{"id":"https://openalex.org/W7131125972","doi":"https://doi.org/10.1109/iccvw69036.2025.00643","title":"Zero-Shot Customized Video Editing with Diffusion Feature Transfer","display_name":"Zero-Shot Customized Video Editing with Diffusion Feature Transfer","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W7131125972","doi":"https://doi.org/10.1109/iccvw69036.2025.00643"},"language":null,"primary_location":{"id":"doi:10.1109/iccvw69036.2025.00643","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw69036.2025.00643","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","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/A5126627803","display_name":"Wei Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Chen","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101717680","display_name":"Huidong Liu","orcid":"https://orcid.org/0000-0003-3833-9475"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Huidong Liu","raw_affiliation_strings":["Amazon.com, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon.com, Inc","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100356000","display_name":"Yang Liu","orcid":"https://orcid.org/0000-0002-8369-6175"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":["Amazon.com, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon.com, Inc","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021739840","display_name":"Chien-chih Wang","orcid":"https://orcid.org/0000-0001-5127-3939"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Chien-Chih Wang","raw_affiliation_strings":["Amazon.com, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon.com, Inc","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126600143","display_name":"Moyan Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Moyan Li","raw_affiliation_strings":["Amazon.com, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon.com, Inc","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hongdong Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hongdong Li","raw_affiliation_strings":["Amazon.com, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon.com, Inc","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101432451","display_name":"Bryan Wang","orcid":"https://orcid.org/0000-0001-9016-038X"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bryan Wang","raw_affiliation_strings":["Amazon.com, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon.com, Inc","institution_ids":["https://openalex.org/I4210089985"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6173","last_page":"6182"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.7968000173568726,"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":0.7968000173568726,"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/T10741","display_name":"Video Coding and Compression Technologies","score":0.061500001698732376,"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"}},{"id":"https://openalex.org/T12720","display_name":"Multimedia Communication and Technology","score":0.026399999856948853,"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/video-editing","display_name":"Video editing","score":0.6596999764442444},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.633400022983551},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5562000274658203},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.5037000179290771},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4438000023365021},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.4140999913215637},{"id":"https://openalex.org/keywords/motion-compensation","display_name":"Motion compensation","score":0.3855000138282776},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.3815000057220459},{"id":"https://openalex.org/keywords/video-capture","display_name":"Video capture","score":0.37790000438690186}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8353999853134155},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.6596999764442444},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.63919997215271},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.633400022983551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6204000115394592},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5562000274658203},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.5037000179290771},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4438000023365021},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.4140999913215637},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.3855000138282776},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3815000057220459},{"id":"https://openalex.org/C151211776","wikidata":"https://www.wikidata.org/wiki/Q2778015","display_name":"Video capture","level":3,"score":0.37790000438690186},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.36090001463890076},{"id":"https://openalex.org/C106030495","wikidata":"https://www.wikidata.org/wiki/Q1797012","display_name":"Video compression picture