{"id":"https://openalex.org/W4417073315","doi":"https://doi.org/10.1145/3743093.3771042","title":"DreamSwap: Motion-Preserving Personalized Video Subject Swapping with Video Diffusion Models","display_name":"DreamSwap: Motion-Preserving Personalized Video Subject Swapping with Video Diffusion Models","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W4417073315","doi":"https://doi.org/10.1145/3743093.3771042"},"language":null,"primary_location":{"id":"doi:10.1145/3743093.3771042","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3743093.3771042","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","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/A5052817188","display_name":"Cong Luo","orcid":"https://orcid.org/0009-0005-4358-1284"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong Luo","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0005-4358-1284","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xingxi Yin","orcid":"https://orcid.org/0009-0009-8939-4459"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingxi Yin","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0009-8939-4459","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074428255","display_name":"Yan Gong","orcid":"https://orcid.org/0009-0005-5060-953X"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Gong","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0005-5060-953X","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021252504","display_name":"Yin Zhang","orcid":"https://orcid.org/0000-0002-6702-6753"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yin Zhang","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0002-6702-6753","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I168879160"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I168879160"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.44936562,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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":0.7289000153541565,"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":0.7289000153541565,"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":0.14650000631809235,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0414000004529953,"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/flexibility","display_name":"Flexibility (engineering)","score":0.6728000044822693},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5821999907493591},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.5450999736785889},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5357999801635742},{"id":"https://openalex.org/keywords/video-editing","display_name":"Video editing","score":0.5051000118255615},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.5048999786376953},{"id":"https://openalex.org/keywords/motion-compensation","display_name":"Motion compensation","score":0.47119998931884766},{"id":"https://openalex.org/keywords/subject","display_name":"Subject (documents)","score":0.4325999915599823}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8291000127792358},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.6728000044822693},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5821999907493591},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.5450999736785889},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5357999801635742},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.5051000118255615},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.5048999786376953},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48590001463890076},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.47119998931884766},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.4325999915599823},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41530001163482666},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4092000126838684},{"id":"https://openalex.org/C30814859","wikidata":"https://www.wikidata.org/wiki/Q4119603","display_name":"Video denoising","level":5,"score":0.358599990606308},{"id":"https://openalex.org/C106030495","wikidata":"https://www.wikidata.org/wiki/Q1797012","display_name":"Video compression picture types","level":4,"score":0.34299999475479126},{"id":"https://openalex.org/C117090137","wikidata":"https://www.wikidata.org/wiki/Q7927977","display_name":"Video post-processing","level":5,"score":0.3384000062942505},{"id":"https://openalex.org/C2776566319","wikidata":"https://www.wikidata.org/wiki/Q3495514","display_name":"Interactive video","level":2,"score":0.3165000081062317},{"id":"https://openalex.org/C108803254","wikidata":"https://www.wikidata.org/wiki/Q857512","display_name":"Smacker video","level":4,"score":0.31470000743865967},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.30790001153945923},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3003999888896942},{"id":"https://openalex.org/C2778598663","wikidata":"https://www.wikidata.org/wiki/Q1407599","display_name":"Video content analysis","level":4,"score":0.2955999970436096},{"id":"https://openalex.org/C151211776","wikidata":"https://www.wikidata.org/wiki/Q2778015","display_name":"Video capture","level":3,"score":0.28700000047683716},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2712000012397766}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3743093.3771042","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3743093.3771042","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","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":24,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2470139095","https://openalex.org/W4312933868","https://openalex.org/W4386071613","https://openalex.org/W4386072096","https://openalex.org/W4386076425","https://openalex.org/W4386113271","https://openalex.org/W4389539288","https://openalex.org/W4390871782","https://openalex.org/W4390871980","https://openalex.org/W4390872556","https://openalex.org/W4390872862","https://openalex.org/W4390873135","https://openalex.org/W4390873195","https://openalex.org/W4390874393","https://openalex.org/W4390874580","https://openalex.org/W4400582187","https://openalex.org/W4402702984","https://openalex.org/W4402727368","https://openalex.org/W4402727429","https://openalex.org/W4402727736","https://openalex.org/W4402753775","https://openalex.org/W4402781367","https://openalex.org/W4407351351"],"related_works":[],"abstract_inverted_index":{"Most":[0],"existing":[1],"diffusion-based":[2],"video":[3,28,42,48,74,85,109,147],"editing":[4,29],"methods":[5],"are":[6],"text-driven,":[7],"limiting":[8],"users\u2019":[9],"flexibility":[10],"in":[11,58,66,143],"generating":[12,144],"desired":[13],"content":[14,54],"by":[15,55,88],"restricting":[16],"modifications":[17],"to":[18,30,51,103,119],"text":[19],"prompts.":[20],"In":[21,76],"this":[22],"work,":[23],"we":[24,111],"explore":[25],"subject-driven":[26],"personalized":[27,41,53,73,108,146],"enhance":[31],"user":[32],"control":[33],"and":[34,72,94,125,138],"creativity.":[35],"We":[36],"propose":[37],"DreamSwap,":[38],"a":[39,99],"novel":[40],"subject":[43,70,78],"swapping":[44],"method":[45,82,142],"that":[46],"leverages":[47],"diffusion":[49,86],"models":[50],"generate":[52],"replacing":[56],"subjects":[57],"input":[59],"videos":[60],"with":[61,98,115],"user-specified":[62],"targets.":[63],"DreamSwap":[64],"operates":[65],"two":[67],"main":[68],"stages:":[69],"learning":[71,79],"swapping.":[75],"the":[77,84,130,136],"stage,":[80],"our":[81,141],"finetunes":[83],"model":[87],"jointly":[89],"optimizing":[90],"learnable":[91],"textual":[92],"embeddings":[93],"spatial":[95,116],"attention":[96],"weights":[97],"region":[100],"reconstruction":[101],"loss":[102],"capture":[104],"subject-specific":[105],"characteristics.":[106],"For":[107],"swapping,":[110],"combine":[112],"motion":[113,127],"guidance":[114],"feature":[117],"injection":[118],"effectively":[120],"preserve":[121],"both":[122],"layout":[123],"information":[124],"primary":[126],"dynamics":[128],"from":[129],"source":[131],"video.":[132],"Extensive":[133],"experiments":[134],"demonstrate":[135],"efficiency":[137],"effectiveness":[139],"of":[140],"high-quality":[145],"content.":[148]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-12-06T00:00:00"}
