{"id":"https://openalex.org/W4407093099","doi":"https://doi.org/10.1109/iccv51701.2025.01017","title":"GestureLSM: Latent Shortcut Based Co-Speech Gesture Generation with Spatial-Temporal Modeling","display_name":"GestureLSM: Latent Shortcut Based Co-Speech Gesture Generation with Spatial-Temporal Modeling","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4407093099","doi":"https://doi.org/10.1109/iccv51701.2025.01017"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01017","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01017","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2501.18898","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079498468","display_name":"Pinxin Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pinxin Liu","raw_affiliation_strings":["University of Rochester"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024413169","display_name":"Luchuan Song","orcid":"https://orcid.org/0000-0002-0126-1259"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luchuan Song","raw_affiliation_strings":["University of Rochester"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055269290","display_name":"Junhua Huang","orcid":"https://orcid.org/0009-0008-9553-0704"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junhua Huang","raw_affiliation_strings":["University of Rochester"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haiyang Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Haiyang Liu","raw_affiliation_strings":["University of Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":null,"display_name":"Chenliang Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chenliang Xu","raw_affiliation_strings":["University of Rochester"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester","institution_ids":["https://openalex.org/I5388228"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00684361,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10929","last_page":"10939"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9968000054359436,"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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9968000054359436,"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"}},{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9890999794006348,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9732000231742859,"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/gesture","display_name":"Gesture","score":0.7537006139755249},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.672587513923645},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5463424921035767},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40183037519454956}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.7537006139755249},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.672587513923645},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5463424921035767},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40183037519454956}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01017","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01017","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2501.18898","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.18898","pdf_url":"https://arxiv.org/pdf/2501.18898","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2501.18898","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2501.18898","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:2501.18898","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.18898","pdf_url":"https://arxiv.org/pdf/2501.18898","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2537963312","https://openalex.org/W2066003895","https://openalex.org/W2537762514","https://openalex.org/W2349788282","https://openalex.org/W577271088","https://openalex.org/W2120801881","https://openalex.org/W1982853263"],"abstract_inverted_index":{"Generating":[0],"full-body":[1,94],"human":[2],"gestures":[3],"based":[4],"on":[5,10,156],"speech":[6],"signals":[7],"remains":[8],"challenges":[9],"quality":[11,139],"and":[12,24,36,40,88,127,140,147,174],"speed.":[13],"Existing":[14],"approaches":[15],"model":[16,79],"different":[17],"body":[18,84],"regions":[19,85],"such":[20],"as":[21],"body,":[22],"legs":[23],"hands":[25],"separately,":[26],"which":[27],"fail":[28],"to":[29,52,101,135,164],"capture":[30],"the":[31,80,98,109,115,144],"spatial":[32,87],"interactions":[33],"between":[34],"them":[35],"result":[37],"in":[38,177],"unnatural":[39],"disjointed":[41],"movements.":[42],"Additionally,":[43],"their":[44],"autoregressive/diffusion-based":[45],"pipelines":[46],"show":[47],"slow":[48],"generation":[49],"speed":[50],"due":[51],"dozens":[53],"of":[54,82,118],"inference":[55,161],"steps.":[56],"To":[57,113],"address":[58],"these":[59],"two":[60],"challenges,":[61],"we":[62,122],"propose":[63,123],"GestureLSM,":[64],"a":[65],"flow-matching-based":[66],"approach":[67],"for":[68,91,170],"Co-Speech":[69],"Gesture":[70],"Generation":[71],"with":[72],"spatial-temporal":[73,145],"modeling.":[74],"Our":[75],"method":[76],"i)":[77],"explicitly":[78,107],"interaction":[81],"tokenized":[83],"through":[86],"temporal":[89],"attention,":[90],"generating":[92],"coherent":[93],"gestures.":[95],"ii)":[96],"introduce":[97],"flow":[99,119,149],"matching":[100,120],"enable":[102],"more":[103],"efficient":[104],"sampling":[105,132],"by":[106],"modeling":[108,146],"latent":[110,124],"velocity":[111],"space.":[112],"overcome":[114],"suboptimal":[116],"performance":[117,155],"baseline,":[121],"shortcut":[125],"learning":[126],"beta":[128],"distribution":[129],"time":[130,162],"stamp":[131],"during":[133],"training":[134],"enhance":[136],"gesture":[137],"synthesis":[138],"accelerate":[141],"inference.":[142],"Combining":[143],"improved":[148],"matching-based":[150],"framework,":[151],"GestureLSM":[152],"achieves":[153],"state-of-the-art":[154],"BEAT2":[157],"while":[158],"significantly":[159],"reducing":[160],"compared":[163],"existing":[165],"methods,":[166],"highlighting":[167],"its":[168],"potential":[169],"enhancing":[171],"digital":[172],"humans":[173],"embodied":[175],"agents":[176],"real-world":[178],"applications.":[179],"Project":[180],"Page:":[181],"https://andypinxinliu.github.io/GestureLSM":[182]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}