{"id":"https://openalex.org/W4400526836","doi":"https://doi.org/10.1109/fg59268.2024.10581980","title":"A Gloss-Free Sign Language Production with Discrete Representation","display_name":"A Gloss-Free Sign Language Production with Discrete Representation","publication_year":2024,"publication_date":"2024-05-27","ids":{"openalex":"https://openalex.org/W4400526836","doi":"https://doi.org/10.1109/fg59268.2024.10581980"},"language":"en","primary_location":{"id":"doi:10.1109/fg59268.2024.10581980","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fg59268.2024.10581980","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG)","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/A5090807474","display_name":"Eui Jun 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":true,"raw_author_name":"Eui Jun Hwang","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST),Daejeon,Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST),Daejeon,Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062372746","display_name":"Huije Lee","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":"Huije Lee","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST),Daejeon,Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST),Daejeon,Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100641120","display_name":"Jong Cheol Park","orcid":"https://orcid.org/0000-0002-8859-5111"},"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":"Jong C. Park","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST),Daejeon,Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST),Daejeon,Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5090807474"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":2.4432,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.88741311,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"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":0.9998000264167786,"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":0.9998000264167786,"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":0.9905999898910522,"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/T13382","display_name":"Robotics and Automated Systems","score":0.9843999743461609,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6196302175521851},{"id":"https://openalex.org/keywords/gloss","display_name":"Gloss (optics)","score":0.5985420346260071},{"id":"https://openalex.org/keywords/sign-language","display_name":"Sign language","score":0.4682024121284485},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42342615127563477},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4220491051673889},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3911374807357788},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3693088889122009},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.09907528758049011},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.08602052927017212}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6196302175521851},{"id":"https://openalex.org/C143025027","wikidata":"https://www.wikidata.org/wiki/Q900581","display_name":"Gloss (optics)","level":3,"score":0.5985420346260071},{"id":"https://openalex.org/C522192633","wikidata":"https://www.wikidata.org/wiki/Q34228","display_name":"Sign language","level":2,"score":0.4682024121284485},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42342615127563477},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4220491051673889},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3911374807357788},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3693088889122009},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.09907528758049011},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.08602052927017212},{"id":"https://openalex.org/C2781448156","wikidata":"https://www.wikidata.org/wiki/Q1570182","display_name":"Coating","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fg59268.2024.10581980","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fg59268.2024.10581980","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.49000000953674316}],"awards":[{"id":"https://openalex.org/G3377911995","display_name":null,"funder_award_id":"20014406","funder_id":"https://openalex.org/F4320336569","funder_display_name":"Shenzhen Science and Technology Innovation Program"}],"funders":[{"id":"https://openalex.org/F4320336569","display_name":"Shenzhen Science and Technology Innovation Program","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3119463769","https://openalex.org/W2035926194","https://openalex.org/W2514360315","https://openalex.org/W2045489541","https://openalex.org/W2134811186","https://openalex.org/W2160360150","https://openalex.org/W1985904311","https://openalex.org/W4247897165","https://openalex.org/W2358737221","https://openalex.org/W2040681928"],"abstract_inverted_index":{"Gloss-free":[0],"Sign":[1,47],"Language":[2,77],"Production":[3],"(SLP)":[4],"offers":[5],"a":[6,62,70],"direct":[7],"translation":[8],"of":[9,57,101,123],"spoken":[10],"language":[11,48,90],"sentences":[12],"into":[13],"sign":[14,58,113],"language,":[15],"bypassing":[16],"the":[17,82,98,121],"need":[18],"for":[19],"gloss":[20],"intermediaries.":[21],"Previous":[22],"autoregressive":[23],"SLP":[24,106],"methods":[25,107],"have":[26],"not":[27],"fully":[28],"achieved":[29],"true":[30],"autoregression,":[31],"as":[32,93,129],"they":[33],"often":[34],"depend":[35],"on":[36],"ground-truth":[37],"data":[38],"during":[39],"inference.":[40],"To":[41],"fill":[42],"this":[43],"gap,":[44],"we":[45,80],"introduce":[46],"Vector":[49],"Quantization":[50],"Network":[51],"(SignVQNet),":[52],"leveraging":[53],"discrete":[54,63,83],"spatio-temporal":[55],"representations":[56],"poses.":[59],"With":[60],"such":[61,92],"representation,":[64],"our":[65,102,117],"method":[66,103],"incorporates":[67],"beam":[68],"search,":[69],"decoding":[71],"strategy":[72],"widely":[73],"used":[74],"in":[75,108,132],"Natural":[76],"Processing.":[78],"Furthermore,":[79],"align":[81],"representation":[84],"with":[85],"linguistic":[86],"features":[87],"from":[88],"pre-trained":[89],"models":[91,139],"BERT.":[94],"Our":[95],"results":[96],"show":[97],"superior":[99],"performance":[100],"over":[104],"prior":[105],"generating":[109],"accurate":[110],"and":[111,125,138],"realistic":[112],"pose":[114],"sequences.":[115],"Additionally,":[116],"analysis":[118],"shows":[119],"that":[120],"reliability":[122],"Back-Translation":[124],"Fr\u00e9chet":[126],"Gesture":[127],"Distance":[128],"evaluation":[130],"metrics,":[131],"contrast":[133],"to":[134],"DTW-MJE.":[135],"The":[136],"code":[137],"are":[140],"available":[141],"at":[142],"https://github.com/eddie-euijun-hwang/SignVQNet.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}