{"id":"https://openalex.org/W4415288091","doi":"https://doi.org/10.48550/arxiv.2503.15914","title":"Text-Driven Diffusion Model for Sign Language Production","display_name":"Text-Driven Diffusion Model for Sign Language Production","publication_year":2025,"publication_date":"2025-03-20","ids":{"openalex":"https://openalex.org/W4415288091","doi":"https://doi.org/10.48550/arxiv.2503.15914"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2503.15914","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.15914","pdf_url":"https://arxiv.org/pdf/2503.15914","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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.15914","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063731922","display_name":"Jiayi He","orcid":"https://orcid.org/0009-0004-7373-0423"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"He, Jiayi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110389609","display_name":"Xu Wang","orcid":"https://orcid.org/0009-0003-4788-8000"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhang, Ruobei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Ruobei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076104260","display_name":"Shengeng Tang","orcid":"https://orcid.org/0000-0001-6313-2543"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Shengeng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101651167","display_name":"Yaxiong Wang","orcid":"https://orcid.org/0000-0001-6596-8117"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yaxiong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5060524512","display_name":"Lechao Cheng","orcid":"https://orcid.org/0000-0002-7546-9052"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Lechao","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5063731922"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9728999733924866,"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":0.9728999733924866,"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/T12031","display_name":"Speech and dialogue systems","score":0.9388999938964844,"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/sign","display_name":"Sign (mathematics)","score":0.7052000164985657},{"id":"https://openalex.org/keywords/orientation","display_name":"Orientation (vector space)","score":0.6358000040054321},{"id":"https://openalex.org/keywords/sign-language","display_name":"Sign language","score":0.5708000063896179},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5253999829292297},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.49779999256134033},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4832000136375427},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.47929999232292175},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.43790000677108765},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.38019999861717224}],"concepts":[{"id":"https://openalex.org/C139676723","wikidata":"https://www.wikidata.org/wiki/Q1193832","display_name":"Sign (mathematics)","level":2,"score":0.7052000164985657},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6812999844551086},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.6358000040054321},{"id":"https://openalex.org/C522192633","wikidata":"https://www.wikidata.org/wiki/Q34228","display_name":"Sign language","level":2,"score":0.5708000063896179},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5253999829292297},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.49779999256134033},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4832000136375427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48170000314712524},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.47929999232292175},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.43790000677108765},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4049000144004822},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.38019999861717224},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3781000077724457},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.3682999908924103},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35499998927116394},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.35249999165534973},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3488999903202057},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.3294000029563904},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3131999969482422},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.30410000681877136},{"id":"https://openalex.org/C4250","wikidata":"https://www.wikidata.org/wiki/Q236813","display_name":"Sign function","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.2946000099182129},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2662999927997589},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2596000134944916}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2503.15914","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.15914","pdf_url":"https://arxiv.org/pdf/2503.15914","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.2503.15914","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.15914","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.15914","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.15914","pdf_url":"https://arxiv.org/pdf/2503.15914","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":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"introduce":[1],"the":[2,7,38,53,66,72,94,97,101,108,112,123,126,129,134,139,142,160,164,184,201],"hfut-lmc":[3],"team's":[4],"solution":[5,191],"to":[6,15,45,59,89],"SLRTP":[8],"Sign":[9],"Production":[10],"Challenge.":[11],"The":[12,82],"challenge":[13],"aims":[14],"generate":[16,60],"semantically":[17,171],"aligned":[18],"sign":[19,61,173,185],"language":[20,174,186],"pose":[21,62,74,103,175],"sequences":[22,48,104,157],"from":[23],"text":[24,47,165],"inputs.":[25],"To":[26,64],"this":[27],"end,":[28],"we":[29,76],"propose":[30],"a":[31,147,193],"Text-driven":[32],"Diffusion":[33],"Model":[34],"(TDM)":[35],"framework.":[36],"During":[37],"training":[39],"phase,":[40],"TDM":[41,143],"utilizes":[42],"an":[43],"encoder":[44],"encode":[46],"and":[49,69,92,105,169,189],"incorporates":[50],"them":[51],"into":[52],"diffusion":[54],"model":[55],"as":[56],"conditional":[57],"input":[58],"sequences.":[63,176],"guarantee":[65],"high":[67],"quality":[68],"accuracy":[70],"of":[71,100,107,125,163,196],"generated":[73,102,130],"sequences,":[75],"utilize":[77],"two":[78],"key":[79],"loss":[80,84,115],"functions.":[81],"joint":[83,98],"function":[85,116],"L_{joint}":[86],"is":[87,118],"used":[88],"precisely":[90],"measure":[91],"minimize":[93],"differences":[95],"between":[96],"positions":[99],"those":[106],"ground":[109],"truth.":[110],"Similarly,":[111],"bone":[113],"orientation":[114,124],"L_{bone}":[117],"instrumental":[119],"in":[120,128,200],"ensuring":[121],"that":[122],"bones":[127],"poses":[131],"aligns":[132],"with":[133,155],"actual,":[135],"correct":[136],"orientations.":[137],"In":[138],"inference":[140],"stage,":[141],"framework":[144,180],"takes":[145],"on":[146,183],"different":[148],"yet":[149],"equally":[150],"important":[151],"task.":[152],"It":[153],"starts":[154],"noisy":[156],"and,":[158],"under":[159],"strict":[161],"constraints":[162],"conditions,":[166],"gradually":[167],"refines":[168],"generates":[170],"consistent":[172],"Our":[177],"carefully":[178],"designed":[179],"performs":[181],"well":[182],"production":[187],"task,":[188],"our":[190],"achieves":[192],"BLEU-1":[194],"score":[195],"20.17,":[197],"placing":[198],"second":[199],"challenge.":[202]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-17T00:00:00"}