{"id":"https://openalex.org/W4396788058","doi":"https://doi.org/10.1145/3641519.3657422","title":"LGTM: Local-to-Global Text-Driven Human Motion Diffusion Model","display_name":"LGTM: Local-to-Global Text-Driven Human Motion Diffusion Model","publication_year":2024,"publication_date":"2024-07-12","ids":{"openalex":"https://openalex.org/W4396788058","doi":"https://doi.org/10.1145/3641519.3657422"},"language":"en","primary_location":{"id":"doi:10.1145/3641519.3657422","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3641519.3657422","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2405.03485","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114910715","display_name":"Haowen Sun","orcid":"https://orcid.org/0000-0002-6450-7746"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haowen Sun","raw_affiliation_strings":["Shenzhen University, China"],"raw_orcid":"https://orcid.org/0000-0002-6450-7746","affiliations":[{"raw_affiliation_string":"Shenzhen University, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104297793","display_name":"Ruikun Zheng","orcid":"https://orcid.org/0009-0003-8178-3886"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruikun Zheng","raw_affiliation_strings":["Shenzhen University, China"],"raw_orcid":"https://orcid.org/0009-0003-8178-3886","affiliations":[{"raw_affiliation_string":"Shenzhen University, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101795031","display_name":"Haibin Huang","orcid":"https://orcid.org/0000-0002-7787-6428"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]},{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haibin Huang","raw_affiliation_strings":["Kuaishou Technology, China","Shenzhen University, China"],"raw_orcid":"https://orcid.org/0000-0002-7787-6428","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, China","institution_ids":["https://openalex.org/I4401726859"]},{"raw_affiliation_string":"Shenzhen University, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025046851","display_name":"Chongyang Ma","orcid":"https://orcid.org/0000-0002-8243-9513"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chongyang Ma","raw_affiliation_strings":["ByteDance Inc., United States of America"],"raw_orcid":"https://orcid.org/0000-0002-8243-9513","affiliations":[{"raw_affiliation_string":"ByteDance Inc., United States of America","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034304352","display_name":"Hui Huang","orcid":"https://orcid.org/0000-0003-3212-0544"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]},{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Huang","raw_affiliation_strings":["Kuaishou Technology, China","Shenzhen University, China"],"raw_orcid":"https://orcid.org/0000-0003-3212-0544","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, China","institution_ids":["https://openalex.org/I4401726859"]},{"raw_affiliation_string":"Shenzhen University, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013892799","display_name":"Ruizhen Hu","orcid":"https://orcid.org/0000-0002-6798-0336"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruizhen Hu","raw_affiliation_strings":["Shenzhen University, China"],"raw_orcid":"https://orcid.org/0000-0002-6798-0336","affiliations":[{"raw_affiliation_string":"Shenzhen University, China","institution_ids":["https://openalex.org/I180726961"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991000294685364,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9943000078201294,"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/computer-science","display_name":"Computer science","score":0.8165534734725952},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.7482073307037354},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.7086676359176636},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.6233280301094055},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5688738226890564},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.511195957660675},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5030309557914734},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4436526894569397},{"id":"https://openalex.org/keywords/text-generation","display_name":"Text generation","score":0.4424033463001251},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.442403107881546},{"id":"https://openalex.org/keywords/motion-capture","display_name":"Motion capture","score":0.4338029623031616},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.35929542779922485},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33735957741737366},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.182369202375412}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8165534734725952},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.7482073307037354},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.7086676359176636},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.6233280301094055},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5688738226890564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.511195957660675},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5030309557914734},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4436526894569397},{"id":"https://openalex.org/C2985684807","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Text