{"id":"https://openalex.org/W4415537978","doi":"https://doi.org/10.1145/3746027.3754493","title":"Separate Motion from Appearance: Customizing Motion via Customizing Text-to-Video Diffusion Models","display_name":"Separate Motion from Appearance: Customizing Motion via Customizing Text-to-Video Diffusion Models","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415537978","doi":"https://doi.org/10.1145/3746027.3754493"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754493","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754493","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":"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":null,"display_name":"Huijie Liu","orcid":"https://orcid.org/0009-0006-1395-3873"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huijie Liu","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-1395-3873","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091826509","display_name":"Jingyun Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyun Wang","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-4276-2779","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shuai Ma","orcid":"https://orcid.org/0009-0001-7338-2105"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Ma","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-7338-2105","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100679575","display_name":"Jie Hu","orcid":"https://orcid.org/0000-0002-5150-1003"},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Hu","raw_affiliation_strings":["Meituan, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5150-1003","affiliations":[{"raw_affiliation_string":"Meituan, Beijing, China","institution_ids":["https://openalex.org/I4210087373"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069204507","display_name":"Xiaoming Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoming Wei","raw_affiliation_strings":["Meituan, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7471-8344","affiliations":[{"raw_affiliation_string":"Meituan, Beijing, China","institution_ids":["https://openalex.org/I4210087373"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011488839","display_name":"Guoliang Kang","orcid":"https://orcid.org/0000-0003-1978-2025"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoliang Kang","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1978-2025","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9227","last_page":"9236"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9641000032424927,"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/T11448","display_name":"Face recognition and analysis","score":0.9641000032424927,"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":0.9380000233650208,"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":0.7838000059127808},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.7217000126838684},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.46000000834465027},{"id":"https://openalex.org/keywords/motion-field","display_name":"Motion field","score":0.4496000111103058},{"id":"https://openalex.org/keywords/motion-estimation","display_name":"Motion estimation","score":0.4374000132083893},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.41350001096725464},{"id":"https://openalex.org/keywords/motion-capture","display_name":"Motion capture","score":0.39480000734329224},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.3926999866962433}],"concepts":[{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.7838000059127808},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.7217000126838684},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7202000021934509},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6863999962806702},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6499000191688538},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.46000000834465027},{"id":"https://openalex.org/C124774092","wikidata":"https://www.wikidata.org/wiki/Q6917782","display_name":"Motion field","level":3,"score":0.4496000111103058},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.4374000132083893},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.41350001096725464},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.39480000734329224},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3926999866962433},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3792000114917755},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3684999942779541},{"id":"https://openalex.org/C95020103","wikidata":"https://www.wikidata.org/wiki/Q1813492","display_name":"Match moving","level":3,"score":0.35670000314712524},{"id":"https://openalex.org/C146159030","wikidata":"https://www.wikidata.org/wiki/Q7625099","display_name":"Structure from motion","level":3,"score":0.34040001034736633},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.32199999690055847},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3188999891281128},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C20864712","wikidata":"https://www.wikidata.org/wiki/Q667800","display_name":"Biological motion","level":3,"score":0.3009999990463257},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C174493125","wikidata":"https://www.wikidata.org/wiki/Q1073461","display_name":"Quarter-pixel motion","level":3,"score":0.2856999933719635},{"id":"https://openalex.org/C2780624872","wikidata":"https://www.wikidata.org/wiki/Q852453","display_name":"Motion detection","level":3,"score":0.2824000120162964},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.2596000134944916}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754493","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754493","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":[{"id":"https://openalex.org/G8115063663","display_name":null,"funder_award_id":"92370114","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2101194540","https://openalex.org/W2966421984","https://openalex.org/W4312933868","https://openalex.org/W4386071957","https://openalex.org/W4386075896","https://openalex.org/W4390871980","https://openalex.org/W4390873135","https://openalex.org/W4390874580","https://openalex.org/W4402660110"],"related_works":[],"abstract_inverted_index":{"Motion":[0],"customization":[1],"aims":[2],"to":[3,9,38,48,55,62,82,136,141,151,179,196,211,238,251],"adapt":[4],"the":[5,13,23,31,40,46,53,64,68,71,110,117,133,143,169,173,198,221,231,239,264,272],"diffusion":[6,93],"model":[7,39],"(DM)":[8],"generate":[10,49,257],"videos":[11,258],"with":[12,22,201,259,263,271],"motion":[14,25,42,65,87,98,111,139,144,202,268],"specified":[15,41],"by":[16,185],"a":[17,86,97,138,187,213],"set":[18],"of":[19,33,74,224,233,241],"video":[20],"clips":[21],"same":[24],"concept.":[26],"To":[27],"realize":[28],"this":[29,57,129],"goal,":[30],"adaptation":[32,72],"DM":[34],"should":[35],"be":[36,209],"possible":[37],"concept,":[43,112,145],"without":[44],"compromising":[45],"ability":[47],"diverse":[50],"appearances.":[51],"Thus,":[52,190],"key":[54],"solving":[56],"problem":[58],"lies":[59],"in":[60,70,119,123,168,191,217,228],"how":[61],"separate":[63],"concept":[66,88],"from":[67,230],"appearance":[69,118,125,161,260],"process":[73],"DM.":[75],"Typical":[76],"previous":[77,252],"works":[78],"explore":[79],"different":[80],"ways":[81],"represent":[83],"and":[84,160,267],"insert":[85],"into":[89],"large-scale":[90],"pre-trained":[91],"text-to-video":[92],"models,":[94],"e.g.,":[95],"learning":[96],"LoRA,":[99],"using":[100],"latent":[101],"noise":[102],"residuals,":[103],"etc.":[104],"While":[105],"those":[106],"methods":[107],"can":[108,208,256],"encode":[109,116,142],"they":[113],"also":[114],"inevitably":[115],"reference":[120,273],"videos,":[121],"resulting":[122],"weakened":[124],"generation":[126],"capability.":[127],"In":[128],"paper,":[130],"we":[131,165,193,219],"follow":[132],"typical":[134],"way":[135],"learn":[137],"LoRA":[140],"but":[146],"propose":[147],"two":[148],"novel":[149],"strategies":[150],"enhance":[152],"motion-appearance":[153],"separation,":[154],"including":[155],"temporal":[156,170,199,235],"attention":[157,171,200,236,244],"purification":[158],"(TAP)":[159],"highway":[162],"(AH).":[163],"Specifically,":[164],"assume":[166],"that":[167,205,249],"module,":[172],"pretrained":[174],"Value":[175,206],"embeddings":[176,207],"are":[177],"sufficient":[178],"serve":[180],"as":[181],"basic":[182],"components":[183],"needed":[184],"producing":[186],"new":[188,214],"motion.":[189,215],"TAP,":[192],"choose":[194],"only":[195],"reshape":[197],"LoRAs":[203],"so":[204],"reorganized":[210],"produce":[212],"Further,":[216],"AH,":[218],"alter":[220],"starting":[222],"point":[223],"each":[225,234,242],"skip":[226],"connection":[227],"U-Net":[229],"output":[232,240],"module":[237],"spatial":[243],"module.":[245],"Extensive":[246],"experiments":[247],"demonstrate":[248],"compared":[250],"works,":[253],"our":[254],"method":[255],"more":[261,269],"aligned":[262],"text":[265],"descriptions":[266],"consistent":[270],"videos.":[274]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}