{"id":"https://openalex.org/W4224930880","doi":"https://doi.org/10.1109/icassp43922.2022.9746526","title":"Vision Transformer Equipped With Neural Resizer On Facial Expression Recognition Task","display_name":"Vision Transformer Equipped With Neural Resizer On Facial Expression Recognition Task","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224930880","doi":"https://doi.org/10.1109/icassp43922.2022.9746526"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746526","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746526","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5047506151","display_name":"Hyeonbin Hwang","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyeonbin Hwang","raw_affiliation_strings":["KAIST,Korea","KAIST, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"KAIST, Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100350562","display_name":"Soyeon Kim","orcid":"https://orcid.org/0000-0001-7049-9191"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Soyeon Kim","raw_affiliation_strings":["KAIST,Korea","KAIST, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"KAIST, Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025992462","display_name":"Wei-Jin Park","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei-Jin Park","raw_affiliation_strings":["ACRYL,Korea","ACRYL, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ACRYL,Korea","institution_ids":[]},{"raw_affiliation_string":"ACRYL, Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083441138","display_name":"Jiho Seo","orcid":"https://orcid.org/0000-0001-9374-4591"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiho Seo","raw_affiliation_strings":["ACRYL,Korea","ACRYL, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ACRYL,Korea","institution_ids":[]},{"raw_affiliation_string":"ACRYL, Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109543217","display_name":"Kyungtae Ko","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kyungtae Ko","raw_affiliation_strings":["ACRYL,Korea","ACRYL, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ACRYL,Korea","institution_ids":[]},{"raw_affiliation_string":"ACRYL, Korea","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055617751","display_name":"Hyeon Yeo","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyeon Yeo","raw_affiliation_strings":["KAIST,Korea","KAIST, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"KAIST, Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9246,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.83310258,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2614","last_page":"2618"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10057","display_name":"Face and Expression Recognition","score":0.9987999796867371,"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/T10057","display_name":"Face and Expression Recognition","score":0.9987999796867371,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9975000023841858,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7691383361816406},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6619887948036194},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5646164417266846},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.4691060185432434},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44933223724365234},{"id":"https://openalex.org/keywords/low-resolution","display_name":"Low resolution","score":0.41944265365600586},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.4162091314792633},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41036534309387207},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39601409435272217},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34112775325775146},{"id":"https://openalex.org/keywords/high-resolution","display_name":"High resolution","score":0.20255932211875916},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.19650617241859436},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.18976730108261108}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7691383361816406},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6619887948036194},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5646164417266846},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.4691060185432434},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44933223724365234},{"id":"https://openalex.org/C3019883945","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Low resolution","level":3,"score":0.41944265365600586},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.4162091314792633},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41036534309387207},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39601409435272217},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34112775325775146},{"id":"https://openalex.org/C3020199158","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"High resolution","level":2,"score":0.20255932211875916},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.19650617241859436},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.18976730108261108},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746526","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746526","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W603908379","https://openalex.org/W1796263212","https://openalex.org/W2108113956","https://openalex.org/W2481681431","https://openalex.org/W2738672149","https://openalex.org/W2799041689","https://openalex.org/W2897552070","https://openalex.org/W2960178077","https://openalex.org/W2963351448","https://openalex.org/W2970941190","https://openalex.org/W2985817549","https://openalex.org/W3003720578","https://openalex.org/W3021995521","https://openalex.org/W3035336958","https://openalex.org/W3035605421","https://openalex.org/W3043496927","https://openalex.org/W3094502228","https://openalex.org/W3124054989","https://openalex.org/W3137278571","https://openalex.org/W3138516171","https://openalex.org/W3141497777","https://openalex.org/W3170874841","https://openalex.org/W3171206729","https://openalex.org/W4214753187","https://openalex.org/W4287083813","https://openalex.org/W4287716221","https://openalex.org/W4394645697","https://openalex.org/W6618372016","https://openalex.org/W6676019839","https://openalex.org/W6761681504","https://openalex.org/W6764733053","https://openalex.org/W6780530918","https://openalex.org/W6784333009","https://openalex.org/W6788135285","https://openalex.org/W6792072491","https://openalex.org/W6797970987","https://openalex.org/W6864202710"],"related_works":["https://openalex.org/W2123478443","https://openalex.org/W2115635058","https://openalex.org/W2088830394","https://openalex.org/W2081765545","https://openalex.org/W2088050694","https://openalex.org/W2109002610","https://openalex.org/W2386244137","https://openalex.org/W2907949889","https://openalex.org/W1978502011","https://openalex.org/W3083834739"],"abstract_inverted_index":{"When":[0],"it":[1],"comes":[2],"to":[3,34,48,62,66,88,92,105],"wild":[4],"conditions,":[5],"Facial":[6],"Expression":[7],"Recognition":[8],"is":[9,86],"often":[10],"challenged":[11],"with":[12,51,118,131,138],"low-quality":[13],"data":[14,91],"and":[15,111,124,143],"imbalanced,":[16],"ambiguous":[17],"labels.":[18],"This":[19],"field":[20,55],"has":[21,45],"much":[22],"benefited":[23],"from":[24],"CNN":[25,29],"based":[26],"approaches;":[27],"however,":[28],"models":[30,65],"have":[31],"structural":[32],"limitations":[33],"see":[35],"the":[36,63,77,82,122,136,146],"facial":[37],"regions":[38],"in":[39,113,141],"distance.":[40],"As":[41],"a":[42,52,99,114],"remedy,":[43],"Transformer":[44,107,139],"been":[46],"introduced":[47],"vision":[49],"fields":[50],"global":[53],"receptive":[54],"but":[56],"requires":[57],"adjusting":[58],"input":[59],"spatial":[60],"size":[61],"pretrained":[64],"enjoy":[67],"its":[68],"strong":[69],"inductive":[70],"bias":[71],"at":[72],"hands.":[73],"We":[74],"herein":[75],"raise":[76],"question":[78],"of":[79],"whether":[80],"using":[81],"deterministic":[83],"interpolation":[84],"method":[85],"enough":[87],"feed":[89],"low-resolution":[90],"Transformer.":[93],"In":[94],"this":[95],"work,":[96],"we":[97],"propose":[98],"novel":[100],"training":[101],"framework,":[102],"Neural":[103,129],"Resizer,":[104],"support":[106],"by":[108],"compensating":[109],"information":[110],"downscaling":[112],"data-driven":[115],"manner":[116],"trained":[117],"loss":[119,133],"function":[120,134],"balancing":[121],"noisiness":[123],"imbalance.":[125],"Experiments":[126],"show":[127],"our":[128],"Resizer":[130],"F-PDLS":[132],"improves":[135],"performance":[137],"variants":[140],"general":[142],"nearly":[144],"achieves":[145],"state-of-the-art":[147],"performance.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}