{"id":"https://openalex.org/W4413156214","doi":"https://doi.org/10.1109/cvpr52734.2025.00188","title":"TokenMotion: Decoupled Motion Control via Token Disentanglement for Human-centric Video Generation","display_name":"TokenMotion: Decoupled Motion Control via Token Disentanglement for Human-centric Video Generation","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413156214","doi":"https://doi.org/10.1109/cvpr52734.2025.00188"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.00188","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00188","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"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/A5030771483","display_name":"Ruineng Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210129149","display_name":"Postmaster Psychologie Opleidingen","ror":"https://ror.org/03naar428","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210129149"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Ruineng Li","raw_affiliation_strings":["OPPO US AI Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO US AI Center","institution_ids":["https://openalex.org/I4210129149"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Daitao Xing","orcid":null},"institutions":[{"id":"https://openalex.org/I4210129149","display_name":"Postmaster Psychologie Opleidingen","ror":"https://ror.org/03naar428","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210129149"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Daitao Xing","raw_affiliation_strings":["OPPO US AI Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO US AI Center","institution_ids":["https://openalex.org/I4210129149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007055510","display_name":"Huiming Sun","orcid":"https://orcid.org/0000-0001-8721-798X"},"institutions":[{"id":"https://openalex.org/I4210129149","display_name":"Postmaster Psychologie Opleidingen","ror":"https://ror.org/03naar428","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210129149"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Huiming Sun","raw_affiliation_strings":["OPPO US AI Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO US AI Center","institution_ids":["https://openalex.org/I4210129149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108216418","display_name":"Y.R. Ha","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuanzhou Ha","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036427401","display_name":"J. Shen","orcid":"https://orcid.org/0000-0002-3852-2002"},"institutions":[{"id":"https://openalex.org/I4210129149","display_name":"Postmaster Psychologie Opleidingen","ror":"https://ror.org/03naar428","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210129149"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Jinglin Shen","raw_affiliation_strings":["OPPO US AI Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO US AI Center","institution_ids":["https://openalex.org/I4210129149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032649304","display_name":"Chun\u2010Yen Ho","orcid":null},"institutions":[{"id":"https://openalex.org/I4210129149","display_name":"Postmaster Psychologie Opleidingen","ror":"https://ror.org/03naar428","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210129149"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Chiuman Ho","raw_affiliation_strings":["OPPO US AI Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO US AI Center","institution_ids":["https://openalex.org/I4210129149"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1951","last_page":"1961"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9865999817848206,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9865999817848206,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9801999926567078,"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/T12290","display_name":"Human Motion and Animation","score":0.9757000207901001,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.686702311038971},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6829079389572144},{"id":"https://openalex.org/keywords/motion-control","display_name":"Motion control","score":0.5026731491088867},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.4171246886253357},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.2507283687591553},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.24840369820594788},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20571959018707275},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.07576024532318115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.686702311038971},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6829079389572144},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.5026731491088867},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4171246886253357},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2507283687591553},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.24840369820594788},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20571959018707275},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.07576024532318115}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.00188","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00188","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2471962767","https://openalex.org/W2962785568","https://openalex.org/W2963557767","https://openalex.org/W4293363567","https://openalex.org/W4312933868","https://openalex.org/W4386071957","https://openalex.org/W4389539288","https://openalex.org/W4390190334","https://openalex.org/W4390872297","https://openalex.org/W4390872556","https://openalex.org/W4390873054","https://openalex.org/W4390874580","https://openalex.org/W4391622623","https://openalex.org/W4400573519","https://openalex.org/W4402704510","https://openalex.org/W4402727736","https://openalex.org/W4402754210","https://openalex.org/W4402961675","https://openalex.org/W4403003238","https://openalex.org/W4403021266","https://openalex.org/W4403562353","https://openalex.org/W4403878131","https://openalex.org/W4403990754","https://openalex.org/W4404527320","https://openalex.org/W4404719810","https://openalex.org/W4405695475","https://openalex.org/W4409366251","https://openalex.org/W4409367532"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W4385009901","https://openalex.org/W2044900919"],"abstract_inverted_index":{"Human-centric":[0],"motion":[1,41,50,118,140],"control":[2,67,90,141],"in":[3,19,138,149],"video":[4,29,61,151],"generation":[5],"remains":[6],"a":[7,95,100,105,146],"critical":[8],"challenge,":[9],"particularly":[10],"when":[11],"jointly":[12],"controlling":[13],"camera":[14,47,69,79],"movements":[15],"and":[16,43,48,73,81,130],"human":[17,49,71,82],"poses":[18,83],"scenarios":[20],"like":[21],"the":[22,58,112],"iconic":[23],"Grammy":[24],"Glambot":[25],"moment.":[26],"While":[27],"recent":[28],"diffusion":[30,62],"models":[31],"have":[32],"made":[33],"significant":[34,147],"progress,":[35],"existing":[36],"approaches":[37],"struggle":[38],"with":[39,153],"limited":[40],"representations":[42],"inadequate":[44],"integration":[45],"of":[46,116],"controls.":[51],"In":[52],"this":[53],"work,":[54],"we":[55,123],"present":[56],"TokenMotion,":[57],"first":[59],"DiT-based":[60],"framework":[63,98],"that":[64,109],"enables":[65],"fine-grained":[66],"over":[68],"motion,":[70,72],"their":[74],"joint":[75],"interaction.":[76],"We":[77],"represent":[78],"trajectories":[80],"as":[84],"spatio-temporal":[85],"tokens":[86],"to":[87],"enable":[88],"local":[89],"granularity.":[91],"Our":[92,143],"approach":[93],"introduces":[94],"unified":[96],"modeling":[97],"utilizing":[99],"decouple-and-fuse":[101],"strategy,":[102],"bridged":[103],"by":[104],"human-aware":[106],"dynamic":[107],"mask":[108],"effectively":[110],"handles":[111],"spatially-and-temporally":[113],"varying":[114],"nature":[115],"combined":[117],"signals.":[119],"Through":[120],"extensive":[121],"experiments,":[122],"demonstrate":[124],"TokenMotion\u2019s":[125],"effectiveness":[126],"across":[127],"both":[128],"text-to-video":[129],"image-to-video":[131],"paradigms,":[132],"consistently":[133],"outperforming":[134],"current":[135],"state-of-the-art":[136],"methods":[137],"human-centric":[139],"tasks.":[142],"work":[144],"represents":[145],"advancement":[148],"controllable":[150],"generation,":[152],"particular":[154],"relevance":[155],"for":[156],"creative":[157],"production":[158],"applications.":[159]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}