{"id":"https://openalex.org/W7123362259","doi":"https://doi.org/10.1109/tcsvt.2026.3652425","title":"Training-Free Controllable Text-Guided Video Editing","display_name":"Training-Free Controllable Text-Guided Video Editing","publication_year":2026,"publication_date":"2026-01-12","ids":{"openalex":"https://openalex.org/W7123362259","doi":"https://doi.org/10.1109/tcsvt.2026.3652425"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2026.3652425","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3652425","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","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/A5122894213","display_name":"Yuanzhi Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanzhi Wang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-2594-2574","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yong Li","orcid":"https://orcid.org/0000-0002-6521-5921"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Li","raw_affiliation_strings":["School of Computer Science and Engineering and the Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-6521-5921","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering and the Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122876548","display_name":"Mengyi Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210160629","display_name":"China Information Technology Security Evaluation Center","ror":"https://ror.org/053cexp66","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210160629"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengyi Liu","raw_affiliation_strings":["Kuaishou Technology, Department of Content Security, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Department of Content Security, Beijing, China","institution_ids":["https://openalex.org/I4210160629"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaoya Zhang","orcid":"https://orcid.org/0000-0003-4136-7880"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoya Zhang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-4136-7880","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhen Cui","orcid":"https://orcid.org/0000-0002-0543-4196"},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Cui","raw_affiliation_strings":["School of Artificial Intelligence, Beijing Normal University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0543-4196","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing Normal University, Beijing, China","institution_ids":["https://openalex.org/I25254941"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jian Yang","orcid":"https://orcid.org/0000-0003-4800-832X"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Yang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-4800-832X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05397341,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"5","first_page":"6558","last_page":"6571"},"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":0.37790000438690186,"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":0.37790000438690186,"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":0.3499999940395355,"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":0.02070000022649765,"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/video-editing","display_name":"Video editing","score":0.786300003528595},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.5823000073432922},{"id":"https://openalex.org/keywords/video-compression-picture-types","display_name":"Video compression picture types","score":0.5066999793052673},{"id":"https://openalex.org/keywords/motion-compensation","display_name":"Motion compensation","score":0.5052000284194946},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.48750001192092896},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.4381999969482422},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.4104999899864197},{"id":"https://openalex.org/keywords/video-capture","display_name":"Video capture","score":0.388700008392334},{"id":"https://openalex.org/keywords/compositing","display_name":"Compositing","score":0.38839998841285706},{"id":"https://openalex.org/keywords/non-linear-editing-system","display_name":"Non-linear editing system","score":0.3662000000476837}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8830000162124634},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.786300003528595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6532999873161316},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6492000222206116},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.5823000073432922},{"id":"https://openalex.org/C106030495","wikidata":"https://www.wikidata.org/wiki/Q1797012","display_name":"Video compression picture types","level":4,"score":0.5066999793052673},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.5052000284194946},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.48750001192092896},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.4381999969482422},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.4104999899864197},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3946000039577484},{"id":"https://openalex.org/C151211776","wikidata":"https://www.wikidata.org/wiki/Q2778015","display_name":"Video capture","level":3,"score":0.388700008392334},{"id":"https://openalex.org/C129315195","wikidata":"https://www.wikidata.org/wiki/Q1121886","display_name":"Compositing","level":3,"score":0.38839998841285706},{"id":"https://openalex.org/C137402728","wikidata":"https://www.wikidata.org/wiki/Q1330119","display_name":"Non-linear editing system","level":5,"score":0.3662000000476837},{"id":"https://openalex.org/C32653426","wikidata":"https://www.wikidata.org/wiki/Q3813641","display_name":"Background