{"id":"https://openalex.org/W3090421714","doi":"https://doi.org/10.3233/faia200425","title":"Self-Attention-Based Fully-Inception Networks for Continuous Sign Language Recognition","display_name":"Self-Attention-Based Fully-Inception Networks for Continuous Sign Language Recognition","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3090421714","doi":"https://doi.org/10.3233/faia200425","mag":"3090421714"},"language":"en","primary_location":{"id":"doi:10.3233/faia200425","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia200425","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia200425","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102378005","display_name":"Mingjie Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou Mingjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010561682","display_name":"Michael K. Ng","orcid":"https://orcid.org/0000-0001-6833-5227"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ng Michael","raw_affiliation_strings":["University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101133571","display_name":"Zixin Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cai Zixin","raw_affiliation_strings":["Beijing Jiaotong University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":null,"display_name":"Cheung Ka Chun","orcid":null},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Cheung Ka Chun","raw_affiliation_strings":["Nvidia (United Kingdom), Reading, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nvidia (United Kingdom), Reading, United Kingdom","institution_ids":["https://openalex.org/I1304085615"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.7471,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.94564047,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2832","last_page":"2839"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9998999834060669,"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":0.9998999834060669,"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/T12740","display_name":"Gait Recognition and Analysis","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11285","display_name":"Hearing Impairment and Communication","score":0.9894999861717224,"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/computer-science","display_name":"Computer science","score":0.5752408504486084},{"id":"https://openalex.org/keywords/sign-language","display_name":"Sign language","score":0.4877038896083832},{"id":"https://openalex.org/keywords/sign","display_name":"Sign (mathematics)","score":0.4676135778427124},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.354037344455719},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35104334354400635},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3321705758571625},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.32111960649490356},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2769179344177246},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08461001515388489},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.061473339796066284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5752408504486084},{"id":"https://openalex.org/C522192633","wikidata":"https://www.wikidata.org/wiki/Q34228","display_name":"Sign language","level":2,"score":0.4877038896083832},{"id":"https://openalex.org/C139676723","wikidata":"https://www.wikidata.org/wiki/Q1193832","display_name":"Sign (mathematics)","level":2,"score":0.4676135778427124},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.354037344455719},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35104334354400635},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3321705758571625},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.32111960649490356},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2769179344177246},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08461001515388489},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.061473339796066284},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3233/faia200425","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia200425","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},{"id":"mag:3090421714","is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/conf/ecai/ecai2020.html#ZhouNCC20","pdf_url":null,"source":{"id":"https://openalex.org/S4306418308","display_name":"European Conference on Artificial Intelligence","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":null,"is_accepted":false,"is_published":null,"raw_source_name":"European