{"id":"https://openalex.org/W4390873438","doi":"https://doi.org/10.1109/tvcg.2024.3352002","title":"GUESS: GradUally Enriching SyntheSis for Text-Driven Human Motion Generation","display_name":"GUESS: GradUally Enriching SyntheSis for Text-Driven Human Motion Generation","publication_year":2024,"publication_date":"2024-01-15","ids":{"openalex":"https://openalex.org/W4390873438","doi":"https://doi.org/10.1109/tvcg.2024.3352002","pmid":"https://pubmed.ncbi.nlm.nih.gov/38224502"},"language":"en","primary_location":{"id":"doi:10.1109/tvcg.2024.3352002","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2024.3352002","pdf_url":null,"source":{"id":"https://openalex.org/S84775595","display_name":"IEEE Transactions on Visualization and Computer Graphics","issn_l":"1077-2626","issn":["1077-2626","1941-0506","2160-9306"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Visualization and Computer Graphics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009374796","display_name":"Xuehao Gao","orcid":"https://orcid.org/0000-0003-3168-5770"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuehao Gao","raw_affiliation_strings":["Xi’an Jiaotong University, Xi’an, China","National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0003-3168-5770","affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100397450","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0001-8687-4427"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":["Xi’an Jiaotong University, Xi’an, China","School of Electronic and Information Engineering, Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0001-8687-4427","affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"School of Electronic and Information Engineering, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060590214","display_name":"Zhenyu Xie","orcid":"https://orcid.org/0000-0001-9207-1014"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenyu Xie","raw_affiliation_strings":["School of Intelligent Systems Engineering, Sun Yat-sen University, Guangzhou, China","School of Intelligent Systems Engineering, Sun Yat-sen University, GuangZhou, China"],"raw_orcid":"https://orcid.org/0000-0001-9207-1014","affiliations":[{"raw_affiliation_string":"School of Intelligent Systems Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Intelligent Systems Engineering, Sun Yat-sen University, GuangZhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044668212","display_name":"Shaoyi Du","orcid":"https://orcid.org/0000-0002-7092-0596"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaoyi Du","raw_affiliation_strings":["Xi’an Jiaotong University, Xi’an, China","National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-7092-0596","affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038814111","display_name":"Zhongqian Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongqian Sun","raw_affiliation_strings":["Tencent AI Lab., Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-1812-6085","affiliations":[{"raw_affiliation_string":"Tencent AI Lab., Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100741279","display_name":"Yang Wu","orcid":"https://orcid.org/0000-0001-8010-6857"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Wu","raw_affiliation_strings":["Tencent AI Lab., Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-8010-6857","affiliations":[{"raw_affiliation_string":"Tencent AI Lab., Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.4308,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.96227279,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"30","issue":"12","first_page":"7518","last_page":"7530"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9976000189781189,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.984000027179718,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7493846416473389},{"id":"https://openalex.org/keywords/text-generation","display_name":"Text generation","score":0.5943719148635864},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.5305410027503967},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5081791877746582},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5037335753440857},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4934922456741333},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4583214819431305},{"id":"https://openalex.org/keywords/human-motion","display_name":"Human motion","score":0.4323671758174896},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.37410804629325867},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3303226828575134}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7493846416473389},{"id":"https://openalex.org/C2985684807","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Text generation","level":2,"score":0.5943719148635864},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.5305410027503967},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5081791877746582},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5037335753440857},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4934922456741333},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4583214819431305},{"id":"https://openalex.org/C2986578859","wikidata":"https://www.wikidata.org/wiki/Q657632","display_name":"Human motion","level":3,"score":0.4323671758174896},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37410804629325867},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3303226828575134}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003196","descriptor_name":"Computer Graphics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003196","descriptor_name":"Computer Graphics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003196","descriptor_name":"Computer