generation","level":2,"score":0.4424033463001251},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.442403107881546},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.4338029623031616},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.35929542779922485},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33735957741737366},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.182369202375412},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3641519.3657422","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3641519.3657422","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2405.03485","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.03485","pdf_url":"https://arxiv.org/pdf/2405.03485","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2405.03485","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.03485","pdf_url":"https://arxiv.org/pdf/2405.03485","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.5400000214576721,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1967554269","https://openalex.org/W2028952633","https://openalex.org/W2043554875","https://openalex.org/W2462754282","https://openalex.org/W2801567109","https://openalex.org/W2982625143","https://openalex.org/W2986708244","https://openalex.org/W3048539707","https://openalex.org/W3121370741","https://openalex.org/W3144253442","https://openalex.org/W3166396011","https://openalex.org/W3184783479","https://openalex.org/W3217476340","https://openalex.org/W4221045999","https://openalex.org/W4221082970","https://openalex.org/W4297981470","https://openalex.org/W4297989763","https://openalex.org/W4298187450","https://openalex.org/W4310832606","https://openalex.org/W4310997803","https://openalex.org/W4311802354","https://openalex.org/W4312635677","https://openalex.org/W4312933868","https://openalex.org/W4312936899","https://openalex.org/W4313145975","https://openalex.org/W4377010269","https://openalex.org/W4382334257","https://openalex.org/W4385527465","https://openalex.org/W4386065848","https://openalex.org/W4386410086","https://openalex.org/W4387610430"],"related_works":["https://openalex.org/W4310844315","https://openalex.org/W2532377291","https://openalex.org/W2000013817","https://openalex.org/W4296190881","https://openalex.org/W3169129874","https://openalex.org/W2018882065","https://openalex.org/W4210514273","https://openalex.org/W2379697716","https://openalex.org/W3113680985","https://openalex.org/W1503071992"],"abstract_inverted_index":{"In":[0],"this":[1,57,66,139],"paper,":[2],"we":[3,59],"introduce":[4],"LGTM,":[5],"a":[6,15,61,129],"novel":[7],"Local-to-Global":[8],"pipeline":[9,63],"for":[10,138],"Text-to-Motion":[11],"generation.":[12],"LGTM":[13,117],"utilizes":[14],"diffusion-based":[16],"architecture":[17],"and":[18,108,136],"aims":[19],"to":[20,50,64,75,92],"address":[21,56],"the":[22,51,104,110],"challenge":[23],"of":[24],"accurately":[25],"translating":[26],"textual":[27],"descriptions":[28,79],"into":[29,80],"semantically":[30],"coherent":[31],"human":[32,126],"motion":[33,78,90,105],"in":[34,46,121,132],"computer":[35],"animation.":[36],"Specifically,":[37],"traditional":[38],"methods":[39],"often":[40],"struggle":[41],"with":[42],"semantic":[43,96],"discrepancies,":[44],"particularly":[45],"aligning":[47],"specific":[48],"motions":[49],"correct":[52],"body":[53],"parts.":[54],"To":[55],"issue,":[58],"propose":[60],"two-stage":[62],"overcome":[65],"challenge:":[67],"it":[68],"first":[69],"employs":[70],"large":[71],"language":[72],"models":[73],"(LLMs)":[74],"decompose":[76],"global":[77],"part-specific":[81],"narratives,":[82],"which":[83],"are":[84,141],"then":[85],"processed":[86],"by":[87],"independent":[88],"body-part":[89],"encoders":[91],"ensure":[93],"precise":[94],"local":[95],"alignment.":[97],"Finally,":[98],"an":[99],"attention-based":[100],"full-body":[101],"optimizer":[102],"refines":[103],"generation":[106],"results":[107],"guarantees":[109],"overall":[111],"coherence.":[112],"Our":[113],"experiments":[114],"demonstrate":[115],"that":[116],"gains":[118],"significant":[119],"improvements":[120],"generating":[122],"locally":[123],"accurate,":[124],"semantically-aligned":[125],"motion,":[127],"marking":[128],"notable":[130],"advancement":[131],"text-to-motion":[133],"applications.":[134],"Code":[135],"data":[137],"paper":[140],"available":[142],"at":[143],"https://github.com/L-Sun/LGTM":[144]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":9}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}