{"id":"https://openalex.org/W4409260544","doi":"https://doi.org/10.1109/tmm.2025.3557634","title":"VideoDreamer: Customized Multi-Subject Text-to-Video Generation With Disen-Mix Finetuning on Language-Video Foundation Models","display_name":"VideoDreamer: Customized Multi-Subject Text-to-Video Generation With Disen-Mix Finetuning on Language-Video Foundation Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4409260544","doi":"https://doi.org/10.1109/tmm.2025.3557634"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3557634","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3557634","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/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":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, 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":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111068871","display_name":"Guanning Zeng","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":"Guanning Zeng","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, 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":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, 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":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008538297","display_name":"Feilin Han","orcid":null},"institutions":[{"id":"https://openalex.org/I2802536167","display_name":"Beijing Film Academy","ror":"https://ror.org/03y0w9190","country_code":"CN","type":"education","lineage":["https://openalex.org/I2802536167"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feilin Han","raw_affiliation_strings":["Department of Film and TV Technology, Beijing Film Academy, Beijing, China","Department of Film and TV Technology, Beijing Film Academy, China"],"affiliations":[{"raw_affiliation_string":"Department of Film and TV Technology, Beijing Film Academy, Beijing, China","institution_ids":["https://openalex.org/I2802536167"]},{"raw_affiliation_string":"Department of Film and TV Technology, Beijing Film Academy, China","institution_ids":["https://openalex.org/I2802536167"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yaofei Wu","orcid":"https://orcid.org/0009-0001-8474-0027"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaofei Wu","raw_affiliation_strings":["Beijing University of Technology, Beijing, China","Beijing University of Technology, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]},{"raw_affiliation_string":"Beijing University of Technology, China","institution_ids":["https://openalex.org/I37796252"]}]},{"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":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100420416"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":3.4851,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.9176036,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"27","issue":null,"first_page":"2875","last_page":"2885"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.8495000004768372,"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":0.8495000004768372,"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":0.7825000286102295,"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"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.7426999807357788,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8733230829238892},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.5396566390991211},{"id":"https://openalex.org/keywords/subject","display_name":"Subject (documents)","score":0.5221579074859619},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4437265992164612},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3842566907405853},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3811170160770416},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.32158565521240234},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.30920273065567017}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8733230829238892},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.5396566390991211},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.5221579074859619},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4437265992164612},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3842566907405853},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3811170160770416},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.32158565521240234},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.30920273065567017},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3557634","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3557634","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G3022012397","display_name":null,"funder_award_id":"BNR2023TD03006","funder_id":"https://openalex.org/F4320329777","funder_display_name":"Beijing National Research Center For Information