Graphics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D009068","descriptor_name":"Movement","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D009068","descriptor_name":"Movement","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D009068","descriptor_name":"Movement","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/tvcg.2024.3352002","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2024.3352002","pdf_url":null,"source":{"id":"https://openalex.org/S84775595","display_name":"IEEE Transactions on Visualization and Computer Graphics","issn_l":"1077-2626","issn":["1077-2626","1941-0506","2160-9306"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Visualization and Computer Graphics","raw_type":"journal-article"},{"id":"pmid:38224502","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38224502","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on visualization and computer graphics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.4099999964237213}],"awards":[{"id":"https://openalex.org/G6295026556","display_name":null,"funder_award_id":"2018AAA0102500","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1487977235","https://openalex.org/W2080489767","https://openalex.org/W2113135938","https://openalex.org/W2474702929","https://openalex.org/W2497597915","https://openalex.org/W2617807999","https://openalex.org/W2801810226","https://openalex.org/W2809440348","https://openalex.org/W2897682634","https://openalex.org/W2963092440","https://openalex.org/W2966745778","https://openalex.org/W2971625077","https://openalex.org/W2971856312","https://openalex.org/W2982625143","https://openalex.org/W3124346429","https://openalex.org/W3144253442","https://openalex.org/W3153832461","https://openalex.org/W3204221554","https://openalex.org/W3216650889","https://openalex.org/W4206861281","https://openalex.org/W4236011499","https://openalex.org/W4288079574","https://openalex.org/W4297981470","https://openalex.org/W4312635677","https://openalex.org/W4312933868","https://openalex.org/W4312936899","https://openalex.org/W4312995056","https://openalex.org/W4379983649","https://openalex.org/W4386065848","https://openalex.org/W4386076405","https://openalex.org/W4390872595","https://openalex.org/W6679045638","https://openalex.org/W6756726438","https://openalex.org/W6778946027","https://openalex.org/W6791353385","https://openalex.org/W6797359156","https://openalex.org/W6809885388","https://openalex.org/W6838639034","https://openalex.org/W6844223692","https://openalex.org/W6845281891","https://openalex.org/W6849037083"],"related_works":["https://openalex.org/W2035558540","https://openalex.org/W2529580585","https://openalex.org/W2804584315","https://openalex.org/W2004712313","https://openalex.org/W2020678219","https://openalex.org/W2167757589","https://openalex.org/W2332110715","https://openalex.org/W2988011613","https://openalex.org/W2806036343","https://openalex.org/W2079653927"],"abstract_inverted_index":{"In":[0],"this":[1],"article,":[2],"we":[3,162],"propose":[4],"a":[5,18,55,64,115,120,136,141],"novel":[6],"cascaded":[7,121],"diffusion-based":[8],"generative":[9],"framework":[10,118],"for":[11],"text-driven":[12,100],"human":[13,65,82,101,132],"motion":[14,83,95,102,133,149,187],"synthesis,":[15],"which":[16],"exploits":[17],"strategy":[19,29],"named":[20],"GradUally":[21],"Enriching":[22],"SyntheSis":[23],"(GUESS":[24],"as":[25],"its":[26],"abbreviation).":[27],"The":[28,98],"sets":[30],"up":[31],"generation":[32,117,191],"objectives":[33],"by":[34,205],"grouping":[35],"body":[36],"joints":[37],"of":[38,50,143,179,210],"detailed":[39],"skeletons":[40,71],"in":[41,189,208],"close":[42],"semantic":[43],"proximity":[44],"together":[45],"and":[46,69,86,89,112,156,184,213],"then":[47,106],"replacing":[48],"each":[49],"such":[51],"joint":[52],"group":[53],"with":[54,114,119,166],"single":[56],"body-part":[57],"node.":[58],"Such":[59],"an":[60,125],"operation":[61],"recursively":[62],"abstracts":[63],"pose":[66],"to":[67,173],"coarser":[68,70],"at":[72],"multiple":[73,109],"granularity":[74],"levels.":[75],"With":[76],"gradually":[77,146],"increasing":[78],"the":[79,93,130,148,153,157,167,176,180],"abstraction":[80,110],"level,":[81],"becomes":[84],"more":[85,87],"concise":[88],"stable,":[90],"significantly":[91],"benefiting":[92],"cross-modal":[94],"synthesis":[96,103],"task.":[97],"whole":[99],"problem":[104],"is":[105],"divided":[107],"into":[108],"levels":[111],"solved":[113],"multi-stage":[116],"latent":[122],"diffusion":[123],"model:":[124],"initial":[126],"generator":[127],"first":[128],"generates":[129],"coarsest":[131],"guess":[134],"from":[135],"given":[137,181],"text":[138],"description;":[139],"then,":[140],"series":[142],"successive":[144],"generators":[145],"enrich":[147],"details":[150],"based":[151],"on":[152,195],"textual":[154,182],"description":[155],"previous":[158],"synthesized":[159,185],"results.":[160],"Notably,":[161],"further":[163],"integrate":[164],"GUESS":[165,200],"proposed":[168],"dynamic":[169],"multi-condition":[170],"fusion":[171],"mechanism":[172],"dynamically":[174],"balance":[175],"cooperative":[177],"effects":[178],"condition":[183],"coarse":[186],"prompt":[188],"different":[190],"stages.":[192],"Extensive":[193],"experiments":[194],"large-scale":[196],"datasets":[197],"verify":[198],"that":[199],"outperforms":[201],"existing":[202],"state-of-the-art":[203],"methods":[204],"large":[206],"margins":[207],"terms":[209],"accuracy,":[211],"realisticness,":[212],"diversity.":[214]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-13T07:31:44.756512","created_date":"2025-10-10T00:00:00"}