{"id":"https://openalex.org/W7123346878","doi":"https://doi.org/10.1109/tai.2025.3646146","title":"ConSignformer: Conformer-Based Framework for Continuous Sign Language Recognition","display_name":"ConSignformer: Conformer-Based Framework for Continuous Sign Language Recognition","publication_year":2026,"publication_date":"2026-01-12","ids":{"openalex":"https://openalex.org/W7123346878","doi":"https://doi.org/10.1109/tai.2025.3646146"},"language":null,"primary_location":{"id":"doi:10.1109/tai.2025.3646146","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2025.3646146","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Artificial Intelligence","raw_type":"journal-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/A5073222395","display_name":"Neena Aloysius","orcid":"https://orcid.org/0000-0002-3212-6607"},"institutions":[{"id":"https://openalex.org/I81556334","display_name":"Amrita Vishwa Vidyapeetham","ror":"https://ror.org/03am10p12","country_code":"IN","type":"education","lineage":["https://openalex.org/I81556334"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Neena Aloysius","raw_affiliation_strings":["AmritaCREATE, Amrita Vishwa Vidyapeetham, Amritapuri, Kerala, India"],"raw_orcid":"https://orcid.org/0000-0002-3212-6607","affiliations":[{"raw_affiliation_string":"AmritaCREATE, Amrita Vishwa Vidyapeetham, Amritapuri, Kerala, India","institution_ids":["https://openalex.org/I81556334"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122902781","display_name":"Geetha M","orcid":null},"institutions":[{"id":"https://openalex.org/I81556334","display_name":"Amrita Vishwa Vidyapeetham","ror":"https://ror.org/03am10p12","country_code":"IN","type":"education","lineage":["https://openalex.org/I81556334"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Geetha M","raw_affiliation_strings":["Amrita School of Computing, Amrita Vishwa Vidyapeetham, Amritapuri, Kerala, India"],"raw_orcid":"https://orcid.org/0000-0002-5150-8731","affiliations":[{"raw_affiliation_string":"Amrita School of Computing, Amrita Vishwa Vidyapeetham, Amritapuri, Kerala, India","institution_ids":["https://openalex.org/I81556334"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005494115","display_name":"Atul Sajjanhar","orcid":"https://orcid.org/0000-0002-0445-0573"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Atul Sajjanhar","raw_affiliation_strings":["School of Information Technology, Deakin University, Geelong, VIC, Australia"],"raw_orcid":"https://orcid.org/0000-0002-0445-0573","affiliations":[{"raw_affiliation_string":"School of Information Technology, Deakin University, Geelong, VIC, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054568448","display_name":"Prema Nedungadi","orcid":"https://orcid.org/0000-0001-8774-3541"},"institutions":[{"id":"https://openalex.org/I81556334","display_name":"Amrita Vishwa Vidyapeetham","ror":"https://ror.org/03am10p12","country_code":"IN","type":"education","lineage":["https://openalex.org/I81556334"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Prema Nedungadi","raw_affiliation_strings":["Amrita School of Computing, Amrita Vishwa Vidyapeetham, Amritapuri, Kerala, India"],"raw_orcid":"https://orcid.org/0000-0001-8774-3541","affiliations":[{"raw_affiliation_string":"Amrita School of Computing, Amrita Vishwa Vidyapeetham, Amritapuri, Kerala, India","institution_ids":["https://openalex.org/I81556334"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":0.03387582,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"7","issue":"7","first_page":"3808","last_page":"3822"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9927999973297119,"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":0.9927999973297119,"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/T11285","display_name":"Hearing Impairment and Communication","score":0.0015999999595806003,"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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.0008999999845400453,"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/sign-language","display_name":"Sign language","score":0.8102999925613403},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.671999990940094},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.49950000643730164},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.48489999771118164},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.4788999855518341},{"id":"https://openalex.org/keywords/sign","display_name":"Sign (mathematics)","score":0.450300008058548},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.3995000123977661},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.3953999876976013},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.38960000872612},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.37619999051094055}],"concepts":[{"id":"https://openalex.org/C522192633","wikidata":"https://www.wikidata.org/wiki/Q34228","display_name":"Sign