Science And Technology"},{"id":"https://openalex.org/G8567821897","display_name":null,"funder_award_id":"62222209","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"},{"id":"https://openalex.org/F4320329777","display_name":"Beijing National Research Center For Information Science And Technology","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2558805089","https://openalex.org/W2963345606","https://openalex.org/W2981592093","https://openalex.org/W3204588463","https://openalex.org/W4226289673","https://openalex.org/W4294541506","https://openalex.org/W4312933868","https://openalex.org/W4378771767","https://openalex.org/W4386065764","https://openalex.org/W4386072096","https://openalex.org/W4386076425","https://openalex.org/W4389539271","https://openalex.org/W4389539288","https://openalex.org/W4390871782","https://openalex.org/W4390872341","https://openalex.org/W4390872556","https://openalex.org/W4390873135","https://openalex.org/W4390874393","https://openalex.org/W4391807605","https://openalex.org/W4400573550","https://openalex.org/W4402660110","https://openalex.org/W4402727429","https://openalex.org/W4402727699","https://openalex.org/W4402753775","https://openalex.org/W4402753906","https://openalex.org/W4402782221","https://openalex.org/W4407151317","https://openalex.org/W6757817989","https://openalex.org/W6766978945","https://openalex.org/W6779823529","https://openalex.org/W6783713337","https://openalex.org/W6790978476","https://openalex.org/W6794385437","https://openalex.org/W6796581206","https://openalex.org/W6803376173","https://openalex.org/W6809885388","https://openalex.org/W6810940779","https://openalex.org/W6838327568","https://openalex.org/W6838639034","https://openalex.org/W6838785959","https://openalex.org/W6841755765","https://openalex.org/W6844305113","https://openalex.org/W6845281891","https://openalex.org/W6846007759","https://openalex.org/W6846820273","https://openalex.org/W6847405979","https://openalex.org/W6848729602","https://openalex.org/W6850484678","https://openalex.org/W6851513319","https://openalex.org/W6852912373","https://openalex.org/W6854463369","https://openalex.org/W6857152876","https://openalex.org/W6858216652","https://openalex.org/W7004972456"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W4388258507","https://openalex.org/W2392013855","https://openalex.org/W2381393187","https://openalex.org/W2332779545","https://openalex.org/W4318064328","https://openalex.org/W2357926602","https://openalex.org/W3200517220","https://openalex.org/W2374569605","https://openalex.org/W2386062718"],"abstract_inverted_index":{"Customized":[0],"text-to-video":[1,25,153],"generation":[2,35],"aims":[3],"to":[4,22,90,112,129,168,181],"generate":[5,52,91,138,169],"text-guided":[6,55],"videos":[7,56,139,170],"with":[8,75,140,171],"user-given":[9],"subjects,":[10],"which":[11,50,102],"has":[12],"gained":[13],"increasing":[14],"attention.":[15],"However,":[16],"existing":[17],"works":[18],"are":[19],"primarily":[20],"limited":[21],"single-subject":[23],"oriented":[24],"generation,":[26,154],"leaving":[27],"the":[28,60,64,71,84,87,104,114,131,148,157,163,182],"more":[29],"challenging":[30],"problem":[31,117],"of":[32,63,86,118,150,166],"customized":[33,99,142,151,183],"multi-subject":[34,119,152],"unexplored.":[36],"In":[37],"this":[38,42],"paper,":[39],"we":[40,122,136,155],"fill":[41],"gap":[43],"and":[44,108,144,178],"propose":[45],"a":[46,124],"novel":[47],"VideoDreamer":[48,69,167],"framework,":[49],"can":[51,137],"temporally":[53],"consistent":[54],"that":[57,135],"faithfully":[58],"preserve":[59],"visual":[61],"features":[62],"given":[65],"multiple":[66,184],"subjects.":[67,185],"Specifically,":[68],"adopts":[70],"pretrained":[72],"Stable":[73],"Diffusion":[74],"temporal":[76,132],"modules":[77,133],"as":[78,175],"its":[79],"base":[80],"video":[81,95],"generator,":[82],"taking":[83],"power":[85],"text-to-image":[88],"model":[89],"diversified":[92],"content.":[93],"The":[94],"generator":[96],"is":[97],"further":[98],"for":[100],"multi-subjects,":[101],"leverages":[103],"proposed":[105],"Disen-Mix":[106],"Finetuning":[107],"Human-in-the-Loop":[109],"Re-finetuning":[110],"strategy,":[111],"tackle":[113],"attribute":[115],"binding":[116],"generation.":[120],"Additionally,":[121],"present":[123],"disentangled":[125],"motion":[126],"customization":[127],"strategy":[128],"finetune":[130],"so":[134],"both":[141],"subjects":[143],"motions.":[145],"To":[146],"evaluate":[147],"performance":[149],"introduce":[156],"MultiStudioBench":[158],"benchmark.":[159],"Extensive":[160],"experiments":[161],"demonstrate":[162],"remarkable":[164],"ability":[165],"new":[172,176],"content":[173],"such":[174],"events":[177],"backgrounds,":[179],"tailored":[180]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}
