{"id":"https://openalex.org/W7162687643","doi":"https://doi.org/10.1016/j.gmod.2026.101332","title":"Co-speech holistic 3D motion generation with style from video","display_name":"Co-speech holistic 3D motion generation with style from video","publication_year":2026,"publication_date":"2026-05-28","ids":{"openalex":"https://openalex.org/W7162687643","doi":"https://doi.org/10.1016/j.gmod.2026.101332"},"language":"en","primary_location":{"id":"doi:10.1016/j.gmod.2026.101332","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.gmod.2026.101332","pdf_url":null,"source":{"id":"https://openalex.org/S137436721","display_name":"Graphical Models","issn_l":"1524-0703","issn":["1524-0703","1524-0711"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Graphical Models","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1016/j.gmod.2026.101332","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122181889","display_name":"Yayu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yayu Zhang","raw_affiliation_strings":["Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence (Beijing Jiaotong University), Beijing, 100044, China","School of Computer Science and Technology, Beijing Jiaotong University, Beijing, 100044, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence (Beijing Jiaotong University), Beijing, 100044, China","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Jiaotong University, Beijing, 100044, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034005121","display_name":"Yu\u2010Hui Wen","orcid":"https://orcid.org/0000-0001-6195-9782"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yu-Hui Wen","raw_affiliation_strings":["Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence (Beijing Jiaotong University), Beijing, 100044, China","School of Computer Science and Technology, Beijing Jiaotong University, Beijing, 100044, China"],"raw_orcid":"https://orcid.org/0000-0001-6195-9782","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence (Beijing Jiaotong University), Beijing, 100044, China","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Jiaotong University, Beijing, 100044, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137252592","display_name":"Chenguang Li","orcid":null},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenguang Li","raw_affiliation_strings":["Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence (Beijing Jiaotong University), Beijing, 100044, China","School of Computer Science and Technology, Beijing Jiaotong University, Beijing, 100044, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence (Beijing Jiaotong University), Beijing, 100044, China","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Jiaotong University, Beijing, 100044, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137294297","display_name":"Liping Jing","orcid":null},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liping Jing","raw_affiliation_strings":["Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence (Beijing Jiaotong University), Beijing, 100044, China","School of Computer Science and Technology, Beijing Jiaotong University, Beijing, 100044, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence (Beijing Jiaotong University), Beijing, 100044, China","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Jiaotong University, Beijing, 100044, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5137303876","display_name":"Jian Yu","orcid":"https://orcid.org/0000-0002-9965-4703"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Yu","raw_affiliation_strings":["Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence (Beijing Jiaotong University), Beijing, 100044, China","School of Computer Science and Technology, Beijing Jiaotong University, Beijing, 100044, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence (Beijing Jiaotong University), Beijing, 100044, China","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Jiaotong University, Beijing, 100044, China","institution_ids":["https://openalex.org/I21193070"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5034005121"],"corresponding_institution_ids":["https://openalex.org/I21193070"],"apc_list":{"value":1750,"currency":"USD","value_usd":1750},"apc_paid":{"value":1750,"currency":"USD","value_usd":1750},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.67368796,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"146","issue":null,"first_page":"101332","last_page":"101332"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.5214999914169312,"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"}},"topics":[{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.5214999914169312,"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/T12290","display_name":"Human Motion and Animation","score":0.1770000010728836,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.050999999046325684,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social 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/motion","display_name":"Motion (physics)","score":0.4772000014781952},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.3443000018596649},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.3179999887943268},{"id":"https://openalex.org/keywords/match-moving","display_name":"Match