{"id":"https://openalex.org/W4408352290","doi":"https://doi.org/10.1109/icassp49660.2025.10890302","title":"3DSignDiff: Towards 3D Sign Language Gesture Generation","display_name":"3DSignDiff: Towards 3D Sign Language Gesture Generation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352290","doi":"https://doi.org/10.1109/icassp49660.2025.10890302"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890302","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890302","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5024353923","display_name":"Ronghao Yu","orcid":"https://orcid.org/0009-0008-8551-5834"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ronghao Yu","raw_affiliation_strings":["ShanghaiTech,Center for Adaptive System Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech,Center for Adaptive System Engineering,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103805411","display_name":"Yun Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Liu","raw_affiliation_strings":["ShanghaiTech,Center for Adaptive System Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech,Center for Adaptive System Engineering,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiyue Bai","orcid":null},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiyue Bai","raw_affiliation_strings":["ShanghaiTech,Center for Adaptive System Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech,Center for Adaptive System Engineering,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085192407","display_name":"Rui Yang","orcid":"https://orcid.org/0000-0002-7143-5568"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Yang","raw_affiliation_strings":["ShanghaiTech,Center for Adaptive System Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech,Center for Adaptive System Engineering,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111513090","display_name":"Yingna Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingna Wu","raw_affiliation_strings":["ShanghaiTech,Center for Adaptive System Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech,Center for Adaptive System Engineering,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I30809798"],"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":"1","last_page":"5"},"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":0.9833999872207642,"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/T10914","display_name":"Tactile and Sensory Interactions","score":0.9609000086784363,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.8026609420776367},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7346513867378235},{"id":"https://openalex.org/keywords/sign-language","display_name":"Sign language","score":0.6375750303268433},{"id":"https://openalex.org/keywords/sign","display_name":"Sign (mathematics)","score":0.5276229381561279},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44965294003486633},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.4275430738925934},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40449434518814087},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2801443636417389},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08404228091239929},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.05336374044418335}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.8026609420776367},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7346513867378235},{"id":"https://openalex.org/C522192633","wikidata":"https://www.wikidata.org/wiki/Q34228","display_name":"Sign language","level":2,"score":0.6375750303268433},{"id":"https://openalex.org/C139676723","wikidata":"https://www.wikidata.org/wiki/Q1193832","display_name":"Sign (mathematics)","level":2,"score":0.5276229381561279},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44965294003486633},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.4275430738925934},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40449434518814087},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2801443636417389},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08404228091239929},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.05336374044418335},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890302","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890302","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2497597915","https://openalex.org/W2752796333","https://openalex.org/W2962730651","https://openalex.org/W2963361924","https://openalex.org/W2967443589","https://openalex.org/W2982625143","https://openalex.org/W2997573805","https://openalex.org/W3083173864","https://openalex.org/W3107972479","https://openalex.org/W3118288752","https://openalex.org/W3168702146","https://openalex.org/W3180355996","https://openalex.org/W4312262410","https://openalex.org/W4312674262","https://openalex.org/W4386076103","https://openalex.org/W4390872297","https://openalex.org/W4392902988","https://openalex.org/W4400527496","https://openalex.org/W6640963894","https://openalex.org/W6739901393","https://openalex.org/W6765779288","https://openalex.org/W6779823529","https://openalex.org/W6791353385","https://openalex.org/W6795288823","https://openalex.org/W6859942556","https://openalex.org/W6864614635"],"related_works":["https://openalex.org/W4308478915","https://openalex.org/W4389049376","https://openalex.org/W1986488374","https://openalex.org/W3040456104","https://openalex.org/W2902873204","https://openalex.org/W2185750513","https://openalex.org/W2010878661","https://openalex.org/W3147379364","https://openalex.org/W2026258298","https://openalex.org/W3204639664"],"abstract_inverted_index":{"Sign":[0],"language":[1,29,40,49,62,70,91,105,147,161],"is":[2,54,112,155,181],"vital":[3],"for":[4,64],"communication":[5],"within":[6],"the":[7,55,141,169,174],"deaf":[8],"and":[9,20,66,124],"hard-of-hearing":[10],"community.":[11],"Deep":[12],"learning":[13],"techniques,":[14],"such":[15],"as":[16,129],"Generative":[17],"Adversarial":[18],"Networks":[19],"diffusion":[21,127],"models,":[22],"have":[23],"shown":[24],"promise":[25],"in":[26,163],"generating":[27],"sign":[28,39,48,61,69,90,104,146,160],"video":[30,41,71],"content.":[31],"However,":[32],"existing":[33],"methods":[34],"typically":[35],"focus":[36],"on":[37,114,120,145,168],"2D":[38],"generation,":[42],"with":[43,94],"limited":[44],"exploration":[45],"into":[46],"3D":[47,60,68,89,103],"generation.":[50],"A":[51],"prominent":[52],"issue":[53],"lack":[56],"of":[57,88,143,176],"an":[58,150],"available":[59,182],"dataset":[63,81,172,180],"training":[65],"evaluating":[67],"generation":[72,106,153],"models.":[73],"To":[74],"address":[75],"this,":[76],"we":[77],"introduce":[78],"a":[79,101,115,126,130],"new":[80],"called":[82],"How2Gesture,":[83],"which":[84],"contains":[85],"long":[86,121],"sequences":[87],"actions":[92,162],"along":[93],"detailed":[95],"text":[96,122,135,144],"translations.":[97],"We":[98],"also":[99,133],"propose":[100],"novel":[102],"paradigm,":[107],"named":[108],"3DSignDiff.":[109],"This":[110],"model":[111,128],"based":[113],"Transformer":[116],"encoder,":[117],"directly":[118],"conditioning":[119],"sequences,":[123],"uses":[125],"denoiser.":[131],"It":[132],"employs":[134],"context":[136],"enhancement":[137],"techniques":[138],"to":[139,157],"strengthen":[140],"guidance":[142],"actions.":[148],"Additionally,":[149],"advanced":[151],"joint":[152],"approach":[154],"used":[156],"generate":[158],"human":[159],"stages.":[164],"Extensive":[165],"experiments":[166],"conducted":[167],"open-source":[170],"How2Gesture":[171],"validate":[173],"superiority":[175],"our":[177],"model.":[178],"How2Geature":[179],"at":[183],"https://github.com/lifeisawar41/3Dsigndiff.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}