{"id":"https://openalex.org/W7169721105","doi":"https://doi.org/10.1186/s42492-026-00224-2","title":"Aligned and realistic latent diffusion for text-to-motion generation","display_name":"Aligned and realistic latent diffusion for text-to-motion generation","publication_year":2026,"publication_date":"2026-07-20","ids":{"openalex":"https://openalex.org/W7169721105","doi":"https://doi.org/10.1186/s42492-026-00224-2","pmid":"https://pubmed.ncbi.nlm.nih.gov/42474681"},"language":"en","primary_location":{"id":"doi:10.1186/s42492-026-00224-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s42492-026-00224-2","pdf_url":"https://link.springer.com/content/pdf/10.1186/s42492-026-00224-2.pdf","source":{"id":"https://openalex.org/S3035464634","display_name":"Visual Computing for Industry Biomedicine and Art","issn_l":"2096-496X","issn":["2096-496X","2524-4442"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Visual Computing for Industry, Biomedicine, and Art","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://link.springer.com/content/pdf/10.1186/s42492-026-00224-2.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5141150137","display_name":"Zhaowu Li","orcid":null},"institutions":[{"id":"https://openalex.org/I156292868","display_name":"Dalian University of Foreign Languages","ror":"https://ror.org/008a8z393","country_code":"CN","type":"education","lineage":["https://openalex.org/I156292868"]},{"id":"https://openalex.org/I61565387","display_name":"Dalian Minzu University","ror":"https://ror.org/02hxfx521","country_code":"CN","type":"education","lineage":["https://openalex.org/I61565387"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaowu Li","raw_affiliation_strings":["National and Local Joint Engineering Laboratory of Computer Aided Design, School of Software Engineering, Dalian University, Dalian, Liaoning, 116622, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National and Local Joint Engineering Laboratory of Computer Aided Design, School of Software Engineering, Dalian University, Dalian, Liaoning, 116622, China","institution_ids":["https://openalex.org/I156292868","https://openalex.org/I61565387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120312350","display_name":"Rui Liu","orcid":"https://orcid.org/0000-0002-5200-640X"},"institutions":[{"id":"https://openalex.org/I61565387","display_name":"Dalian Minzu University","ror":"https://ror.org/02hxfx521","country_code":"CN","type":"education","lineage":["https://openalex.org/I61565387"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Rui Liu","raw_affiliation_strings":["National and Local Joint Engineering Laboratory of Computer Aided Design, School of Software Engineering, Dalian University, Dalian, Liaoning, 116622, China. liurui@dlu.edu.cn"],"raw_orcid":"https://orcid.org/0000-0002-5200-640X","affiliations":[{"raw_affiliation_string":"National and Local Joint Engineering Laboratory of Computer Aided Design, School of Software Engineering, Dalian University, Dalian, Liaoning, 116622, China. liurui@dlu.edu.cn","institution_ids":["https://openalex.org/I61565387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020159089","display_name":"Deheng Zhu","orcid":"https://orcid.org/0000-0003-3802-4481"},"institutions":[{"id":"https://openalex.org/I156292868","display_name":"Dalian University of Foreign Languages","ror":"https://ror.org/008a8z393","country_code":"CN","type":"education","lineage":["https://openalex.org/I156292868"]},{"id":"https://openalex.org/I61565387","display_name":"Dalian Minzu University","ror":"https://ror.org/02hxfx521","country_code":"CN","type":"education","lineage":["https://openalex.org/I61565387"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deheng Zhu","raw_affiliation_strings":["National and Local Joint Engineering Laboratory of Computer Aided Design, School of Software Engineering, Dalian University, Dalian, Liaoning, 116622, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National and Local Joint Engineering Laboratory of Computer Aided Design, School of Software Engineering, Dalian University, Dalian, Liaoning, 116622, China","institution_ids":["https://openalex.org/I156292868","https://openalex.org/I61565387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141156105","display_name":"Dongsheng Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I61565387","display_name":"Dalian Minzu University","ror":"https://ror.org/02hxfx521","country_code":"CN","type":"education","lineage":["https://openalex.org/I61565387"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dongsheng Zhou","raw_affiliation_strings":["National and Local Joint Engineering Laboratory of Computer Aided Design, School of Software Engineering, Dalian