{"id":"https://openalex.org/W4401754348","doi":"https://doi.org/10.1109/itc-cscc62988.2024.10628332","title":"Evaluating the Accuracy of Real-Time Japanese Sign Language Word Recognition with Vision Transformer Models Trained on Angular Features","display_name":"Evaluating the Accuracy of Real-Time Japanese Sign Language Word Recognition with Vision Transformer Models Trained on Angular Features","publication_year":2024,"publication_date":"2024-07-02","ids":{"openalex":"https://openalex.org/W4401754348","doi":"https://doi.org/10.1109/itc-cscc62988.2024.10628332"},"language":"en","primary_location":{"id":"doi:10.1109/itc-cscc62988.2024.10628332","doi":"https://doi.org/10.1109/itc-cscc62988.2024.10628332","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itc-cscc62988.2024.10628332","pdf_url":null,"source":{"id":"https://openalex.org/S4306498411","display_name":"International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2024 International Technical Conference on Circuits/Systems, Computers, and Communications (ITC-CSCC)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5095378514","display_name":"Tamon Kondo","orcid":"https://orcid.org/0009-0006-4394-4417","observed_orcids":["https://orcid.org/0009-0006-4394-4417"]},"institutions":[{"id":"https://openalex.org/I31618427","display_name":"Tokyo Polytechnic University","ror":"https://ror.org/035kpke84","country_code":"JP","type":"education","lineage":["https://openalex.org/I31618427"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tamon Kondo","raw_affiliation_strings":["Graduate School of Engineering, Tokyo Polytechnic University,Atsugi,Kanagawa,Japan,243-0297"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, Tokyo Polytechnic University,Atsugi,Kanagawa,Japan,243-0297","institution_ids":["https://openalex.org/I31618427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000460972","display_name":"Ryota Murai","orcid":"https://orcid.org/0009-0007-0248-9267","observed_orcids":["https://orcid.org/0009-0007-0248-9267"]},"institutions":[{"id":"https://openalex.org/I31618427","display_name":"Tokyo Polytechnic University","ror":"https://ror.org/035kpke84","country_code":"JP","type":"education","lineage":["https://openalex.org/I31618427"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryouta Murai","raw_affiliation_strings":["Tokyo Polytechnic University,Dept. of Engineering,Atsugi,Kanagawa,Japan,243-0297"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Polytechnic University,Dept. of Engineering,Atsugi,Kanagawa,Japan,243-0297","institution_ids":["https://openalex.org/I31618427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036878728","display_name":"Duk Shin","orcid":"https://orcid.org/0000-0001-8454-0319","observed_orcids":["https://orcid.org/0000-0001-8454-0319"]},"institutions":[{"id":"https://openalex.org/I31618427","display_name":"Tokyo Polytechnic University","ror":"https://ror.org/035kpke84","country_code":"JP","type":"education","lineage":["https://openalex.org/I31618427"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Duk Shin","raw_affiliation_strings":["Tokyo Polytechnic University,Faculty of Engineering,Atsugi,Kanagawa,Japan,243-0297"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Polytechnic University,Faculty of Engineering,Atsugi,Kanagawa,Japan,243-0297","institution_ids":["https://openalex.org/I31618427"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030887727","display_name":"Yousun Kang","orcid":"https://orcid.org/0009-0006-4391-7064","observed_orcids":["https://orcid.org/0009-0006-4391-7064"]},"institutions":[{"id":"https://openalex.org/I31618427","display_name":"Tokyo Polytechnic University","ror":"https://ror.org/035kpke84","country_code":"JP","type":"education","lineage":["https://openalex.org/I31618427"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yousun Kang","raw_affiliation_strings":["Tokyo Polytechnic University,Faculty of Engineering,Atsugi,Kanagawa,Japan,243-0297"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Polytechnic University,Faculty of Engineering,Atsugi,Kanagawa,Japan,243-0297","institution_ids":["https://openalex.org/I31618427"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I31618427"],"apc_list":null,"apc_paid":null,"fwci":0.7251,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.65828307,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9994999766349792,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.00019999999494757503,"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/T11285","display_name":"Hearing Impairment and Communication","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational 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/japanese-sign-language","display_name":"Japanese Sign Language","score":0.9950000047683716},{"id":"https://openalex.org/keywords/sign-language-recognition","display_name":"sign