types","level":4,"score":0.3601999878883362},{"id":"https://openalex.org/C137402728","wikidata":"https://www.wikidata.org/wiki/Q1330119","display_name":"Non-linear editing system","level":5,"score":0.35190001130104065},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3140000104904175},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.2985000014305115},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C23431618","wikidata":"https://www.wikidata.org/wiki/Q1404672","display_name":"Multiview Video Coding","level":4,"score":0.29429998993873596},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.2782000005245209},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.273499995470047},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C117090137","wikidata":"https://www.wikidata.org/wiki/Q7927977","display_name":"Video post-processing","level":5,"score":0.2619999945163727},{"id":"https://openalex.org/C2777036941","wikidata":"https://www.wikidata.org/wiki/Q6917771","display_name":"Motion analysis","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccvw69036.2025.00643","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw69036.2025.00643","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","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":35,"referenced_works":["https://openalex.org/W2133665775","https://openalex.org/W2754213847","https://openalex.org/W2948978827","https://openalex.org/W2962785568","https://openalex.org/W3035242260","https://openalex.org/W3153469116","https://openalex.org/W3180355996","https://openalex.org/W4233762729","https://openalex.org/W4283806547","https://openalex.org/W4312234230","https://openalex.org/W4312933868","https://openalex.org/W4386072096","https://openalex.org/W4386076425","https://openalex.org/W4386076532","https://openalex.org/W4386113271","https://openalex.org/W4388230738","https://openalex.org/W4389539288","https://openalex.org/W4390871782","https://openalex.org/W4390872862","https://openalex.org/W4390873054","https://openalex.org/W4390873135","https://openalex.org/W4390874580","https://openalex.org/W4402702984","https://openalex.org/W4402702999","https://openalex.org/W4402703034","https://openalex.org/W4402716173","https://openalex.org/W4402727429","https://openalex.org/W4402753768","https://openalex.org/W4402753907","https://openalex.org/W4402774219","https://openalex.org/W4402781367","https://openalex.org/W4403878131","https://openalex.org/W4404612908","https://openalex.org/W4407351351","https://openalex.org/W4413145530"],"related_works":[],"abstract_inverted_index":{"Customized":[0],"video":[1,12,64,105,129,164,175,203,210,224,233],"editing":[2,106,225,234],"aims":[3],"at":[4],"substituting":[5],"the":[6,32,35,38,44,48,94,113,119,123,127,133,145,149,162,173,181,189],"object":[7,16,67,125],"in":[8,37,126,148,180],"a":[9,14,84,102],"given":[10,86],"source":[11,49,63,128,163,202],"with":[13],"target":[15],"from":[17,47,161,168],"reference":[18,39,87,150,169],"images":[19,170],"(Fig.":[20],"1).":[21],"Existing":[22],"approaches":[23],"often":[24,79],"rely":[25],"on":[26],"fine-tuning":[27,58,229],"pre-trained":[28,95],"models":[29],"by":[30,92,132],"learning":[31],"appearance":[33,147,166],"of":[34,112,122,188,200],"objects":[36],"images,":[40],"as":[41,43,57],"well":[42],"temporal":[45,186],"information":[46,121],"video.":[50],"These":[51],"methods":[52,226],"are":[53,130],"however":[54],"not":[55],"scalable":[56],"is":[59],"required":[60],"for":[61],"each":[62,66],"and":[65,165,230],"to":[68,81,83,171,196,208],"be":[69],"customized,":[70],"incurring":[71],"computational":[72],"overhead.":[73],"More":[74],"importantly,":[75],"such":[76],"individual":[77],"customization":[78],"leads":[80],"overfitting":[82],"few":[85],"images.":[88,151],"In":[89],"this":[90,154],"paper,":[91],"leveraging":[93],"Stable":[96],"Diffusion":[97],"model,":[98],"we":[99,116,156,192],"propose":[100],"FreeMix,":[101],"zero-shot":[103],"customized":[104,223],"approach.":[107],"From":[108],"careful":[109],"empirical":[110],"analysis":[111],"diffusion":[114,136,141,182,198],"features,":[115,137],"observe":[117],"that":[118,217,227],"motion":[120,159],"moving":[124],"captured":[131],"low-frequency":[134],"high-level":[135],"while":[138],"high-frequency":[139],"low-level":[140,197],"features":[142,199],"encode":[143],"more":[144],"object's":[146],"By":[152],"exploiting":[153],"observation,":[155],"achieve":[157],"effective":[158],"transfer":[160,167,179],"synthesize":[172],"output":[174],"via":[176],"simple":[177],"feature":[178,206],"model.":[183],"To":[184],"enhance":[185],"consistency":[187],"synthesized":[190],"video,":[191],"apply":[193],"optimal":[194],"transport":[195],"consecutive":[201],"frames,":[204],"establishing":[205],"correspondences":[207],"guide":[209],"generation.":[211],"We":[212],"conduct":[213],"comprehensive":[214],"experiments,":[215],"demonstrating":[216],"our":[218],"approach":[219],"surpasses":[220],"both":[221],"state-of-the-art":[222],"require":[228],"general":[231],"text-based":[232],"methods.":[235]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-24T00:00:00"}