language","level":2,"score":0.8102999925613403},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7810999751091003},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.671999990940094},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6068999767303467},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.49950000643730164},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.48489999771118164},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.4788999855518341},{"id":"https://openalex.org/C139676723","wikidata":"https://www.wikidata.org/wiki/Q1193832","display_name":"Sign (mathematics)","level":2,"score":0.450300008058548},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4300000071525574},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3995000123977661},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3953999876976013},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.38960000872612},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.37619999051094055},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3686000108718872},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.35690000653266907},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3483999967575073},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.34360000491142273},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3353999853134155},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.3319999873638153},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.3271999955177307},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32510000467300415},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.3192000091075897},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31859999895095825},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.31209999322891235},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3027999997138977},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C190553849","wikidata":"https://www.wikidata.org/wiki/Q6752310","display_name":"Manual communication","level":3,"score":0.25859999656677246},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.25440001487731934}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tai.2025.3646146","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2025.3646146","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8283026218414307,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Continuous":[0],"Sign":[1],"Language":[2],"Recognition":[3],"(CSLR)":[4],"is":[5,59,83],"a":[6,40,46,50,60,100,107,123,197],"challenging":[7],"computer":[8],"vision":[9],"task":[10],"that":[11],"automatically":[12],"recognizes":[13],"sequences":[14],"of":[15,39,99,117,159,180],"sign":[16,81,135],"language":[17,82],"gestures":[18],"from":[19],"continuous":[20],"video":[21],"streams,":[22],"aiming":[23],"to":[24,162,190],"bridge":[25],"communication":[26],"barriers":[27],"for":[28,36,52,80],"the":[29,70,77,97,113,118,157,160,169,178,181,191,207],"deaf":[30],"community.":[31],"Conventional":[32],"deep":[33],"learning":[34,57,115],"frameworks":[35],"CSLR":[37,92,201],"consist":[38],"single":[41],"or":[42],"multimodal":[43],"feature":[44],"extractor,":[45],"sequence-learning":[47,109],"module":[48,58],"and":[49,106,141,164,171,185,211],"decoder":[51],"outputting":[53],"glosses.":[54],"The":[55,174],"sequence":[56,72,114],"crucial":[61],"part":[62],"wherein":[63],"transformers":[64],"have":[65],"demonstrated":[66],"their":[67],"efficacy":[68],"in":[69,76],"sequenceto-":[71],"tasks.":[73],"However,":[74],"experimentation":[75],"sequencelearning":[78],"component":[79],"limited.":[84],"In":[85],"this":[86],"work,":[87],"we":[88,121],"present":[89],"an":[90],"innovative":[91],"framework,":[93],"ConSignformer,":[94],"which":[95,132,154],"combines":[96],"strengths":[98],"hybrid":[101],"network":[102],"built":[103],"with":[104],"S3DCNN":[105],"Conformer-based":[108,198],"backbone.":[110],"To":[111],"enhance":[112],"capabilities":[116],"Conformer":[119,161],"module,":[120],"propose":[122],"novel":[124],"unsupervised":[125],"pretraining":[126,183],"strategy":[127,184],"called":[128],"Regressional":[129],"Feature":[130],"Extraction,":[131],"uniquely":[133],"leverages":[134],"pose":[136],"videos":[137],"as":[138],"training":[139],"data":[140],"employs":[142],"Mean":[143],"Squared":[144],"Error":[145],"loss.":[146],"We":[147],"then":[148],"introduce":[149],"Cross-Modal":[150],"Relative":[151],"Attention":[152],"(CMRA),":[153],"further":[155],"enhances":[156],"ability":[158],"learn":[163],"utilize":[165],"complex":[166],"relationships":[167],"within":[168],"RGB":[170],"keypoints":[172],"data.":[173],"experimental":[175],"results":[176],"confirm":[177],"effectiveness":[179],"adopted":[182],"demonstrate":[186],"how":[187],"CMRA":[188],"contributes":[189],"recognition":[192],"process.":[193],"Remarkably,":[194],"by":[195],"leveraging":[196],"backbone,":[199],"our":[200],"model":[202],"achieves":[203],"state-ofthe-art":[204],"performance":[205],"on":[206],"benchmark":[208],"datasets:":[209],"PHOENIX-2014":[210],"PHOENIX-2014T.":[212]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-01-14T00:00:00"}