language recognition","score":0.921999990940094},{"id":"https://openalex.org/keywords/real-time-recognition","display_name":"real-time recognition","score":0.7599999904632568},{"id":"https://openalex.org/keywords/vision-transformer","display_name":"vision transformer","score":0.7799999713897705},{"id":"https://openalex.org/keywords/angular-features","display_name":"angular features","score":0.8519999980926514},{"id":"https://openalex.org/keywords/mediapipe","display_name":"MediaPipe","score":0.7699999809265137},{"id":"https://openalex.org/keywords/sign-language-translation","display_name":"sign language translation","score":0.640999972820282},{"id":"https://openalex.org/keywords/hearing-impaired-communication","display_name":"hearing-impaired communication","score":0.8019999861717224}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6949514150619507},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6337815523147583},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5001857280731201},{"id":"https://openalex.org/C522192633","wikidata":"https://www.wikidata.org/wiki/Q34228","display_name":"Sign language","level":2,"score":0.46065282821655273},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45787733793258667},{"id":"https://openalex.org/C139676723","wikidata":"https://www.wikidata.org/wiki/Q1193832","display_name":"Sign (mathematics)","level":2,"score":0.4106348752975464},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38926398754119873},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1381048560142517},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13176995515823364},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08753710985183716},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.06665515899658203},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.06455522775650024},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/itc-cscc62988.2024.10628332","doi":"https://doi.org/10.1109/itc-cscc62988.2024.10628332","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itc-cscc62988.2024.10628332","pdf_url":null,"source":{"id":"https://openalex.org/S4306498411","display_name":"International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2024 International Technical Conference on Circuits/Systems, Computers, and Communications (ITC-CSCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2559085405","https://openalex.org/W2949520286","https://openalex.org/W3173262825","https://openalex.org/W3184215204"],"related_works":["https://openalex.org/W4394755076","https://openalex.org/W7144758565","https://openalex.org/W4407691919","https://openalex.org/W7164661523","https://openalex.org/W4415822406","https://openalex.org/W7167075796","https://openalex.org/W4406524223","https://openalex.org/W4391149381","https://openalex.org/W4414017942","https://openalex.org/W4395690596"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"deep":[3],"learning":[4],"technology":[5],"has":[6,19],"greatly":[7],"advanced":[8],"research":[9,18],"designed":[10],"to":[11,44,59,84,109,126],"improve":[12],"communication":[13],"with":[14,132,138],"hearing-impaired":[15],"individuals.":[16],"This":[17,51],"particularly":[20],"focused":[21],"on":[22,121],"improving":[23],"systems":[24],"for":[25,90],"automatically":[26],"recognizing":[27],"and":[28,70,133,149],"translating":[29],"sign":[30,140],"language.":[31],"Our":[32,136],"study":[33],"introduces":[34],"a":[35,40,86],"new":[36],"method":[37,117],"that":[38],"utilizes":[39],"Vision":[41],"Transformer":[42],"(ViT)":[43],"recognize":[45],"Japanese":[46,139],"Sign":[47],"Language":[48],"in":[49,105],"real-time.":[50],"technique":[52],"employs":[53],"the":[54,61,91,100,106,111,144],"Mediapipe":[55],"pose":[56],"estimation":[57],"library":[58],"pinpoint":[60],"exact":[62],"positions":[63,73],"of":[64,102],"finger":[65],"joints":[66],"within":[67],"video":[68,122],"frames":[69],"converts":[71],"these":[72],"into":[74],"one-dimensional":[75],"angular":[76],"features.":[77],"These":[78],"features":[79],"are":[80],"then":[81],"organized":[82],"sequentially":[83],"create":[85],"two-dimensional":[87],"input":[88],"vector":[89],"ViT":[92,107],"model.":[93],"We":[94],"explored":[95],"different":[96],"configurations":[97],"by":[98],"varying":[99],"number":[101],"encoder":[103],"layers":[104],"model":[108],"find":[110],"most":[112],"accurate":[113],"setup.":[114],"The":[115],"proposed":[116,145],"was":[118],"further":[119],"tested":[120],"data":[123],"representing":[124],"words":[125],"assess":[127],"its":[128],"effectiveness,":[129],"covering":[130],"signs":[131],"without":[134],"actions.":[135],"experiments":[137],"language":[141],"videos":[142],"showed":[143],"approach's":[146],"real-time":[147],"capabilities":[148],"accuracy":[150],"evalutation.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2024-08-23T00:00:00"}