University, Dalian, Liaoning, 116622, China. zhouds@dlu.edu.cn"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National and Local Joint Engineering Laboratory of Computer Aided Design, School of Software Engineering, Dalian University, Dalian, Liaoning, 116622, China. zhouds@dlu.edu.cn","institution_ids":["https://openalex.org/I61565387"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5141150499","display_name":"Xiaopeng Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaopeng Wei","raw_affiliation_strings":["School of Computer Science and Technology, Dalian University of Technology, Dalian, Liaoning, 116024, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Dalian University of Technology, Dalian, Liaoning, 116024, China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5120312350","https://openalex.org/A5141156105"],"corresponding_institution_ids":["https://openalex.org/I61565387"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8698401,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"9","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.8873999714851379,"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":0.8873999714851379,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.042399998754262924,"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":0.016100000590085983,"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/discriminator","display_name":"Discriminator","score":0.5875999927520752},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4262000024318695},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.38589999079704285},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.367900013923645},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.3628000020980835},{"id":"https://openalex.org/keywords/diffusion-process","display_name":"Diffusion process","score":0.36079999804496765},{"id":"https://openalex.org/keywords/doors","display_name":"Doors","score":0.35760000348091125},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.3513999879360199},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.34610000252723694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6868000030517578},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.5875999927520752},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4262000024318695},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4260999858379364},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4153999984264374},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.38589999079704285},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.367900013923645},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.3628000020980835},{"id":"https://openalex.org/C68710425","wikidata":"https://www.wikidata.org/wiki/Q5275442","display_name":"Diffusion process","level":3,"score":0.36079999804496765},{"id":"https://openalex.org/C125209513","wikidata":"https://www.wikidata.org/wiki/Q4037520","display_name":"Doors","level":2,"score":0.35760000348091125},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3522000014781952},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.3513999879360199},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.34610000252723694},{"id":"https://openalex.org/C77660652","wikidata":"https://www.wikidata.org/wiki/Q150971","display_name":"Computer graphics","level":2,"score":0.3384999930858612},{"id":"https://openalex.org/C55128770","wikidata":"https://www.wikidata.org/wiki/Q5275440","display_name":"Diffusion map","level":4,"score":0.33730000257492065},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.33469998836517334},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.30959999561309814},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.2727999985218048},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.2721000015735626},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25769999623298645},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1186/s42492-026-00224-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s42492-026-00224-2","pdf_url":"https://link.springer.com/content/pdf/10.1186/s42492-026-00224-2.pdf","source":{"id":"https://openalex.org/S3035464634","display_name":"Visual Computing for Industry Biomedicine and Art","issn_l":"2096-496X","issn":["2096-496X","2524-4442"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Visual Computing for Industry, Biomedicine, and Art","raw_type":"journal-article"},{"id":"pmid:42474681","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42474681","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":"Visual computing for industry, biomedicine, and art","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13385530","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13385530/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Vis