{"id":"https://openalex.org/W4416105439","doi":"https://doi.org/10.1109/iccv51701.2025.01239","title":"Go to Zero: Towards Zero-Shot Motion Generation with Million-Scale Data","display_name":"Go to Zero: Towards Zero-Shot Motion Generation with Million-Scale Data","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416105439","doi":"https://doi.org/10.1109/iccv51701.2025.01239"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01239","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01239","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.07095","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102825365","display_name":"Ke Fan","orcid":"https://orcid.org/0000-0002-4841-1138"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Fan","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028455158","display_name":"Shunlin Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Shunlin Lu","raw_affiliation_strings":["CUHK,Shenzhen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CUHK,Shenzhen","institution_ids":["https://openalex.org/I4210116924","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112328810","display_name":"Minyue Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minyue Dai","raw_affiliation_strings":["Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010529350","display_name":"Runyi Yu","orcid":"https://orcid.org/0000-0003-1925-8442"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Runyi Yu","raw_affiliation_strings":["HKUST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HKUST","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112595869","display_name":"Linqi Xiao","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":"Lixing Xiao","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059487131","display_name":"Zhiyang Dou","orcid":"https://orcid.org/0000-0003-0186-8269"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhiyang Dou","raw_affiliation_strings":["HKU"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HKU","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006558591","display_name":"Junting Dong","orcid":"https://orcid.org/0000-0003-0050-3989"},"institutions":[{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junting Dong","raw_affiliation_strings":["Shanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4210122302","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084218062","display_name":"Lizhuang Ma","orcid":"https://orcid.org/0000-0003-1653-4341"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lizhuang Ma","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008376498","display_name":"Jingbo Wang","orcid":"https://orcid.org/0000-0002-6316-2678"},"institutions":[{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingbo Wang","raw_affiliation_strings":["Shanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4210122302","https://openalex.org/I4391012619"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.36896017,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13336","last_page":"13348"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.5403000116348267,"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":0.5403000116348267,"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":0.18639999628067017,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.1340000033378601,"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/generalization","display_name":"Generalization","score":0.8119000196456909},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.720300018787384},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6157000064849854},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6122000217437744},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5831999778747559},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.48969998955726624},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.48820000886917114},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.45980000495910645}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.8119000196456909},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7390999794006348},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.720300018787384},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6157000064849854},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6122000217437744},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5910000205039978},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5831999778747559},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5446000099182129},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.48969998955726624},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.48820000886917114},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.45980000495910645},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4593999981880188},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3815999925136566},{"id":"https://openalex.org/C2986578859","wikidata":"https://www.wikidata.org/wiki/Q657632","display_name":"Human motion","level":3,"score":0.3718000054359436},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3158999979496002},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2939000129699707},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.26980000734329224},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.26980000734329224},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2590000033378601},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2513999938964844},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.2506999969482422}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/iccv51701.2025.01239","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01239","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.07095","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.07095","pdf_url":"https://arxiv.org/pdf/2507.07095","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-170708","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-170708","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"},{"id":"doi:10.48550/arxiv.2507.07095","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.07095","pdf_url":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.07095","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.07095","pdf_url":"https://arxiv.org/pdf/2507.07095","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1914323026","display_name":null,"funder_award_id":"2022ZD0160201","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G3356995396","display_name":null,"funder_award_id":"YG2023QNA35","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G4127385765","display_name":null,"funder_award_id":"72192821,62472282","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/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Generating":[0],"diverse":[1],"and":[2,14,25,103,116,146,159],"natural":[3],"human":[4,107,169],"motion":[5,108,120,133,170],"sequences":[6],"based":[7],"on":[8,150],"textual":[9],"descriptions":[10],"constitutes":[11],"a":[12,55,81,136,164],"fundamental":[13],"challenging":[15],"research":[16],"area":[17],"within":[18],"the":[19,45,52,60,88,126],"domains":[20],"of":[21,48,54,62,91],"computer":[22],"vision,":[23],"graphics,":[24],"robotics.":[26],"Despite":[27],"significant":[28,165],"advancements":[29],"in":[30],"this":[31,63,73,94],"field,":[32],"current":[33],"methodologies":[34],"often":[35],"face":[36],"challenges":[37],"regarding":[38],"zero-shot":[39,132,168],"generalization":[40,89,156],"capabilities,":[41],"largely":[42],"attributable":[43],"to":[44,67,77,86,110,143,157],"limited":[46],"size":[47],"training":[49],"datasets.":[50],"Moreover,":[51],"lack":[53],"comprehensive":[56,128],"evaluation":[57],"framework":[58],"impedes":[59],"advancement":[61],"task":[64],"by":[65],"failing":[66],"identify":[68],"directions":[69],"for":[70,130],"improvement.":[71],"In":[72],"work,":[74],"we":[75,97,123,139],"aim":[76],"push":[78],"text-to-motion":[79],"into":[80],"new":[82],"era,":[83],"that":[84],"is,":[85],"achieve":[87],"ability":[90],"zero-shot.":[92],"To":[93],"end,":[95],"firstly,":[96],"develop":[98],"an":[99],"efficient":[100],"annotation":[101],"pipeline":[102],"introduce":[104],"MotionMillion-the":[105],"largest":[106],"dataset":[109],"date,":[111],"featuring":[112],"over":[113],"2,000":[114],"hours":[115],"2":[117],"million":[118],"high-quality":[119],"sequences.":[121],"Additionally,":[122],"propose":[124],"MotionMillion-Eval,":[125],"most":[127],"benchmark":[129],"evaluating":[131],"generation.":[134,171],"Leveraging":[135],"scalable":[137],"architecture,":[138],"scale":[140],"our":[141],"model":[142],"7B":[144],"parameters":[145],"validate":[147],"its":[148],"performance":[149],"MotionMillion-Eval.":[151],"Our":[152],"results":[153],"demonstrate":[154],"strong":[155],"out-of-domain":[158],"complex":[160],"compositional":[161],"motions,":[162],"marking":[163],"step":[166],"toward":[167],"The":[172],"code":[173],"is":[174],"available":[175],"at":[176],"https://github.com/VankouF/MotionMillion-Codes.":[177]},"counts_by_year":[],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}