subtraction","level":3,"score":0.35519999265670776},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.35510000586509705},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3425999879837036},{"id":"https://openalex.org/C2779769447","wikidata":"https://www.wikidata.org/wiki/Q3813641","display_name":"Foreground detection","level":4,"score":0.3301999866962433},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.328000009059906},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3181999921798706},{"id":"https://openalex.org/C23431618","wikidata":"https://www.wikidata.org/wiki/Q1404672","display_name":"Multiview Video Coding","level":4,"score":0.304500013589859},{"id":"https://openalex.org/C2776673561","wikidata":"https://www.wikidata.org/wiki/Q655357","display_name":"Atlas (anatomy)","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C2776566319","wikidata":"https://www.wikidata.org/wiki/Q3495514","display_name":"Interactive video","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C117090137","wikidata":"https://www.wikidata.org/wiki/Q7927977","display_name":"Video post-processing","level":5,"score":0.29910001158714294},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.29739999771118164},{"id":"https://openalex.org/C166142869","wikidata":"https://www.wikidata.org/wiki/Q60061622","display_name":"Video production","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C146044194","wikidata":"https://www.wikidata.org/wiki/Q5157334","display_name":"Computational photography","level":4,"score":0.27900001406669617},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C108803254","wikidata":"https://www.wikidata.org/wiki/Q857512","display_name":"Smacker video","level":4,"score":0.2770000100135803},{"id":"https://openalex.org/C30814859","wikidata":"https://www.wikidata.org/wiki/Q4119603","display_name":"Video denoising","level":5,"score":0.26989999413490295},{"id":"https://openalex.org/C167510206","wikidata":"https://www.wikidata.org/wiki/Q2835824","display_name":"Block-matching algorithm","level":4,"score":0.2653000056743622},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.2551000118255615}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2026.3652425","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3652425","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4212941527366638}],"awards":[{"id":"https://openalex.org/G1672266476","display_name":null,"funder_award_id":"11300-312200502507","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G2287201929","display_name":null,"funder_award_id":"62476133","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2757873042","display_name":null,"funder_award_id":"62576099","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G756906411","display_name":null,"funder_award_id":"RF1028625087","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/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Decomposition-based":[0],"text-guided":[1,220],"video":[2,17,26,132,197,216,221,226],"editing":[3,134,222],"paradigm":[4],"aims":[5],"to":[6,13,96,111,123,155,188],"utilize":[7],"the":[8,15,25,36,70,138,162,168,174,182,200,212],"layered":[9],"neural":[10],"atlas":[11,61,104],"model":[12],"decompose":[14,113],"input":[16],"into":[18,115],"foreground":[19,71,116,128,164,184],"and":[20,23,34,117,166,217,225],"background":[21,118,158],"parts":[22],"edit":[24],"in":[27,77],"a":[28,59,87,146],"divide-and-conquer":[29],"manner,":[30],"which":[31],"is":[32,67],"meaningful":[33],"improves":[35],"controllability":[37],"of":[38,51,101,196,202,214],"editing.":[39],"However,":[40],"they":[41],"may":[42],"suffer":[43],"from":[44],"some":[45],"limitations:":[46],"1)":[47],"High":[48],"computational":[49],"cost":[50],"per-video":[52],"training":[53,58,102],"(i.e,":[54],"7\u223c8":[55],"hours":[56],"for":[57],"single":[60],"model).":[62],"2)":[63],"Foreground":[64],"object":[65],"deformation":[66],"restricted":[68],"by":[69,161,180],"opacity":[72],"value.":[73],"3)":[74],"Restricted":[75],"flexibility":[76],"manipulating":[78],"multiple":[79],"objects.":[80,172],"In":[81,186],"this":[82],"paper,":[83],"we":[84,144],"propose":[85],"TraFrCo,":[86],"<italic":[88],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[89],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Training-Free":[90],"Controllable":[91],"Text-guided":[92],"Video":[93],"Editing</i>":[94],"framework":[95],"mitigate":[97],"these":[98],"challenges.":[99],"Instead":[100],"complex":[103],"models,":[105],"our":[106,208],"method":[107],"leverages":[108],"pre-trained":[109],"segmentation":[110],"rapidly":[112],"videos":[114],"parts.":[119],"This":[120],"allows":[121],"users":[122],"perform":[124],"independent":[125],"edits":[126],"on":[127],"objects":[129],"using":[130],"existing":[131],"diffusion":[133],"models":[135],"without":[136,199],"affecting":[137],"environment.":[139],"To":[140],"ensure":[141],"visual":[142],"consistency,":[143],"introduce":[145],"training-free":[147],"mechanism":[148],"that":[149,207],"effectively":[150],"propagates":[151],"information":[152],"across":[153],"frames":[154],"fill":[156],"missing":[157],"regions":[159],"caused":[160],"segmentation-derived":[163],"masks":[165],"reconstructs":[167],"scene":[169],"behind":[170],"moving":[171],"Finally,":[173],"edited":[175],"components":[176],"are":[177],"seamlessly":[178],"composited":[179],"re-predicting":[181],"new":[183],"masks.":[185],"contrast":[187],"prior":[189],"works,":[190],"TraFrCo":[191,209],"enables":[192],"efficient,":[193],"fine-grained":[194],"manipulation":[195],"content":[198],"burden":[201],"training.":[203],"Experimental":[204],"results":[205],"verify":[206],"consistently":[210],"reduces":[211],"costs":[213],"decomposing":[215],"achieves":[218],"superior":[219],"performance.":[223],"Codes":[224],"demos":[227],"will":[228],"be":[229],"released":[230],"at":[231],"https://github.com/mdswyz/TraFrCo.":[232]},"counts_by_year":[],"updated_date":"2026-05-07T06:04:25.777469","created_date":"2026-01-14T00:00:00"}