Conference on Artificial Intelligence","raw_type":null}],"best_oa_location":{"id":"doi:10.3233/faia200425","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia200425","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1677182931","https://openalex.org/W1943054406","https://openalex.org/W2127141656","https://openalex.org/W2188882108","https://openalex.org/W2250689755","https://openalex.org/W2263232528","https://openalex.org/W2463640844","https://openalex.org/W2587277634","https://openalex.org/W2746301562","https://openalex.org/W2755802490","https://openalex.org/W2759302818","https://openalex.org/W2775795276","https://openalex.org/W2788334925","https://openalex.org/W2908497602","https://openalex.org/W2948139159","https://openalex.org/W2963403868","https://openalex.org/W2963524571","https://openalex.org/W2964121744","https://openalex.org/W2964452558"],"related_works":["https://openalex.org/W2110143569","https://openalex.org/W3122938442","https://openalex.org/W4379621602","https://openalex.org/W4294690766","https://openalex.org/W2159815235","https://openalex.org/W3204710839","https://openalex.org/W2025206082","https://openalex.org/W2093958826","https://openalex.org/W1989687946","https://openalex.org/W3204019825"],"abstract_inverted_index":{"In":[0,223],"hearing-loss":[1,19],"community,":[2],"sign":[3,26,95,102],"language":[4,27,96],"is":[5,15,35,50,60,135,152,164],"a":[6,36,206],"primary":[7],"tool":[8],"to":[9,117,154,213,218,249],"communicate":[10],"with":[11,21,113,131,137,159,169],"people":[12,20],"while":[13],"there":[14],"communication":[16,33],"gap":[17],"between":[18],"normal":[22],"hearing":[23],"people.":[24],"Continuous":[25],"recognition,":[28],"which":[29,270],"can":[30],"bridge":[31],"the":[32,41,61,85,99,125,127,144,156,190,215,229,238,241,251,259,265],"gap,":[34],"challenging":[37],"task":[38],"because":[39],"of":[40,101,267],"weakly":[42],"supervised":[43],"ordered":[44],"annotations":[45],"where":[46],"no":[47],"frame-level":[48],"label":[49,212],"provided.":[51],"To":[52,122,236],"overcome":[53],"this":[54,82],"problem,":[55],"connectionist":[56],"temporal":[57,246],"classification":[58],"(CTC)":[59],"most":[62],"widely":[63],"used":[64,153],"method.":[65],"However,":[66],"CTC":[67,176],"learning":[68,174,181],"could":[69],"perform":[70],"bad":[71],"if":[72],"extracted":[73],"features":[74,158],"are":[75],"not":[76],"good.":[77],"For":[78],"better":[79,207,230],"feature":[80,150,173,180,231],"extraction,":[81],"work":[83],"presents":[84],"novel":[86],"self-attention-based":[87],"fully-inception":[88],"(SAFI)":[89],"networks":[90,146],"for":[91,210,233],"vision-based":[92],"end-to-end":[93,184,234],"continuous":[94],"recognition.":[97],"Considering":[98],"length":[100],"words":[103],"differs":[104],"from":[105],"each":[106],"other,":[107],"we":[108,244],"introduce":[109],"fully":[110,128],"inception":[111,129],"network":[112,130],"different":[114],"receptive":[115],"field":[116],"extract":[118],"dynamic":[119],"clip-level":[120,157,172],"features.":[121],"further":[123],"boost":[124],"performance,":[126],"an":[132,183],"auxiliary":[133],"classifier":[134],"trained":[136],"aggregation":[138],"cross":[139],"entropy":[140],"(ACE)":[141],"loss.":[142],"Then":[143],"self-attention":[145],"as":[147],"global":[148,178],"sequential":[149,179],"extractor":[151],"model":[155,163],"CTC.":[160],"The":[161,186],"proposed":[162],"optimized":[165],"by":[166],"jointly":[167],"training":[168],"ACE":[170],"on":[171,177,195,201,228,240,258,274,280],"and":[175,198,277],"in":[182,189],"fashion.":[185],"best":[187],"method":[188],"baselines":[191],"achieves":[192,271],"35.6%":[193],"WER":[194,200,273,279],"validation":[196,275],"set":[197,276],"34.5%":[199],"test":[202,281],"set.":[203,282],"It":[204],"employs":[205],"decoding":[208],"algorithm":[209],"pseudo":[211],"do":[214],"EM-like":[216],"optimization":[217],"fine":[219],"tune":[220],"CNN":[221],"module.":[222],"contrast,":[224],"our":[225,268],"approach":[226,269],"focuses":[227],"extraction":[232],"learning.":[235],"alleviate":[237],"overfitting":[239],"limited":[242],"dataset,":[243],"employ":[245],"elastic":[247],"deformation":[248],"triple":[250],"real-world":[252,260],"dataset":[253,261],"RWTH-PHOENIX-Weather":[254,262],"2014.":[255],"Experimental":[256],"results":[257],"2014":[263],"demonstrate":[264],"effectiveness":[266],"31.7%":[272],"31.3%":[278]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}