{"id":"https://openalex.org/W4417079260","doi":"https://doi.org/10.18653/v1/2026.acl-long.31","title":"Hybrid Autoregressive-Diffusion Model for Real-Time Sign Language Production","display_name":"Hybrid Autoregressive-Diffusion Model for Real-Time Sign Language Production","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4417079260","doi":"https://doi.org/10.18653/v1/2026.acl-long.31"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.31","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.31","pdf_url":null,"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":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.18653/v1/2026.acl-long.31","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108825465","display_name":"M. H. Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maoxiao Ye","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025044299","display_name":"Xinfeng Ye","orcid":"https://orcid.org/0000-0001-8483-2872"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinfeng Ye","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5051272781","display_name":"M. Manoharan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sathiamoorthy Manoharan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.00958543,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"750","last_page":"763"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9839000105857849,"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":0.9839000105857849,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.002899999963119626,"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"}},{"id":"https://openalex.org/T11285","display_name":"Hearing Impairment and Communication","score":0.0027000000700354576,"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/autoregressive-model","display_name":"Autoregressive model","score":0.6358000040054321},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5806999802589417},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5110999941825867},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.46380001306533813},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.40070000290870667},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.3781000077724457},{"id":"https://openalex.org/keywords/sign","display_name":"Sign (mathematics)","score":0.37560001015663147},{"id":"https://openalex.org/keywords/fusion-mechanism","display_name":"Fusion mechanism","score":0.36070001125335693}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7569000124931335},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.6358000040054321},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5806999802589417},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5110999941825867},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5013999938964844},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.46380001306533813},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.40070000290870667},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.3781000077724457},{"id":"https://openalex.org/C139676723","wikidata":"https://www.wikidata.org/wiki/Q1193832","display_name":"Sign (mathematics)","level":2,"score":0.37560001015663147},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.36070001125335693},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.35280001163482666},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.350600004196167},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34599998593330383},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3361000120639801},{"id":"https://openalex.org/C197115733","wikidata":"https://www.wikidata.org/wiki/Q1003136","display_name":"Forcing (mathematics)","level":2,"score":0.3163999915122986},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C522192633","wikidata":"https://www.wikidata.org/wiki/Q34228","display_name":"Sign language","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C42536954","wikidata":"https://www.wikidata.org/wiki/Q7049462","display_name":"Nonlinear autoregressive exogenous model","level":3,"score":0.2712000012397766},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2533000111579895},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.25130000710487366},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.31","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.31","pdf_url":null,"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"},{"id":"pmh:oai:arXiv.org:2507.09105","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2507.09105","pdf_url":"https://arxiv.org/pdf/2507.09105","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.09105","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.09105","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.31","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.31","pdf_url":null,"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":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Earlier":[0],"Sign":[1],"Language":[2],"Production":[3],"(SLP)":[4],"models":[5],"typically":[6],"relied":[7],"on":[8,95],"autoregressive":[9],"decoding,":[10],"which":[11],"naturally":[12],"preserves":[13],"temporal":[14],"causality":[15],"but":[16],"suffers":[17],"from":[18],"error":[19],"accumulation":[20],"at":[21],"inference":[22],"time.":[23],"More":[24],"recent":[25],"diffusion-based":[26],"approaches":[27],"improve":[28,87],"generation":[29,62],"quality":[30],"through":[31],"iterative":[32],"denoising,":[33],"yet":[34],"their":[35],"sequence-level":[36],"refinement":[37],"process":[38],"introduces":[39],"substantial":[40],"latency.":[41],"To":[42],"address":[43],"this":[44],"trade-off,":[45],"we":[46],"propose":[47],"HybridSign,":[48],"a":[49,77,139],"hybrid":[50],"autoregressive-diffusion":[51],"model":[52],"for":[53],"low-latency":[54],"sign":[55],"language":[56],"production":[57],"that":[58,100],"combines":[59],"causal":[60],"frame":[61],"with":[63],"flow-based":[64],"diffusion":[65],"refinement.":[66],"A":[67],"Multi-Scale":[68],"Pose":[69],"Representation":[70],"module":[71],"captures":[72],"fine-grained":[73],"articulator":[74],"features,":[75],"while":[76,127],"Confidence-Aware":[78],"Causal":[79],"Attention":[80],"mechanism":[81],"leverages":[82],"joint-level":[83],"confidence":[84],"scores":[85,120],"to":[86,130,135],"robustness":[88],"under":[89,138],"noisy":[90],"2D":[91],"pose":[92],"observations.":[93],"Experiments":[94],"PHOENIX14T":[96],"and":[97,123,132],"How2Sign":[98,114],"show":[99],"HybridSign":[101],"consistently":[102],"achieves":[103],"the":[104,109,113],"best":[105],"quality--efficiency":[106],"trade-off":[107],"among":[108],"compared":[110],"baselines.":[111],"On":[112],"test":[115],"split,":[116],"it":[117],"reaches":[118],"BLEU-1/4":[119],"of":[121,125],"30.12/6.48":[122],"DTW":[124],"3.89,":[126],"reducing":[128],"time-to-first-frame":[129],"5.90s":[131],"increasing":[133],"throughput":[134],"10.17":[136],"FPS":[137],"60-frame":[140],"evaluation":[141],"protocol.":[142]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}