moving","score":0.29429998993873596},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.28369998931884766}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5666999816894531},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5271999835968018},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5257999897003174},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4772000014781952},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.3443000018596649},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3179999887943268},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.30570000410079956},{"id":"https://openalex.org/C95020103","wikidata":"https://www.wikidata.org/wiki/Q1813492","display_name":"Match moving","level":3,"score":0.29429998993873596},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.27489998936653137},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25859999656677246}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.gmod.2026.101332","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.gmod.2026.101332","pdf_url":null,"source":{"id":"https://openalex.org/S137436721","display_name":"Graphical Models","issn_l":"1524-0703","issn":["1524-0703","1524-0711"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Graphical Models","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.gmod.2026.101332","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.gmod.2026.101332","pdf_url":null,"source":{"id":"https://openalex.org/S137436721","display_name":"Graphical Models","issn_l":"1524-0703","issn":["1524-0703","1524-0711"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Graphical Models","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335843","display_name":"Beijing Science and Technology Planning Project","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2008208299","https://openalex.org/W2052890918","https://openalex.org/W2235920218","https://openalex.org/W2603777577","https://openalex.org/W2766709201","https://openalex.org/W2922298118","https://openalex.org/W2949924544","https://openalex.org/W2962795401","https://openalex.org/W2978956737","https://openalex.org/W3024902055","https://openalex.org/W3083173864","https://openalex.org/W3096831136","https://openalex.org/W3198131199","https://openalex.org/W3204221554","https://openalex.org/W4200630629","https://openalex.org/W4226047505","https://openalex.org/W4230429791","https://openalex.org/W4304080460","https://openalex.org/W4312974539","https://openalex.org/W4367622621","https://openalex.org/W4377010269","https://openalex.org/W4385284180","https://openalex.org/W4386066602","https://openalex.org/W4386075984","https://openalex.org/W4386076103","https://openalex.org/W4386076250","https://openalex.org/W4400818936","https://openalex.org/W4402703119","https://openalex.org/W4402704505","https://openalex.org/W4402727140","https://openalex.org/W4402753998","https://openalex.org/W4402754111","https://openalex.org/W4403792047","https://openalex.org/W4412588114","https://openalex.org/W4412590231","https://openalex.org/W4412673604","https://openalex.org/W4415537146","https://openalex.org/W7160037713","https://openalex.org/W7160112474"],"related_works":[],"abstract_inverted_index":{"Speech-driven":[0],"3D":[1,104,123],"motion":[2,24,39,89,150],"generation":[3,40],"has":[4],"garnered":[5],"increasing":[6],"research":[7],"attention.":[8],"However,":[9],"it":[10],"faces":[11],"significant":[12],"challenges":[13],"in":[14,107,138],"achieving":[15],"style":[16,25,44,67,73,78,114],"controllability,":[17],"primarily":[18],"due":[19],"to":[20,57,88,122],"the":[21],"scarcity":[22],"of":[23],"annotations.":[26],"To":[27],"address":[28],"this,":[29],"we":[30,69,95],"propose":[31],"a":[32,71,97,108,145],"novel":[33],"diffusion-based":[34],"framework":[35],"for":[36,148],"co-speech":[37],"holistic":[38],"that":[41,75,100,131],"enables":[42],"example-based":[43],"control":[45],"from":[46,80,116],"videos.":[47],"Our":[48],"approach":[49,134],"integrates":[50],"hierarchical":[51],"speech":[52],"encoding":[53],"with":[54],"rhythm-aware":[55],"denoising":[56],"produce":[58],"natural":[59],"and":[60,63,103,119,127,141],"synchronized":[61],"gestures":[62],"expressions.":[64],"For":[65],"effective":[66],"guidance,":[68],"introduce":[70],"contrastive":[72],"encoder":[74],"captures":[76],"discriminative":[77],"representations":[79],"reference":[81],"clips":[82],"without":[83],"explicit":[84],"labeling,":[85],"enabling":[86],"generalization":[87],"styles":[90],"unseen":[91],"during":[92],"training.":[93],"Furthermore,":[94],"design":[96],"neural":[98],"mapper":[99],"aligns":[101],"2D":[102],"gesture":[105],"features":[106],"shared":[109],"embedding":[110],"space,":[111],"facilitating":[112],"direct":[113],"extraction":[115],"in-the-wild":[117],"videos":[118],"seamless":[120],"transfer":[121],"motion.":[124],"Extensive":[125],"experiments":[126],"user":[128],"studies":[129],"show":[130],"our":[132],"proposed":[133],"achieves":[135],"state-of-the-art":[136],"performance":[137],"both":[139],"qualitative":[140],"quantitative":[142],"evaluations,":[143],"offering":[144],"flexible":[146],"solution":[147],"controllable":[149],"generation.":[151]},"counts_by_year":[],"updated_date":"2026-05-30T06:14:24.967023","created_date":"2026-05-29T00:00:00"}