{"id":"https://openalex.org/W4403792309","doi":"https://doi.org/10.1145/3664647.3680637","title":"DisenStudio: Customized Multi-Subject Text-to-Video Generation with Disentangled Spatial Control","display_name":"DisenStudio: Customized Multi-Subject Text-to-Video Generation with Disentangled Spatial Control","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403792309","doi":"https://doi.org/10.1145/3664647.3680637"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680637","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3680637","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3664647.3680637","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100420416","display_name":"Hong Chen","orcid":"https://orcid.org/0000-0002-0943-2286"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hong Chen","raw_affiliation_strings":["DCST, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022927606","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0002-0351-2939"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["DCST, BNRist, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"DCST, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088844431","display_name":"Y. J. Zhang","orcid":"https://orcid.org/0009-0002-0886-8296"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yipeng Zhang","raw_affiliation_strings":["DCST, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101273536","display_name":"Yuwei Zhou","orcid":"https://orcid.org/0000-0001-9582-7331"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuwei Zhou","raw_affiliation_strings":["DCST, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086592862","display_name":"Zeyang Zhang","orcid":"https://orcid.org/0000-0003-1329-1313"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeyang Zhang","raw_affiliation_strings":["DCST, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102674788","display_name":"Siao Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siao Tang","raw_affiliation_strings":["DCST, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100339293","display_name":"Wenwu Zhu","orcid":"https://orcid.org/0000-0003-2236-9290"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenwu Zhu","raw_affiliation_strings":["DCST, BNRist, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"DCST, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100420416"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.8369,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.87060215,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3637","last_page":"3646"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9980999827384949,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9980999827384949,"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":0.9968000054359436,"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/T12720","display_name":"Multimedia Communication and Technology","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7644494771957397},{"id":"https://openalex.org/keywords/subject","display_name":"Subject (documents)","score":0.639624834060669},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5249038934707642},{"id":"https://openalex.org/keywords/text-generation","display_name":"Text generation","score":0.5138464570045471},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3294954001903534},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.32947874069213867},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1639547049999237}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7644494771957397},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.639624834060669},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5249038934707642},{"id":"https://openalex.org/C2985684807","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Text generation","level":2,"score":0.5138464570045471},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3294954001903534},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.32947874069213867},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1639547049999237}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3680637","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3680637","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3664647.3680637","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3680637","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W3159481202","https://openalex.org/W3204588463","https://openalex.org/W4226289673","https://openalex.org/W4281485151","https://openalex.org/W4281661987","https://openalex.org/W4312933868","https://openalex.org/W4385270985","https://openalex.org/W4386065764","https://openalex.org/W4386072096","https://openalex.org/W4386076425","https://openalex.org/W4390873135","https://openalex.org/W4390874575","https://openalex.org/W4391807605"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W4388258507","https://openalex.org/W2392013855","https://openalex.org/W4318064328","https://openalex.org/W2357926602","https://openalex.org/W3200517220","https://openalex.org/W2374569605","https://openalex.org/W2386062718","https://openalex.org/W4393047559","https://openalex.org/W899618282"],"abstract_inverted_index":{"Generating":[0],"customized":[1,16,78,113],"content":[2],"in":[3,63,182],"videos":[4,76],"has":[5],"received":[6],"increasing":[7],"attention":[8],"recently.":[9],"However,":[10],"existing":[11,38,180],"works":[12],"primarily":[13],"focus":[14],"on":[15,166],"text-to-video":[17,93],"generation":[18,57,200],"for":[19,77,84,114,197],"single":[20],"subject,":[21],"suffering":[22],"from":[23],"subject-missing":[24],"and":[25,135,147,152],"attribute-binding":[26],"problems":[27],"when":[28,164],"the":[29,43,47,61,106,110,115,119,144,153,157,160],"video":[30],"is":[31,112],"expected":[32],"to":[33,41,46,53,101,173],"contain":[34],"multiple":[35,79,116],"subjects.":[36],"Furthermore,":[37],"models":[39],"struggle":[40],"assign":[42],"desired":[44,107],"actions":[45],"corresponding":[48],"subjects":[49,117],"(action-binding":[50],"problem),":[51],"failing":[52],"achieve":[54],"satisfactory":[55],"multi-subject":[56,129,136],"performance.":[58],"To":[59],"tackle":[60],"problems,":[62],"this":[64],"paper,":[65],"we":[66,186],"propose":[67],"DisenStudio,":[68],"a":[69,90,194],"novel":[70],"framework":[71],"that":[72,188],"can":[73,190],"generate":[74],"text-guided":[75],"subjects,":[80],"given":[81],"few":[82],"images":[83],"each":[85,103],"subject.":[86],"Specifically,":[87],"DisenStudio":[88,177,189],"enhances":[89],"pretrained":[91],"diffusion-based":[92],"model":[94,111,158],"with":[95,105,118],"our":[96,175],"proposed":[97,120,176],"spatial-disentangled":[98],"cross-attention":[99],"mechanism":[100],"associate":[102],"subject":[104,145],"action.":[108],"Then":[109],"motion-preserved":[121,137],"disentangled":[122],"finetuning,":[123],"which":[124],"involves":[125],"three":[126],"tuning":[127],"strategies:":[128],"co-occurrence":[130],"tuning,":[131,134],"masked":[132],"single-subject":[133],"tuning.":[138],"The":[139],"first":[140],"two":[141],"strategies":[142],"guarantee":[143],"occurrence":[146],"preserve":[148],"their":[149],"visual":[150],"attributes,":[151],"third":[154],"strategy":[155],"helps":[156],"maintain":[159],"temporal":[161],"motion-generation":[162],"ability":[163],"finetuning":[165],"static":[167],"images.":[168],"We":[169],"conduct":[170],"extensive":[171],"experiments":[172],"demonstrate":[174],"significantly":[178],"outperforms":[179],"methods":[181],"various":[183,198],"metrics.":[184],"Additionally,":[185],"show":[187],"be":[191],"used":[192],"as":[193],"powerful":[195],"tool":[196],"controllable":[199],"applications.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}
