{"id":"https://openalex.org/W7132844934","doi":"https://doi.org/10.1007/s44267-026-00110-8","title":"Temporal consistency-aware text-to-motion generation","display_name":"Temporal consistency-aware text-to-motion generation","publication_year":2026,"publication_date":"2026-02-28","ids":{"openalex":"https://openalex.org/W7132844934","doi":"https://doi.org/10.1007/s44267-026-00110-8"},"language":"en","primary_location":{"id":"doi:10.1007/s44267-026-00110-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44267-026-00110-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44267-026-00110-8.pdf","source":{"id":"https://openalex.org/S4387289164","display_name":"Visual Intelligence","issn_l":"2731-9008","issn":["2731-9008"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","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 Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://link.springer.com/content/pdf/10.1007/s44267-026-00110-8.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014269015","display_name":"Hongsong Wang","orcid":"https://orcid.org/0000-0002-9464-1778"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongsong Wang","raw_affiliation_strings":["Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, Nanjing, China","School of Computer Science and Engineering, Southeast University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128234585","display_name":"Wenjing Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjing Yan","raw_affiliation_strings":["Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, Nanjing, China","School of Computer Science and Engineering, Southeast University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126622668","display_name":"Qiuxia Lai","orcid":null},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qiuxia Lai","raw_affiliation_strings":["State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6872-5540","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101384253","display_name":"Xin Geng","orcid":"https://orcid.org/0000-0002-6623-0920"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Geng","raw_affiliation_strings":["Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, Nanjing, China","School of Computer Science and Engineering, Southeast University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5126622668"],"corresponding_institution_ids":["https://openalex.org/I75689368"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31441795,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"4","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":0.791100025177002,"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":0.791100025177002,"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":0.09149999916553497,"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":0.033900000154972076,"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/kinematics","display_name":"Kinematics","score":0.6065000295639038},{"id":"https://openalex.org/keywords/temporal-resolution","display_name":"Temporal resolution","score":0.5286999940872192},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5134000182151794},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4438999891281128},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.40310001373291016},{"id":"https://openalex.org/keywords/motion-capture","display_name":"Motion capture","score":0.3984000086784363},{"id":"https://openalex.org/keywords/temporal-logic","display_name":"Temporal logic","score":0.39010000228881836},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.38929998874664307}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7261999845504761},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.6065000295639038},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5559999942779541},{"id":"https://openalex.org/C119666444","wikidata":"https://www.wikidata.org/wiki/Q5977280","display_name":"Temporal resolution","level":2,"score":0.5286999940872192},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5134000182151794},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4438999891281128},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.40310001373291016},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.3984000086784363},{"id":"https://openalex.org/C25016198","wikidata":"https://www.wikidata.org/wiki/Q781833","display_name":"Temporal logic","level":2,"score":0.39010000228881836},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.38929998874664307},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3628000020980835},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.33799999952316284},{"id":"https://openalex.org/C2777489503","wikidata":"https://www.wikidata.org/wiki/Q7698936","display_name":"Temporal scales","level":2,"score":0.3239000141620636},{"id":"https://openalex.org/C77277458","wikidata":"https://www.wikidata.org/wiki/Q1969246","display_name":"Temporal database","level":2,"score":0.31630000472068787},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3086000084877014},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C162670838","wikidata":"https://www.wikidata.org/wiki/Q6057295","display_name":"Interval temporal logic","level":3,"score":0.2928999960422516},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.28529998660087585},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2624000012874603},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2603999972343445},{"id":"https://openalex.org/C4777664","wikidata":"https://www.wikidata.org/wiki/Q1536492","display_name":"Linear temporal logic","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.25429999828338623}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s44267-026-00110-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44267-026-00110-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44267-026-00110-8.pdf","source":{"id":"https://openalex.org/S4387289164","display_name":"Visual Intelligence","issn_l":"2731-9008","issn":["2731-9008"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","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 Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2602.18057","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.18057","pdf_url":"https://arxiv.org/pdf/2602.18057","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":"pmh:oai:doaj.org/article:4f837c5ae7344234a42cf33388d8d929","is_oa":false,"landing_page_url":"https://doaj.org/article/4f837c5ae7344234a42cf33388d8d929","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Visual Intelligence, Vol 4, Iss 1 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s44267-026-00110-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44267-026-00110-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44267-026-00110-8.pdf","source":{"id":"https://openalex.org/S4387289164","display_name":"Visual Intelligence","issn_l":"2731-9008","issn":["2731-9008"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","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 Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1949370213","display_name":null,"funder_award_id":"BK20230833","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G315551539","display_name":null,"funder_award_id":"62302093","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7764565150","display_name":null,"funder_award_id":"52441503","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321605","display_name":"Government of Jiangsu Province","ror":"https://ror.org/004svx814"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324856","display_name":"Southeast University","ror":"https://ror.org/04ct4d772"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7132844934.pdf","grobid_xml":"https://content.openalex.org/works/W7132844934.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W1483019628","https://openalex.org/W2474702929","https://openalex.org/W2982625143","https://openalex.org/W4297989763","https://openalex.org/W4391305822"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Text-to-Motion":[1],"(T2M)":[2],"generation":[3],"aims":[4],"to":[5,47,99],"synthesize":[6],"realistic":[7],"human":[8],"motion":[9,20,85,89],"sequences":[10],"from":[11],"natural":[12],"language":[13],"descriptions.":[14],"While":[15],"two-stage":[16],"frameworks":[17],"leveraging":[18],"discrete":[19],"representations":[21],"have":[22],"advanced":[23],"T2M":[24,66,125],"research,":[25],"they":[26],"often":[27],"neglect":[28],"cross-sequence":[29,78],"temporal":[30,35,64,72,79,119],"consistency,":[31],"i.e.,":[32],"the":[33,42,116],"shared":[34],"structures":[36],"present":[37],"across":[38],"different":[39],"instances":[40],"of":[41,118],"same":[43],"action.":[44],"This":[45],"leads":[46],"semantic":[48],"misalignments":[49],"and":[50,106,123],"physically":[51],"implausible":[52],"motions.":[53],"To":[54],"address":[55],"this":[56],"limitation,":[57],"we":[58],"propose":[59],"TCA-T2M,":[60],"a":[61,71,83,92],"framework":[62],"for":[63,77,87],"consistency-aware":[65,73],"generation.":[67,90,126],"Our":[68],"approach":[69],"introduces":[70],"spatial":[74],"VQ-VAE":[75],"(TCaS-VQ-VAE)":[76],"alignment,":[80],"coupled":[81],"with":[82],"masked":[84],"transformer":[86],"text-conditioned":[88],"Additionally,":[91],"kinematic":[93],"constraint":[94],"block":[95],"mitigates":[96],"discretization":[97],"artifacts":[98],"ensure":[100],"physical":[101],"plausibility.":[102],"Experiments":[103],"on":[104],"HumanML3D":[105],"KIT-ML":[107],"benchmarks":[108],"demonstrate":[109],"that":[110],"TCA-T2M":[111],"achieves":[112],"state-of-the-art":[113],"performance,":[114],"highlighting":[115],"importance":[117],"consistency":[120],"in":[121],"robust":[122],"coherent":[124]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-02-27T00:00:00"}