{"id":"https://openalex.org/W4416191652","doi":"https://doi.org/10.1109/wacv61042.2026.00304","title":"Large Sign Language Models: Toward 3D American Sign Language Translation","display_name":"Large Sign Language Models: Toward 3D American Sign Language Translation","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4416191652","doi":"https://doi.org/10.1109/wacv61042.2026.00304"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00304","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00304","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2511.08535","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059508758","display_name":"Sen Zhang","orcid":"https://orcid.org/0000-0003-0416-8006"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sen Zhang","raw_affiliation_strings":["Rutgers University,US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University,US","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101730102","display_name":"Xiaoxiao He","orcid":"https://orcid.org/0000-0003-4581-0712"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoxiao He","raw_affiliation_strings":["Rutgers University,US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University,US","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075667246","display_name":"Di Liu","orcid":"https://orcid.org/0000-0003-4906-9503"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Di Liu","raw_affiliation_strings":["Meta Reality Labs,US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs,US","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014980847","display_name":"Zhaoyang Xia","orcid":"https://orcid.org/0000-0003-3536-5387"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhaoyang Xia","raw_affiliation_strings":["Rutgers University,US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University,US","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070117750","display_name":"Mingyu Zhao","orcid":"https://orcid.org/0000-0001-8145-8184"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mingyu Zhao","raw_affiliation_strings":["Rutgers University,US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University,US","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103012948","display_name":"Chaowei Tan","orcid":"https://orcid.org/0000-0002-5852-7118"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chaowei Tan","raw_affiliation_strings":["Rutgers University,US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University,US","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020214405","display_name":"Vivian Li","orcid":"https://orcid.org/0000-0003-2041-0085"},"institutions":[{"id":"https://openalex.org/I4210108021","display_name":"Prism Clinical Research","ror":"https://ror.org/011bmz187","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210108021"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vivian Li","raw_affiliation_strings":["PRISMS,US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PRISMS,US","institution_ids":["https://openalex.org/I4210108021"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115587783","display_name":"\u0411\u043e \u041b\u044e","orcid":"https://orcid.org/0000-0003-3045-628X"},"institutions":[{"id":"https://openalex.org/I1330693074","display_name":"Walmart (United States)","ror":"https://ror.org/04j0gge90","country_code":"US","type":"company","lineage":["https://openalex.org/I1330693074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Liu","raw_affiliation_strings":["Walmart Global Tech,US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Walmart Global Tech,US","institution_ids":["https://openalex.org/I1330693074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109600054","display_name":"Dimitris Metaxas","orcid":null},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dimitris N. Metaxas","raw_affiliation_strings":["Rutgers University,US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University,US","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069589954","display_name":"Mubbasir Kapadia","orcid":"https://orcid.org/0000-0002-3501-0028"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mubbasir Kapadia","raw_affiliation_strings":["Rutgers University,US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University,US","institution_ids":["https://openalex.org/I102322142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0035524,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3109","last_page":"3119"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9919000267982483,"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":0.9919000267982483,"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/T10789","display_name":"Interactive and Immersive Displays","score":0.0010999999940395355,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/sign-language","display_name":"Sign language","score":0.6990000009536743},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.6128000020980835},{"id":"https://openalex.org/keywords/american-sign-language","display_name":"American Sign Language","score":0.5289999842643738},{"id":"https://openalex.org/keywords/language-interpretation","display_name":"Language interpretation","score":0.46239998936653137},{"id":"https://openalex.org/keywords/sign","display_name":"Sign (mathematics)","score":0.45159998536109924},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.4456999897956848},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.42289999127388},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.39079999923706055}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7699000239372253},{"id":"https://openalex.org/C522192633","wikidata":"https://www.wikidata.org/wiki/Q34228","display_name":"Sign language","level":2,"score":0.6990000009536743},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.6128000020980835},{"id":"https://openalex.org/C2776737515","wikidata":"https://www.wikidata.org/wiki/Q14759","display_name":"American Sign Language","level":3,"score":0.5289999842643738},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5259000062942505},{"id":"https://openalex.org/C72280650","wikidata":"https://www.wikidata.org/wiki/Q210439","display_name":"Language interpretation","level":3,"score":0.46239998936653137},{"id":"https://openalex.org/C139676723","wikidata":"https://www.wikidata.org/wiki/Q1193832","display_name":"Sign (mathematics)","level":2,"score":0.45159998536109924},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.4456999897956848},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44510000944137573},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.42289999127388},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.39079999923706055},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.38350000977516174},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.3668000102043152},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.3474999964237213},{"id":"https://openalex.org/C150303390","wikidata":"https://www.wikidata.org/wiki/Q1983852","display_name":"Virtual actor","level":3,"score":0.3402999937534332},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.3321000039577484},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33059999346733093},{"id":"https://openalex.org/C83479923","wikidata":"https://www.wikidata.org/wiki/Q2063748","display_name":"Universal Networking Language","level":4,"score":0.3093999922275543},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C83195618","wikidata":"https://www.wikidata.org/wiki/Q590951","display_name":"Cued speech","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.2614000141620636},{"id":"https://openalex.org/C107953548","wikidata":"https://www.wikidata.org/wiki/Q1172433","display_name":"Wired glove","level":3,"score":0.2567000091075897}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00304","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00304","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2511.08535","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.08535","pdf_url":"https://arxiv.org/pdf/2511.08535","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2511.08535","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.08535","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2511.08535","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.08535","pdf_url":"https://arxiv.org/pdf/2511.08535","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306110","display_name":"U.S. Department of Homeland Security","ror":"https://ror.org/00jyr0d86"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4416191652.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,112],"present":[1],"Large":[2,19],"Sign":[3,14],"Language":[4,15,20],"Models":[5,21],"(LSLM),":[6],"a":[7,141],"novel":[8],"framework":[9],"for":[10,74],"translating":[11],"3D":[12,48,61,118],"American":[13],"(ASL)":[16],"by":[17,132],"leveraging":[18],"(LLMs)":[22],"as":[23],"the":[24,75,79,87,95],"backbone,":[25],"which":[26],"can":[27,129],"benefit":[28],"hearing-impaired":[29,76],"individuals\u2019":[30],"virtual":[31],"communication.":[32,111],"Unlike":[33],"existing":[34],"sign":[35,49],"language":[36,50],"recognition":[37],"methods":[38],"that":[39],"rely":[40],"on":[41],"2D":[42],"video,":[43],"our":[44,84],"approach":[45],"directly":[46],"utilizes":[47],"data":[51],"to":[52,105,121],"capture":[53],"rich":[54],"spatial,":[55],"gestural,":[56],"and":[57,67,123],"depth":[58],"information":[59],"in":[60],"scenes.":[62],"This":[63,138],"enables":[64],"more":[65],"accurate":[66],"resilient":[68],"translation,":[69,83],"enhancing":[70],"digital":[71],"communication":[72],"accessibility":[73],"community.":[77],"Beyond":[78],"task":[80],"of":[81,89,98,109,150,154],"ASL":[82],"work":[85,139],"explores":[86],"integration":[88],"complex,":[90],"embodied":[91],"multimodal":[92,146],"languages":[93],"into":[94],"processing":[96],"capabilities":[97],"LLMs,":[99],"moving":[100],"beyond":[101],"purely":[102],"text-based":[103],"inputs":[104],"broaden":[106],"their":[107],"understanding":[108,151],"human":[110],"investigate":[113],"both":[114],"direct":[115],"translation":[116],"from":[117],"gesture":[119],"features":[120],"text":[122],"an":[124],"instruction-guided":[125],"setting":[126],"where":[127],"translations":[128],"be":[130],"modulated":[131],"external":[133],"prompts,":[134],"offering":[135],"greater":[136],"flexibility.":[137],"provides":[140],"foundational":[142],"step":[143],"toward":[144],"inclusive,":[145],"intelligent":[147],"systems":[148],"capable":[149],"diverse":[152],"forms":[153],"language.":[155]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-13T00:00:00"}
