{"id":"https://openalex.org/W7124970744","doi":"https://doi.org/10.1109/cvmi66673.2025.11337663","title":"Real- Time Sign Language Recognition with CNN - Transformer Model","display_name":"Real- Time Sign Language Recognition with CNN - Transformer Model","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W7124970744","doi":"https://doi.org/10.1109/cvmi66673.2025.11337663"},"language":null,"primary_location":{"id":"doi:10.1109/cvmi66673.2025.11337663","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvmi66673.2025.11337663","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Computer Vision and Machine Intelligence (CVMI)","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/A5123383469","display_name":"Reethu Thota","orcid":null},"institutions":[{"id":"https://openalex.org/I53465836","display_name":"Bangalore University","ror":"https://ror.org/050j2vm64","country_code":"IN","type":"education","lineage":["https://openalex.org/I53465836"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Reethu Thota","raw_affiliation_strings":["School of Computer Science Engg RV University,Bengaluru,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science Engg RV University,Bengaluru,India","institution_ids":["https://openalex.org/I53465836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123394590","display_name":"Shreyas Rajiv","orcid":null},"institutions":[{"id":"https://openalex.org/I53465836","display_name":"Bangalore University","ror":"https://ror.org/050j2vm64","country_code":"IN","type":"education","lineage":["https://openalex.org/I53465836"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shreyas Rajiv","raw_affiliation_strings":["School of Computer Science Engg RV University,Bengaluru,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science Engg RV University,Bengaluru,India","institution_ids":["https://openalex.org/I53465836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123397297","display_name":"Avanthi Narasingu","orcid":null},"institutions":[{"id":"https://openalex.org/I53465836","display_name":"Bangalore University","ror":"https://ror.org/050j2vm64","country_code":"IN","type":"education","lineage":["https://openalex.org/I53465836"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Avanthi Narasingu","raw_affiliation_strings":["School of Computer Science Engg RV University,Bengaluru,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science Engg RV University,Bengaluru,India","institution_ids":["https://openalex.org/I53465836"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.63264162,"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":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9958000183105469,"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":0.9958000183105469,"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":0.00039999998989515007,"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":0.00039999998989515007,"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/transformer","display_name":"Transformer","score":0.6327999830245972},{"id":"https://openalex.org/keywords/sign-language","display_name":"Sign language","score":0.6280999779701233},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.5060999989509583},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.4957999885082245},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.49570000171661377},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.4032000005245209},{"id":"https://openalex.org/keywords/sliding-window-protocol","display_name":"Sliding window protocol","score":0.38510000705718994}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8223000168800354},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6327999830245972},{"id":"https://openalex.org/C522192633","wikidata":"https://www.wikidata.org/wiki/Q34228","display_name":"Sign language","level":2,"score":0.6280999779701233},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5446000099182129},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.5060999989509583},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.4957999885082245},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.49570000171661377},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44530001282691956},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.4032000005245209},{"id":"https://openalex.org/C102392041","wikidata":"https://www.wikidata.org/wiki/Q592860","display_name":"Sliding window protocol","level":3,"score":0.38510000705718994},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.36160001158714294},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3594000041484833},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.3228999972343445},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30149999260902405},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2973000109195709},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2637999951839447},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.25870001316070557}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvmi66673.2025.11337663","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvmi66673.2025.11337663","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Computer Vision and Machine Intelligence (CVMI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7031009793281555}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2112796928","https://openalex.org/W2146221819","https://openalex.org/W2471695703","https://openalex.org/W2997591727","https://openalex.org/W3009828227","https://openalex.org/W3036954260","https://openalex.org/W4313855689","https://openalex.org/W4385245566","https://openalex.org/W4394841615","https://openalex.org/W4411541917"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,36],"sign":[4,110],"language":[5,111],"quiz":[6],"application":[7],"that":[8],"leverages":[9],"advanced":[10],"computer":[11],"vision":[12],"and":[13,55,71,76,98],"machine":[14],"learning":[15,58],"techniques.":[16],"Utilizing":[17],"MediaPipe":[18],"for":[19,45,95,109],"hand":[20,25],"tracking,":[21],"the":[22,100,103,106],"system":[23],"interprets":[24],"gestures":[26],"in":[27],"real-time":[28],"to":[29],"evaluate":[30],"user":[31,78],"responses.":[32],"The":[33,61],"backend":[34],"integrates":[35],"Convolutional":[37],"Neural":[38],"Network":[39],"(CNN)-":[40],"Transformer":[41],"hybrid":[42],"model,":[43,101],"fine-tuned":[44],"classification":[46],"through":[47],"sliding":[48],"window":[49],"preprocessing,":[50],"multi-head":[51],"self-attention,":[52],"L2":[53],"regularization,":[54],"an":[56,74,83],"adaptive":[57],"rate":[59],"schedule.":[60],"web":[62],"interface,":[63],"developed":[64],"using":[65],"Flask,":[66],"HyperText":[67],"Markup":[68],"Language":[69],"(HTML),":[70],"JavaScript,":[72],"provides":[73],"interactive":[75],"accessible":[77],"experience.":[79],"Experimental":[80],"results":[81],"demonstrate":[82],"accuracy":[84],"of":[85,105],"96.80%":[86],"on":[87],"data":[88],"spanning":[89],"100":[90],"classes,":[91],"which":[92],"were":[93],"used":[94],"both":[96],"training":[97],"testing":[99],"highlighting":[102],"effectiveness":[104],"proposed":[107],"approach":[108],"learning.":[112]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-01-21T00:00:00"}