/W2799041689","https://openalex.org/W2807869636","https://openalex.org/W2954996726","https://openalex.org/W2963691377","https://openalex.org/W2989219518","https://openalex.org/W3105914803","https://openalex.org/W3137097829","https://openalex.org/W3161346624","https://openalex.org/W4312443924","https://openalex.org/W4389474546","https://openalex.org/W4390678101","https://openalex.org/W6674330103","https://openalex.org/W6751420435","https://openalex.org/W6784333009"],"related_works":["https://openalex.org/W2642127892","https://openalex.org/W4205986151","https://openalex.org/W2355913164","https://openalex.org/W2162992774","https://openalex.org/W1153638794","https://openalex.org/W2168968280","https://openalex.org/W2901126000","https://openalex.org/W4323520705","https://openalex.org/W2116055069","https://openalex.org/W2356663679"],"abstract_inverted_index":{"Facial":[0],"expressions":[1,20,76],"are":[2],"a":[3,44,84,100,126],"powerful":[4],"medium":[5],"for":[6,48],"conveying":[7],"emotions.":[8],"In":[9],"facial":[10,49],"expression":[11,50],"recognition":[12],"(FER)":[13],"field,":[14],"the":[15,31,68,79,92,96,112,115,138,142,150,156,167],"difficulty":[16],"of":[17,34,70,95,114,158,169],"collecting":[18],"specific":[19],"often":[21],"leads":[22],"to":[23,77,90,109],"class":[24,54],"imbalance":[25,55],"in":[26,134,171],"mainstream":[27],"datasets,":[28],"significantly":[29,164],"reducing":[30],"classification":[32],"accuracy":[33,140],"deep":[35],"neural":[36],"networks.":[37],"To":[38],"address":[39],"these":[40],"issues,":[41],"we":[42,73,124],"propose":[43],"stable-diffusion-based":[45],"augmentation":[46],"method":[47],"(SDAFE)":[51],"that":[52,111],"resolves":[53],"problems":[56],"and":[57,99,145,152],"enhances":[58],"data":[59],"generation":[60],"quality":[61,94],"through":[62,166],"cross-modal":[63,103],"label":[64],"guidance.":[65],"By":[66],"leveraging":[67],"neutrality":[69],"neutral":[71],"faces,":[72],"generate":[74],"additional":[75],"balance":[78],"dataset":[80,144],"classes.":[81],"We":[82],"introduce":[83,125],"peak":[85],"signal-to-noise":[86],"ratio":[87],"(PSNR)":[88],"filter":[89,104],"ensure":[91,110],"high":[93],"generated":[97,116],"images":[98,117],"cosine":[101],"similarity":[102],"based":[105],"on":[106,141,149],"CLIP":[107],"encoders":[108],"content":[113],"accurately":[118],"aligns":[119],"with":[120],"their":[121],"labels.":[122],"Furthermore,":[123],"novel":[127],"model,":[128],"FERNeXt,":[129],"which":[130],"demonstrates":[131],"outstanding":[132],"performance":[133,157],"FER":[135],"tasks,":[136],"surpassing":[137],"state-of-the-art":[139],"FER2013":[143],"achieving":[146],"strong":[147],"results":[148],"RAF-DB":[151],"NHFI":[153],"datasets.":[154],"Subsequently,":[155],"several":[159],"models":[160],"across":[161],"different":[162],"datasets":[163],"improves":[165],"use":[168],"SDAFE":[170],"our":[172],"experiments.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}