Comput Ind Biomed Art","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s42492-026-00224-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s42492-026-00224-2","pdf_url":"https://link.springer.com/content/pdf/10.1186/s42492-026-00224-2.pdf","source":{"id":"https://openalex.org/S3035464634","display_name":"Visual Computing for Industry Biomedicine and Art","issn_l":"2096-496X","issn":["2096-496X","2524-4442"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Visual Computing for Industry, Biomedicine, and Art","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7399709820747375}],"awards":[{"id":"https://openalex.org/G49595074","display_name":null,"funder_award_id":"D23006","funder_id":"https://openalex.org/F4320327912","funder_display_name":"Higher Education Discipline Innovation Project"}],"funders":[{"id":"https://openalex.org/F4320327912","display_name":"Higher Education Discipline Innovation Project","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7169721105.pdf","grobid_xml":"https://content.openalex.org/works/W7169721105.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W2474702929","https://openalex.org/W2964076328","https://openalex.org/W4297981470","https://openalex.org/W4312635677","https://openalex.org/W4312936899","https://openalex.org/W4313145975","https://openalex.org/W4386065848","https://openalex.org/W4386076056","https://openalex.org/W4387963302","https://openalex.org/W4390872247","https://openalex.org/W4391305822","https://openalex.org/W4402704510","https://openalex.org/W4402754111","https://openalex.org/W4402754184","https://openalex.org/W4402951640","https://openalex.org/W4403923215","https://openalex.org/W4404600557","https://openalex.org/W4408055962","https://openalex.org/W4409917421","https://openalex.org/W4413147141","https://openalex.org/W4414198465","https://openalex.org/W7160012705","https://openalex.org/W7160025784"],"related_works":[],"abstract_inverted_index":{"Text-to-motion":[0],"generation":[1,96],"aims":[2],"to":[3,64,70,94],"synthesize":[4],"semantically":[5],"consistent":[6],"and":[7,43,68,104,136],"naturally":[8],"coherent":[9],"motion":[10,66,158,200],"sequences":[11,67,159],"from":[12],"natural":[13],"language":[14],"descriptions.":[15,79],"Given":[16],"the":[17,72,82,124,133,148,153,156,161,176,181,189,196],"continuous":[18,28,85,192],"nature":[19],"of":[20,155,183,191,198],"human":[21],"motion,":[22],"diffusion":[23,49,86,91,185,193],"models":[24,50],"operating":[25],"in":[26,39,44,77],"a":[27,110,140],"latent":[29],"space":[30],"offer":[31],"inherent":[32],"advantages":[33],"over":[34],"vector":[35],"quantization-based":[36],"methods,":[37],"particularly":[38],"avoiding":[40],"quantization":[41],"errors":[42],"modeling":[45],"quality.":[46],"However,":[47],"existing":[48],"primarily":[51],"rely":[52],"on":[53,171],"mean":[54,129],"squared":[55],"error":[56],"loss.":[57],"This":[58],"stepwise":[59],"regression":[60],"paradigm":[61],"often":[62],"leads":[63],"'over-smoothed'":[65],"struggles":[69],"capture":[71],"subtle":[73],"semantic":[74,105],"nuances":[75],"embedded":[76],"textual":[78,163],"To":[80],"realize":[81],"potential":[83,190],"for":[84],"generation,":[87],"an":[88],"enhanced":[89],"latent-space":[90,111,141],"framework":[92],"designed":[93],"elevate":[95],"capabilities":[97],"across":[98],"two":[99],"dimensions,":[100],"namely,":[101],"distribution":[102],"approximation":[103],"alignment,":[106],"is":[107,114,145],"proposed.":[108],"Specifically,":[109],"adversarial":[112,119],"discriminator":[113],"incorporated.":[115],"By":[116],"applying":[117],"decoupled":[118],"supervision,":[120],"this":[121],"component":[122],"mitigates":[123],"detail":[125],"loss":[126],"caused":[127],"by":[128],"regression,":[130],"significantly":[131],"enhancing":[132],"physical":[134],"realism":[135],"dynamic":[137],"sharpness.":[138],"Concurrently,":[139],"contrastive":[142],"alignment":[143],"strategy":[144],"introduced":[146],"during":[147],"denoising":[149],"process":[150],"that":[151,175],"reinforces":[152],"correspondence":[154],"generated":[157],"with":[160],"given":[162],"inputs":[164],"via":[165],"explicit":[166],"cross-modal":[167],"constraints.":[168],"Extensive":[169],"experiments":[170],"standard":[172],"benchmarks":[173],"demonstrate":[174],"proposed":[177],"method":[178],"effectively":[179],"addresses":[180],"limitations":[182],"conventional":[184],"models,":[186],"thus":[187],"validating":[188],"frameworks":[194],"within":[195],"domain":[197],"text-driven":[199],"synthesis.":[201]},"counts_by_year":[],"updated_date":"2026-07-25T15:57:00.446498","created_date":"2026-07-20T00:00:00"}
