{"id":"https://openalex.org/W7138434794","doi":"https://doi.org/10.1609/aaai.v40i12.37992","title":"X-MoGen: Unified Motion Generation Across Humans and Animals","display_name":"X-MoGen: Unified Motion Generation Across Humans and Animals","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138434794","doi":"https://doi.org/10.1609/aaai.v40i12.37992"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i12.37992","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i12.37992","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37992/41954","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37992/41954","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129718928","display_name":"Xuan Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xuan Wang","raw_affiliation_strings":["Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129694716","display_name":"Kai Ruan","orcid":null},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Ruan","raw_affiliation_strings":["Renmin University of China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129707316","display_name":"Liyang Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liyang Qian","raw_affiliation_strings":["Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126228081","display_name":"Guo Zhi Zhi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guo Zhi Zhi","raw_affiliation_strings":["Institute of Artificial Intelligence (TeleAI), China Telecom"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI), China Telecom","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129694173","display_name":"Chang Su","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chang Su","raw_affiliation_strings":["Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129725773","display_name":"Gaoang Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gaoang Wang","raw_affiliation_strings":["Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5129718928"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.74,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"12","first_page":"10234","last_page":"10242"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.8587999939918518,"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":0.8587999939918518,"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":0.03440000116825104,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.026399999856948853,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.7181000113487244},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.6858000159263611},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5192000269889832},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4871000051498413},{"id":"https://openalex.org/keywords/human-motion","display_name":"Human motion","score":0.4832000136375427},{"id":"https://openalex.org/keywords/motion-capture","display_name":"Motion capture","score":0.48249998688697815},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.47189998626708984},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.44620001316070557}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7181000113487244},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6858000159263611},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.650600016117096},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6294999718666077},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5192000269889832},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4871000051498413},{"id":"https://openalex.org/C2986578859","wikidata":"https://www.wikidata.org/wiki/Q657632","display_name":"Human motion","level":3,"score":0.4832000136375427},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.48249998688697815},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.47189998626708984},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.44620001316070557},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4108000099658966},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.3962000012397766},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.3790000081062317},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.351500004529953},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.3248000144958496},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C2777036941","wikidata":"https://www.wikidata.org/wiki/Q6917771","display_name":"Motion analysis","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26030001044273376},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2590999901294708}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i12.37992","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i12.37992","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37992/41954","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i12.37992","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i12.37992","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37992/41954","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land","score":0.4665243923664093}],"awards":[{"id":"https://openalex.org/G4985030622","display_name":null,"funder_award_id":"LZ24F030005","funder_id":"https://openalex.org/F4320338464","funder_display_name":"Natural Science Foundation of Zhejiang Province"},{"id":"https://openalex.org/G8575741351","display_name":null,"funder_award_id":"2024YFHZ0001","funder_id":"https://openalex.org/F4320322922","funder_display_name":"Department of Science and Technology of Sichuan Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322922","display_name":"Department of Science and Technology of Sichuan Province","ror":"https://ror.org/04323m874"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null},{"id":"https://openalex.org/F4320338464","display_name":"Natural Science Foundation of Zhejiang Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138434794.pdf","grobid_xml":"https://content.openalex.org/works/W7138434794.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Text-driven":[0],"motion":[1,26,54,69,95,112,116,151],"generation":[2,70],"has":[3],"attracted":[4],"increasing":[5],"attention":[6],"due":[7],"to":[8,114,130],"its":[9],"broad":[10],"applications":[11],"in":[12],"virtual":[13],"reality,":[14],"animation,":[15],"and":[16,24,40,74,149,156,180],"robotics.":[17],"While":[18],"existing":[19],"methods":[20,176],"typically":[21],"model":[22],"human":[23,155],"animal":[25,157],"separately,":[27],"a":[28,37,49,78,82,97,124,143,160],"joint":[29,165],"cross-species":[30,67],"approach":[31],"offers":[32],"key":[33,50],"advantages,":[34],"such":[35],"as":[36],"unified":[38,64,138],"representation":[39],"improved":[41],"generalization.":[42],"However,":[43],"morphological":[44,103,125],"differences":[45],"across":[46,134],"species":[47,148],"remain":[48],"challenge,":[51],"often":[52],"compromising":[53],"plausibility.":[55],"To":[56,136],"address":[57],"this,":[58],"we":[59,109,140],"propose":[60],"X-MoGen,":[61],"the":[62,106],"first":[63],"framework":[65],"for":[66,164],"text-driven":[68],"covering":[71],"both":[72,178],"humans":[73],"animals.":[75],"X-MoGen":[76,173],"adopts":[77],"two-stage":[79],"architecture.":[80],"First,":[81],"conditional":[83],"graph":[84],"variational":[85],"autoencoder":[86,93],"learns":[87],"canonical":[88],"T-pose":[89],"priors,":[90],"while":[91],"an":[92],"encodes":[94],"into":[96],"shared":[98,161],"latent":[99],"space":[100],"regularized":[101],"by":[102],"loss.":[104],"In":[105],"second":[107],"stage,":[108],"perform":[110],"masked":[111],"modeling":[113],"generate":[115],"embeddings":[117],"conditioned":[118],"on":[119,169,177],"textual":[120],"descriptions.":[121],"During":[122],"training,":[123],"consistency":[126],"module":[127],"is":[128],"employed":[129],"promote":[131],"skeletal":[132,162],"plausibility":[133],"species.":[135,182],"support":[137],"modeling,":[139],"construct":[141],"UniMo4D,":[142],"large-scale":[144],"dataset":[145],"of":[146],"115":[147],"119k":[150],"sequences,":[152],"which":[153],"integrates":[154],"motions":[158],"under":[159],"topology":[163],"training.":[166],"Extensive":[167],"experiments":[168],"UniMo4D":[170],"demonstrate":[171],"that":[172],"outperforms":[174],"state-of-the-art":[175],"seen":[179],"unseen":[181]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2026-03-18T00:00:00"}