{"id":"https://openalex.org/W4416419038","doi":"https://doi.org/10.1109/iccv51701.2025.01240","title":"StyleMotif: Multi-Modal Motion Stylization using Style-Content Cross Fusion","display_name":"StyleMotif: Multi-Modal Motion Stylization using Style-Content Cross Fusion","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416419038","doi":"https://doi.org/10.1109/iccv51701.2025.01240"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01240","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01240","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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.21775","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053834265","display_name":"Ziyu Guo","orcid":"https://orcid.org/0000-0002-4792-1398"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ziyu Guo","raw_affiliation_strings":["The Chinese University of Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yizhak Ben-Shabat","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144102","display_name":"Wuhu Hit Robot Technology Research Institute","ror":"https://ror.org/049w4dp92","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144102"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yizhak Ben-Shabat","raw_affiliation_strings":["Roblox,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Roblox,China","institution_ids":["https://openalex.org/I4210144102"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Young Yoon Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144102","display_name":"Wuhu Hit Robot Technology Research Institute","ror":"https://ror.org/049w4dp92","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144102"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Young Yoon Lee","raw_affiliation_strings":["Roblox,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Roblox,China","institution_ids":["https://openalex.org/I4210144102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023687478","display_name":"Joseph K. Liu","orcid":"https://orcid.org/0000-0001-6656-6240"},"institutions":[{"id":"https://openalex.org/I4210144102","display_name":"Wuhu Hit Robot Technology Research Institute","ror":"https://ror.org/049w4dp92","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144102"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Joseph Liu","raw_affiliation_strings":["Roblox,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Roblox,China","institution_ids":["https://openalex.org/I4210144102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000237739","display_name":"Victor Zordan","orcid":"https://orcid.org/0000-0002-7309-7013"},"institutions":[{"id":"https://openalex.org/I4210144102","display_name":"Wuhu Hit Robot Technology Research Institute","ror":"https://ror.org/049w4dp92","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144102"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Victor Zordan","raw_affiliation_strings":["Roblox,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Roblox,China","institution_ids":["https://openalex.org/I4210144102"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069589954","display_name":"Mubbasir Kapadia","orcid":"https://orcid.org/0000-0002-3501-0028"},"institutions":[{"id":"https://openalex.org/I4210144102","display_name":"Wuhu Hit Robot Technology Research Institute","ror":"https://ror.org/049w4dp92","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144102"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mubbasir Kapadia","raw_affiliation_strings":["Roblox,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Roblox,China","institution_ids":["https://openalex.org/I4210144102"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":"13349","last_page":"13359"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.760200023651123,"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":0.760200023651123,"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":0.1492999941110611,"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":0.020600000396370888,"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/motion","display_name":"Motion (physics)","score":0.786300003528595},{"id":"https://openalex.org/keywords/stylized-fact","display_name":"Stylized fact","score":0.7803000211715698},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6553999781608582},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5072000026702881},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.41670000553131104},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.41600000858306885},{"id":"https://openalex.org/keywords/fusion-mechanism","display_name":"Fusion mechanism","score":0.4124999940395355},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.37770000100135803}],"concepts":[{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.786300003528595},{"id":"https://openalex.org/C38935604","wikidata":"https://www.wikidata.org/wiki/Q4330363","display_name":"Stylized fact","level":2,"score":0.7803000211715698},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6732000112533569},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6553999781608582},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5554999709129333},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5321999788284302},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5072000026702881},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.41670000553131104},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.41600000858306885},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.4124999940395355},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.37770000100135803},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3691999912261963},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.35519999265670776},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.3262999951839447},{"id":"https://openalex.org/C146159030","wikidata":"https://www.wikidata.org/wiki/Q7625099","display_name":"Structure from motion","level":3,"score":0.31060001254081726},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.3018999993801117},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.28130000829696655},{"id":"https://openalex.org/C95020103","wikidata":"https://www.wikidata.org/wiki/Q1813492","display_name":"Match moving","level":3,"score":0.2793000042438507},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.2667999863624573},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.25619998574256897}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01240","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01240","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:2503.21775","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.21775","pdf_url":"https://arxiv.org/pdf/2503.21775","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"doi:10.48550/arxiv.2503.21775","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.21775","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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:2503.21775","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.21775","pdf_url":"https://arxiv.org/pdf/2503.21775","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"present":[1],"StyleMotif,":[2],"a":[3,42,66,73,77],"novel":[4],"Stylized":[5],"Motion":[6],"Latent":[7],"Diffusion":[8],"model,":[9,80],"generating":[10,28],"motion":[11,30,40,85,105,113,118],"conditioned":[12],"on":[13,27],"both":[14],"content":[15,31,46],"and":[16,59,71,107,122],"style":[17,34,74,90],"from":[18,35,51],"multiple":[19],"modalities.":[20],"Unlike":[21],"existing":[22,101],"approaches":[23],"that":[24,82,97],"either":[25],"focus":[26],"diverse":[29],"or":[32],"transferring":[33],"sequences,":[36],"StyleMotif":[37],"seamlessly":[38],"synthesizes":[39],"across":[41],"wide":[43],"range":[44],"of":[45],"while":[47,91],"incorporating":[48],"stylistic":[49],"cues":[50],"multi-modal":[52,79,112],"inputs,":[53],"including":[54],"motion,":[55],"text,":[56],"image,":[57],"video,":[58],"audio.":[60],"To":[61],"achieve":[62],"this,":[63],"we":[64],"introduce":[65],"style-content":[67],"cross":[68],"fusion":[69],"mechanism":[70],"align":[72],"encoder":[75],"with":[76],"pre-trained":[78,123],"ensuring":[81],"the":[83,88],"generated":[84],"accurately":[86],"captures":[87],"reference":[89],"preserving":[92],"realism.":[93],"Extensive":[94],"experiments":[95],"demonstrate":[96],"our":[98],"framework":[99],"surpasses":[100],"methods":[102],"in":[103],"stylized":[104],"generation":[106],"exhibits":[108],"emergent":[109],"capabilities":[110],"for":[111],"stylization,":[114],"enabling":[115],"more":[116],"nuanced":[117],"synthesis.":[119],"Source":[120],"code":[121],"models":[124],"will":[125],"be":[126],"released":[127],"upon":[128],"acceptance.":[129],"Project":[130],"Page:":[131],"https://stylemotif.github.io":[132]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}