{"id":"https://openalex.org/W4416332555","doi":"https://doi.org/10.1145/3776750","title":"SignMask: Structure-aware Masked Modeling for Holistic 3D Sign Language Production","display_name":"SignMask: Structure-aware Masked Modeling for Holistic 3D Sign Language Production","publication_year":2025,"publication_date":"2025-11-18","ids":{"openalex":"https://openalex.org/W4416332555","doi":"https://doi.org/10.1145/3776750"},"language":"en","primary_location":{"id":"doi:10.1145/3776750","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3776750","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"type":"article","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":null,"display_name":"Yibo Xia","orcid":"https://orcid.org/0009-0004-1743-817X"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yibo Xia","raw_affiliation_strings":["Beihang University, Beijing, China and Zhongguancun Academy, Beijing, China","Beihang University, China"],"raw_orcid":"https://orcid.org/0009-0004-1743-817X","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China and Zhongguancun Academy, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Beihang University, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120361369","display_name":"Qihui Zhan","orcid":"https://orcid.org/0009-0001-1644-7064"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qihui Zhan","raw_affiliation_strings":["Beihang University, Beijing, China","Beihang University, China"],"raw_orcid":"https://orcid.org/0009-0001-1644-7064","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Beihang University, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072050541","display_name":"Xiaoyan Luo","orcid":"https://orcid.org/0000-0002-7256-4329"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyan Luo","raw_affiliation_strings":["Beihang University, Beijing, China","Beihang University, China"],"raw_orcid":"https://orcid.org/0000-0002-7256-4329","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Beihang University, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107559896","display_name":"Xiaofeng Shi","orcid":"https://orcid.org/0000-0002-8823-6119"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofeng Shi","raw_affiliation_strings":["Beihang University, Beijing, China","Beihang University, China"],"raw_orcid":"https://orcid.org/0000-0002-8823-6119","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Beihang University, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100398953","display_name":"Yunhong Wang","orcid":"https://orcid.org/0000-0001-8001-2703"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunhong Wang","raw_affiliation_strings":["Beihang University, Beijing, China","Beihang University, China"],"raw_orcid":"https://orcid.org/0000-0001-8001-2703","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Beihang University, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":1.0021,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.80749501,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"22","issue":"1","first_page":"1","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9578999876976013,"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":0.9578999876976013,"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/T12290","display_name":"Human Motion and Animation","score":0.010700000450015068,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.0052999998442828655,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.7483999729156494},{"id":"https://openalex.org/keywords/sign-language","display_name":"Sign language","score":0.7276999950408936},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.5232999920845032},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4821000099182129},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.4390000104904175},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4374000132083893},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.3635999858379364},{"id":"https://openalex.org/keywords/semantic-mapping","display_name":"Semantic mapping","score":0.35679998993873596}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8971999883651733},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7483999729156494},{"id":"https://openalex.org/C522192633","wikidata":"https://www.wikidata.org/wiki/Q34228","display_name":"Sign language","level":2,"score":0.7276999950408936},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.5232999920845032},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4821000099182129},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4796999990940094},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44339999556541443},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.4390000104904175},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4374000132083893},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.3635999858379364},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.35679998993873596},{"id":"https://openalex.org/C139676723","wikidata":"https://www.wikidata.org/wiki/Q1193832","display_name":"Sign (mathematics)","level":2,"score":0.3537999987602234},{"id":"https://openalex.org/C2777365542","wikidata":"https://www.wikidata.org/wiki/Q83090","display_name":"Avatar","level":2,"score":0.353300005197525},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.3452000021934509},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3294000029563904},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3237000107765198},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C2776264592","wikidata":"https://www.wikidata.org/wiki/Q463837","display_name":"Language production","level":3,"score":0.29170000553131104},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.26260000467300415},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.2535000145435333},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3776750","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3776750","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2024536104","https://openalex.org/W2108325777","https://openalex.org/W2135431835","https://openalex.org/W2799020610","https://openalex.org/W2949924544","https://openalex.org/W2978956737","https://openalex.org/W2997573805","https://openalex.org/W3034765865","https://openalex.org/W3083173864","https://openalex.org/W3102427165","https://openalex.org/W3168702146","https://openalex.org/W3173290664","https://openalex.org/W3198131199","https://openalex.org/W3215615641","https://openalex.org/W4303448003","https://openalex.org/W4304014869","https://openalex.org/W4313021454","https://openalex.org/W4377010269","https://openalex.org/W4385284180","https://openalex.org/W4386075984","https://openalex.org/W4386083180","https://openalex.org/W4390872297","https://openalex.org/W4402703119","https://openalex.org/W4402704505","https://openalex.org/W4402727140","https://openalex.org/W4402753998","https://openalex.org/W4402754111","https://openalex.org/W4402754184","https://openalex.org/W4403792047","https://openalex.org/W4404966690","https://openalex.org/W4411244490","https://openalex.org/W4413146558"],"related_works":[],"abstract_inverted_index":{"Sign":[0],"Language":[1],"Production":[2],"(SLP)":[3],"aims":[4],"to":[5,51,68,136,171,194,249],"translate":[6],"spoken":[7,60],"textual":[8,178],"languages":[9],"into":[10],"sign":[11,56,114,201,207,236,256,265],"language":[12,257,266],"sequences,":[13,229],"which":[14,35],"can":[15],"significantly":[16],"bridge":[17],"the":[18,79,84,137,144,221,242],"communication":[19],"gap":[20],"for":[21],"deaf":[22],"and":[23,39,77,105,124,141,156,190,203,208,217,233,262],"hard-of-hearing":[24],"individuals.":[25],"Most":[26],"previous":[27],"SLP":[28,49,65,251],"methods":[29,66,252],"typically":[30],"rely":[31],"on":[32,161],"skeleton-based":[33],"data,":[34],"hinders":[36],"their":[37],"realism":[38],"expressive":[40,47],"capacity.":[41],"In":[42],"this":[43],"work,":[44],"we":[45,91,165],"address":[46],"3D":[48,54,64,75,131,235],"tasks":[50],"generate":[52],"high-quality":[53,261],"holistic":[55,113],"motions":[57],"driven":[58],"by":[59,177],"language.":[61],"However,":[62],"existing":[63,250],"struggle":[67],"accurately":[69],"capture":[70,196],"spatial":[71,102,154],"relationships":[72,199],"within":[73],"intricate":[74],"structures":[76],"overlook":[78],"alignment":[80],"of":[81,122,149,245],"semantics":[82],"at":[83],"word":[85],"level.":[86],"To":[87],"overcome":[88],"these":[89,162],"limitations,":[90],"propose":[92],"SignMask,":[93],"a":[94,111,167,184],"novel":[95],"generative":[96],"masked":[97,173],"modeling":[98],"framework":[99],"that":[100,117],"enhances":[101],"structure":[103],"awareness":[104,155],"semantic":[106,139,151,158,204],"understanding.":[107],"We":[108],"first":[109],"design":[110],"structural":[112],"motion":[115,223],"tokenizer":[116,128],"hierarchically":[118],"learns":[119],"discrete":[120],"tokens":[121,202,224],"body":[123],"hand":[125],"movements.":[126],"This":[127],"adaptively":[129],"aggregates":[130],"SMPL-X":[132],"pose":[133,147],"features":[134,148],"corresponding":[135],"same":[138],"parts":[140],"dynamically":[142],"adjusts":[143],"weights":[145],"between":[146,206],"different":[150],"parts,":[152],"enhancing":[153],"ensuring":[157],"consistency.":[159],"Building":[160],"tokenized":[163],"representations,":[164],"introduce":[166],"specialized":[168],"Sign-M":[169,181],"Transformer":[170,182],"learn":[172],"token":[174,228],"prediction":[175],"guided":[176],"input.":[179],"Our":[180],"employs":[183],"hierarchical":[185],"masking":[186],"strategy,":[187],"alongside":[188],"spatio-temporal":[189,198],"cross-modal":[191],"attention":[192],"mechanisms,":[193],"effectively":[195],"complex":[197],"among":[200],"dependencies":[205],"text":[209],"tokens.":[210],"During":[211],"inference,":[212],"our":[213,246],"SignMask":[214],"model":[215],"parallelly":[216],"iteratively":[218],"fills":[219],"up":[220],"missing":[222],"starting":[225],"from":[226],"full-masked":[227],"therefore":[230],"achieving":[231],"high-fidelity":[232],"efficient":[234],"avatar":[237],"generation.":[238],"Extensive":[239],"experiments":[240],"demonstrate":[241],"superior":[243],"performance":[244],"approach":[247],"compared":[248],"across":[253],"various":[254],"lingual":[255],"datasets":[258],"in":[259],"generating":[260],"semantically":[263],"consistent":[264],"motions.":[267]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-11-18T00:00:00"}