{"id":"https://openalex.org/W4415537695","doi":"https://doi.org/10.1145/3746027.3754873","title":"UMSD:High Realism Motion Style Transfer via Unified Mamba-based Diffusion","display_name":"UMSD:High Realism Motion Style Transfer via Unified Mamba-based Diffusion","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415537695","doi":"https://doi.org/10.1145/3746027.3754873"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754873","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754873","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","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/A5086505410","display_name":"Ziyun Qian","orcid":"https://orcid.org/0009-0007-9800-1253"},"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":true,"raw_author_name":"Ziyun Qian","raw_affiliation_strings":["College of Intelligent Robotics and Advanced Manufacturing, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0007-9800-1253","affiliations":[{"raw_affiliation_string":"College of Intelligent Robotics and Advanced Manufacturing, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114126737","display_name":"Zeyu Xiao","orcid":"https://orcid.org/0009-0003-7522-9301"},"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":"Zeyu Xiao","raw_affiliation_strings":["College of Intelligent Robotics and Advanced Manufacturing, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0003-7522-9301","affiliations":[{"raw_affiliation_string":"College of Intelligent Robotics and Advanced Manufacturing, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101613857","display_name":"Xingliang Jin","orcid":"https://orcid.org/0000-0001-9209-7804"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingliang Jin","raw_affiliation_strings":["School of Computer Science and Technology, East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9209-7804","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064280715","display_name":"Dingkang Yang","orcid":"https://orcid.org/0000-0003-1829-5671"},"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":"Dingkang Yang","raw_affiliation_strings":["College of Intelligent Robotics and Advanced Manufacturing, Fudan University&amp;ByteDance Inc., Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-1829-5671","affiliations":[{"raw_affiliation_string":"College of Intelligent Robotics and Advanced Manufacturing, Fudan University&amp;ByteDance Inc., Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058367079","display_name":"M. H. Li","orcid":"https://orcid.org/0009-0000-6244-6081"},"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":"Mingcheng Li","raw_affiliation_strings":["College of Intelligent Robotics and Advanced Manufacturing, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0000-6244-6081","affiliations":[{"raw_affiliation_string":"College of Intelligent Robotics and Advanced Manufacturing, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhenyi Wu","orcid":"https://orcid.org/0009-0002-2981-9813"},"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":"Zhenyi Wu","raw_affiliation_strings":["College of Intelligent Robotics and Advanced Manufacturing, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0002-2981-9813","affiliations":[{"raw_affiliation_string":"College of Intelligent Robotics and Advanced Manufacturing, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114231553","display_name":"Dongliang Kou","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":"Dongliang Kou","raw_affiliation_strings":["College of Intelligent Robotics and Advanced Manufacturing, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0009-5792-6895","affiliations":[{"raw_affiliation_string":"College of Intelligent Robotics and Advanced Manufacturing, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036810000","display_name":"Peng Zhai","orcid":"https://orcid.org/0000-0002-1374-7969"},"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":"Peng Zhai","raw_affiliation_strings":["College of Intelligent Robotics and Advanced Manufacturing, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1374-7969","affiliations":[{"raw_affiliation_string":"College of Intelligent Robotics and Advanced Manufacturing, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100414906","display_name":"Lihua Zhang","orcid":"https://orcid.org/0000-0003-0467-4347"},"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":"Lihua Zhang","raw_affiliation_strings":["College of Intelligent Robotics and Advanced Manufacturing, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-0467-4347","affiliations":[{"raw_affiliation_string":"College of Intelligent Robotics and Advanced Manufacturing, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5086505410"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":2.2665,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.90272566,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"7424","last_page":"7433"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9973000288009644,"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"}},"topics":[{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9973000288009644,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9961000084877014,"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":0.9955000281333923,"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/motion","display_name":"Motion (physics)","score":0.7523000240325928},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.5702000260353088},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5478000044822693},{"id":"https://openalex.org/keywords/stylized-fact","display_name":"Stylized fact","score":0.491100013256073},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.32989999651908875},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.31360000371932983},{"id":"https://openalex.org/keywords/realism","display_name":"Realism","score":0.3116999864578247}],"concepts":[{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.7523000240325928},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6110000014305115},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.5702000260353088},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5478000044822693},{"id":"https://openalex.org/C38935604","wikidata":"https://www.wikidata.org/wiki/Q4330363","display_name":"Stylized fact","level":2,"score":0.491100013256073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4431999921798706},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.32989999651908875},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3278000056743622},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.31360000371932983},{"id":"https://openalex.org/C543847140","wikidata":"https://www.wikidata.org/wiki/Q2642826","display_name":"Realism","level":2,"score":0.3116999864578247},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29100000858306885},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.28450000286102295},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C2776172590","wikidata":"https://www.wikidata.org/wiki/Q7629421","display_name":"Style analysis","level":4,"score":0.27230000495910645},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.2669000029563904},{"id":"https://openalex.org/C146159030","wikidata":"https://www.wikidata.org/wiki/Q7625099","display_name":"Structure from motion","level":3,"score":0.2590999901294708},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.25600001215934753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754873","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754873","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2028000151","https://openalex.org/W2049077434","https://openalex.org/W2756203131","https://openalex.org/W3024902055","https://openalex.org/W3204107037","https://openalex.org/W4221045999","https://openalex.org/W4312805142","https://openalex.org/W4377010269","https://openalex.org/W4386065807","https://openalex.org/W4386065848","https://openalex.org/W4402660084","https://openalex.org/W4402727736","https://openalex.org/W4402727878","https://openalex.org/W4402754100","https://openalex.org/W4403792175"],"related_works":[],"abstract_inverted_index":{"Motion":[0,99,121],"style":[1,66,111,133,159,173,195],"transfer":[2],"is":[3],"a":[4,54,97,152,158],"significant":[5],"research":[6],"area":[7],"in":[8,22,39,69,82,87,131],"computer":[9],"vision,":[10],"enabling":[11],"the":[12,19,29,47,60,120,128,165],"rapid":[13],"switching":[14],"of":[15,33],"stylistic":[16],"variations":[17],"for":[18,127],"same":[20],"motion":[21,84,132,147,169,174,194],"virtual":[23],"digital":[24],"humans.":[25],"This":[26],"dramatically":[27],"enhances":[28],"richness":[30],"and":[31,46,65,72,110,157,187,192],"realism":[32],"motions,":[34,67,112],"making":[35],"it":[36],"widely":[37],"applicable":[38],"multimedia":[40],"contexts":[41],"such":[42],"as":[43],"film,":[44],"gaming,":[45],"Metaverse.":[48],"However,":[49],"most":[50],"existing":[51],"methods":[52,76,185],"employ":[53],"two-stream":[55],"structure,":[56],"which":[57],"often":[58],"overlooks":[59],"intrinsic":[61],"relationships":[62],"between":[63],"content":[64,109,154,168],"resulting":[68,86],"information":[70,115],"loss":[71,156,161],"misalignment.":[73],"Additionally,":[74],"these":[75,93],"struggle":[77],"to":[78,141,162],"capture":[79],"temporal":[80],"dependencies":[81],"long-range":[83],"sequences,":[85],"less":[88],"natural":[89],"outputs.":[90],"To":[91],"address":[92],"limitations,":[94],"we":[95,150],"propose":[96],"Unified":[98],"Style":[100,122],"Diffusion":[101],"(UMSD)":[102],"Framework":[103],"that":[104,164,179],"simultaneously":[105],"extracts":[106],"features":[107],"from":[108],"achieving":[113,189],"comprehensive":[114],"interaction.":[116],"We":[117],"also":[118],"introduce":[119],"Mamba":[123],"(MSM)":[124],"denoiser,":[125],"which,":[126],"first":[129],"time":[130],"transfer,":[134],"leverages":[135],"Mamba's":[136],"powerful":[137],"sequence":[138],"modelling":[139],"capability":[140],"produce":[142],"more":[143,190],"temporally":[144],"coherent":[145,193],"stylized":[146],"sequences.":[148],"Furthermore,":[149],"design":[151],"diffusion-based":[153],"consistency":[155,160],"ensure":[163],"framework":[166],"preserves":[167],"while":[170],"effectively":[171],"learning":[172],"features.":[175],"Extensive":[176],"experiments":[177],"demonstrate":[178],"our":[180],"approach":[181],"outperforms":[182],"State-Of-The-Art":[183],"(SOTA)":[184],"qualitatively":[186],"quantitatively,":[188],"realistic":[191],"transfer.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-25T00:00:00"}
