{"id":"https://openalex.org/W4403780771","doi":"https://doi.org/10.1145/3664647.3680683","title":"Fuse Your Latents: Video Editing with Multi-source Latent Diffusion Models","display_name":"Fuse Your Latents: Video Editing with Multi-source Latent Diffusion Models","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403780771","doi":"https://doi.org/10.1145/3664647.3680683"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680683","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680683","pdf_url":null,"source":null,"license":null,"license_id":null,"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":"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":"https://openalex.org/A5109291377","display_name":"Tianyi Lu","orcid":"https://orcid.org/0009-0003-7803-194X"},"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":"Tianyi Lu","raw_affiliation_strings":["Shanghai Key Lab of Intel. Info. Proc., School of CS, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0003-7803-194X","affiliations":[{"raw_affiliation_string":"Shanghai Key Lab of Intel. Info. Proc., School of CS, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060677081","display_name":"Xing Zhang","orcid":"https://orcid.org/0000-0002-1721-035X"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xing Zhang","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-1721-035X","affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091310860","display_name":"Jiaxi Gu","orcid":"https://orcid.org/0000-0002-6201-9503"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxi Gu","raw_affiliation_strings":["Tencent, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-6201-9503","affiliations":[{"raw_affiliation_string":"Tencent, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102960782","display_name":"Renjing Pei","orcid":"https://orcid.org/0000-0001-7513-6576"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Renjing Pei","raw_affiliation_strings":["Huawei Noah's Ark Lab, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-7513-6576","affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Songcen Xu","orcid":"https://orcid.org/0000-0002-8689-5807"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songcen Xu","raw_affiliation_strings":["Huawei Noah's Ark Lab, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-8689-5807","affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078711649","display_name":"Xingjun Ma","orcid":"https://orcid.org/0000-0003-2099-4973"},"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":"Xingjun Ma","raw_affiliation_strings":["Shanghai Key Lab of Intel. Info. Proc., School of CS, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-2099-4973","affiliations":[{"raw_affiliation_string":"Shanghai Key Lab of Intel. Info. Proc., School of CS, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030497493","display_name":"Songcen Xu","orcid":"https://orcid.org/0000-0002-0022-0906"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Xu","raw_affiliation_strings":["Huawei Noah's Ark Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-0022-0906","affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":null,"display_name":"Zuxuan Wu","orcid":"https://orcid.org/0000-0003-3645-8972"},"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":"Zuxuan Wu","raw_affiliation_strings":["Shanghai Key Lab of Intel. Info. Proc., School of CS, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-3645-8972","affiliations":[{"raw_affiliation_string":"Shanghai Key Lab of Intel. Info. Proc., School of CS, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6745","last_page":"6754"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9926999807357788,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9926999807357788,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9733999967575073,"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/T11309","display_name":"Music and Audio Processing","score":0.9648000001907349,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/fuse","display_name":"Fuse (electrical)","score":0.8775430917739868},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6808541417121887},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.6583732962608337},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.44561389088630676},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09162190556526184},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07367482781410217},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.06271529197692871}],"concepts":[{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.8775430917739868},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6808541417121887},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.6583732962608337},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.44561389088630676},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09162190556526184},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07367482781410217},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.06271529197692871},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3680683","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680683","pdf_url":null,"source":null,"license":null,"license_id":null,"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":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2964024144","https://openalex.org/W3165647589","https://openalex.org/W3212516020","https://openalex.org/W4281485151","https://openalex.org/W4312497550","https://openalex.org/W4312872987","https://openalex.org/W4312933868","https://openalex.org/W4386057725","https://openalex.org/W4386071957","https://openalex.org/W4386072096","https://openalex.org/W4386076027","https://openalex.org/W4386076215","https://openalex.org/W4386076425","https://openalex.org/W4386076532","https://openalex.org/W4386113271","https://openalex.org/W4390871980","https://openalex.org/W4390872862"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W3000097931","https://openalex.org/W2354322770","https://openalex.org/W4237547500","https://openalex.org/W1570848052","https://openalex.org/W2373192430","https://openalex.org/W4239268388","https://openalex.org/W1537496349"],"abstract_inverted_index":{"Latent":[0,54],"Diffusion":[1,55],"Models":[2],"(LDMs)":[3],"are":[4],"renowned":[5],"for":[6],"their":[7],"powerful":[8],"capabilities":[9],"in":[10,108],"image":[11,84,134],"and":[12,32,69,85,101,112,135,148,154],"video":[13,86,136,144],"synthesis.":[14],"Yet,":[15],"compared":[16],"to":[17,35,81,97,132,138],"text-to-image":[18],"(T2I)":[19],"editing,":[20],"text-to-video":[21],"(T2V)":[22],"editing":[23,64,160,165],"suffers":[24],"from":[25],"a":[26,57,75,128],"lack":[27],"of":[28,110,143],"decent":[29],"temporal":[30,113],"consistency":[31],"structure,":[33],"due":[34],"insufficient":[36],"pre-training":[37],"data,":[38],"limited":[39],"model":[40],"editability,":[41],"or":[42],"extensive":[43],"tuning":[44],"costs.":[45],"To":[46],"address":[47],"this":[48],"gap,":[49],"we":[50],"propose":[51],"FLDM":[52,73,124],"(Fused":[53],"Model),":[56],"training-free":[58],"framework":[59],"that":[60,99,123],"achieves":[61],"high-quality":[62,117],"T2V":[63,70,102,155,164],"by":[65],"integrating":[66],"various":[67],"T2I":[68,100,153],"LDMs.":[71],"Specifically,":[72],"utilizes":[74],"hyper-parameter":[76],"with":[77],"an":[78],"update":[79],"schedule":[80],"effectively":[82],"fuse":[83],"latents":[87],"during":[88],"the":[89,95,141],"denoising":[90],"process.":[91],"This":[92],"paper":[93],"is":[94,120],"first":[96],"reveal":[98],"LDMs":[103,156],"can":[104,125],"complement":[105],"each":[106],"other":[107],"terms":[109],"structure":[111],"consistency,":[114],"ultimately":[115],"generating":[116],"videos.":[118],"It":[119],"worth":[121],"noting":[122],"serve":[126],"as":[127],"versatile":[129],"plugin,":[130],"applicable":[131],"off-the-shelf":[133],"LDMs,":[137],"significantly":[139],"enhance":[140],"quality":[142,161],"editing.":[145],"Extensive":[146],"quantitative":[147],"qualitative":[149],"experiments":[150],"on":[151],"popular":[152],"demonstrate":[157],"FLDM's":[158],"superior":[159],"than":[162],"state-of-the-art":[163],"methods.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}