{"id":"https://openalex.org/W7166809358","doi":"https://doi.org/10.18653/v1/2026.acl-long.1928","title":"Sign-Language Datasets at Scale: A Comprehensive Survey on Resources, Benchmarks, and Annotation Standards","display_name":"Sign-Language Datasets at Scale: A Comprehensive Survey on Resources, Benchmarks, and Annotation Standards","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166809358","doi":"https://doi.org/10.18653/v1/2026.acl-long.1928"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1928","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1928","pdf_url":"https://aclanthology.org/2026.acl-long.1928.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.1928.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139717933","display_name":"Yiming Ni","orcid":null},"institutions":[{"id":"https://openalex.org/I4210150356","display_name":"University of Washington Tacoma","ror":"https://ror.org/05n8t2628","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701","https://openalex.org/I4210150356"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiming Ni","raw_affiliation_strings":["Tacoma School of Engineering & Technology , University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tacoma School of Engineering & Technology , University of Washington","institution_ids":["https://openalex.org/I4210150356"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139828320","display_name":"Zhi-Qi Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210150356","display_name":"University of Washington Tacoma","ror":"https://ror.org/05n8t2628","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701","https://openalex.org/I4210150356"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhi-Qi Cheng","raw_affiliation_strings":["Tacoma School of Engineering & Technology , University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tacoma School of Engineering & Technology , University of Washington","institution_ids":["https://openalex.org/I4210150356"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139719141","display_name":"Jiayu Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210150356","display_name":"University of Washington Tacoma","ror":"https://ror.org/05n8t2628","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701","https://openalex.org/I4210150356"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiayu Li","raw_affiliation_strings":["Tacoma School of Engineering & Technology , University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tacoma School of Engineering & Technology , University of Washington","institution_ids":["https://openalex.org/I4210150356"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139827576","display_name":"Wei Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210150356","display_name":"University of Washington Tacoma","ror":"https://ror.org/05n8t2628","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701","https://openalex.org/I4210150356"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Cheng","raw_affiliation_strings":["Tacoma School of Engineering & Technology , University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tacoma School of Engineering & Technology , University of Washington","institution_ids":["https://openalex.org/I4210150356"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210150356"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.83181163,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"41578","last_page":"41604"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.7965999841690063,"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":0.7965999841690063,"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":0.13860000669956207,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.009399999864399433,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/annotation","display_name":"Annotation","score":0.5027999877929688},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2653999924659729},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.2524000108242035},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.25220000743865967}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6363999843597412},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5027999877929688},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39730000495910645},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3312000036239624},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.32710000872612},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2732999920845032},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2524000108242035},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25220000743865967},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.23890000581741333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1928","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1928","pdf_url":"https://aclanthology.org/2026.acl-long.1928.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.1928","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1928","pdf_url":"https://aclanthology.org/2026.acl-long.1928.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320310094","display_name":"University of Washington","ror":"https://ror.org/00cvxb145"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166809358.pdf","grobid_xml":"https://content.openalex.org/works/W7166809358.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Sign":[0],"languages":[1,5],"are":[2],"expressive":[3],"visual":[4],"used":[6],"by":[7,24],"Deaf":[8],"and":[9,19,29,41,75,78,91,102,110,117],"Hard-of-Hearing":[10],"(DHH)":[11],"communities.Despite":[12],"substantial":[13],"progress":[14],"in":[15,121],"sign-language":[16,57,119],"recognition,":[17],"translation,":[18],"production,":[20],"advances":[21],"remain":[22,47],"constrained":[23],"fragmented":[25],"datasets,":[26,58],"inconsistent":[27],"annotations,":[28],"limited":[30],"linguistic":[31],"coverage.Existing":[32],"benchmarks":[33],"often":[34],"fail":[35],"to":[36,98],"reflect":[37],"real-world":[38,122],"communication":[39],"needs,":[40],"systematic":[42],"analyses":[43],"of":[44,56],"these":[45],"limitations":[46],"limited.In":[48],"this":[49],"survey,":[50],"we":[51],"present":[52],"a":[53,87,93,108],"comprehensive":[54],"index":[55],"covering":[59],"120":[60],"resources":[61],"across":[62],"35":[63],"sign":[64],"languages.We":[65],"analyze":[66],"key":[67],"challenges":[68],"such":[69],"as":[70],"modality":[71],"imbalance,":[72],"annotation":[73],"granularity,":[74],"signer":[76],"bias,":[77],"outline":[79],"considerations":[80],"for":[81,113],"future":[82],"dataset":[83],"design.We":[84],"also":[85],"introduce":[86],"24-field":[88],"Sign-Language":[89],"Datasheet":[90],"release":[92],"public":[94],"GitHub":[95],"repository":[96],"1":[97],"support":[99],"standardized":[100],"documentation":[101],"reproducible":[103],"evaluation.Overall,":[104],"our":[105],"work":[106],"provides":[107],"unified":[109],"practical":[111],"foundation":[112],"developing":[114],"inclusive,":[115],"robust,":[116],"scalable":[118],"technologies":[120],"applications.":[123]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}