{"id":"https://openalex.org/W6910691095","doi":"https://doi.org/10.48550/arxiv.2503.13229","title":"HoloGest: Decoupled Diffusion and Motion Priors for Generating Holisticly Expressive Co-speech Gestures","display_name":"HoloGest: Decoupled Diffusion and Motion Priors for Generating Holisticly Expressive Co-speech Gestures","publication_year":2025,"publication_date":"2025-03-17","ids":{"openalex":"https://openalex.org/W6910691095","doi":"https://doi.org/10.48550/arxiv.2503.13229"},"language":"en","primary_location":{"id":"doi:10.48550/arxiv.2503.13229","doi":"https://doi.org/10.48550/arxiv.2503.13229","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.13229","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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"},"volume":null,"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2503.13229","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Cheng, Yongkang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Yongkang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5017818991","display_name":"Shaoli Huang","orcid":"https://orcid.org/0000-0002-1445-3196","observed_orcids":["https://orcid.org/0000-0002-1445-3196"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Shaoli","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":null,"has_fulltext":false,"cited_by_count":0,"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":true,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9984999895095825,"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"}},"topics":[{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9984999895095825,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.000699999975040555,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.00039999998989515007,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/co-speech-gestures","display_name":"co-speech gestures","score":0.8980000019073486},{"id":"https://openalex.org/keywords/gesture-generation","display_name":"gesture generation","score":0.7289999723434448},{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.7749999761581421},{"id":"https://openalex.org/keywords/motion-priors","display_name":"motion priors","score":0.9139999747276306},{"id":"https://openalex.org/keywords/virtual-character-animation","display_name":"virtual character animation","score":0.8090000152587891},{"id":"https://openalex.org/keywords/text-alignment","display_name":"text alignment","score":0.5929999947547913},{"id":"https://openalex.org/keywords/human-motion-dataset","display_name":"human motion dataset","score":0.5979999899864197},{"id":"https://openalex.org/keywords/finger-movements","display_name":"finger movement","score":0.515999972820282}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.8065999746322632},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.796999990940094},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6651999950408936},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6276000142097473},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5975000262260437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49149999022483826},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.4187999963760376},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.4074000120162964},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40470001101493835},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.376800000667572},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3375999927520752},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3325999975204468},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.32910001277923584},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2549000084400177},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2503.13229","doi":"https://doi.org/10.48550/arxiv.2503.13229","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.13229","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,"listed_in":[],"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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2503.13229","doi":"https://doi.org/10.48550/arxiv.2503.13229","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.13229","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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Animating":[0],"virtual":[1],"characters":[2],"with":[3,76,105,161],"holistic":[4],"co-speech":[5,62],"gestures":[6],"is":[7],"a":[8,43,73,131,165],"challenging":[9],"but":[10],"critical":[11],"task.":[12],"Previous":[13],"systems":[14],"have":[15],"primarily":[16],"focused":[17],"on":[18,49],"the":[19,33,56,94,140,153,171],"weak":[20],"correlation":[21],"between":[22,115],"audio":[23,78],"and":[24,52,80,88,108,149,155,182],"gestures,":[25],"leading":[26],"to":[27,71,170],"physically":[28],"unnatural":[29],"outcomes":[30],"that":[31],"degrade":[32],"user":[34,150,177],"experience.":[35,178],"To":[36,92],"address":[37],"this":[38],"problem,":[39],"we":[40,100,129],"introduce":[41],"HoleGest,":[42],"novel":[44],"neural":[45],"network":[46],"framework":[47],"based":[48],"decoupled":[50],"diffusion":[51],"motion":[53,69,82,87,113],"priors":[54],"for":[55,135],"automatic":[57],"generation":[58,95,122,141],"of":[59,97,142,158,167],"high-quality,":[60],"expressive":[61],"gestures.":[63],"Our":[64,179],"system":[65],"leverages":[66],"large-scale":[67],"human":[68],"datasets":[70],"learn":[72],"robust":[74],"prior":[75],"low":[77],"dependency":[79],"high":[81],"reliance,":[83],"enabling":[84,139],"stable":[85],"global":[86],"detailed":[89],"finger":[90],"movements.":[91],"improve":[93],"efficiency":[96],"diffusion-based":[98],"models,":[99],"integrate":[101],"implicit":[102],"joint":[103],"constraints":[104],"explicit":[106],"geometric":[107],"conditional":[109],"constraints,":[110],"capturing":[111],"complex":[112],"distributions":[114],"large":[116],"strides.":[117],"This":[118],"integration":[119],"significantly":[120],"enhances":[121],"speed":[123],"while":[124],"maintaining":[125],"high-quality":[126],"motion.":[127],"Furthermore,":[128],"design":[130],"shared":[132],"embedding":[133],"space":[134],"gesture-transcription":[136],"text":[137],"alignment,":[138],"semantically":[143],"correct":[144],"gesture":[145],"actions.":[146],"Extensive":[147],"experiments":[148],"feedback":[151],"demonstrate":[152],"effectiveness":[154],"potential":[156],"applications":[157],"our":[159,162],"model,":[160,181],"method":[163],"achieving":[164],"level":[166],"realism":[168],"close":[169],"ground":[172],"truth,":[173],"providing":[174],"an":[175],"immersive":[176],"code,":[180],"demo":[183],"are":[184,185],"available":[186],"at":[187],"https://cyk990422.github.io/HoloGest.github.io/.":[188]},"counts_by_year":[],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-10-10T00:00:00"}