{"id":"https://openalex.org/W7204456683","doi":"https://doi.org/10.48550/arxiv.2608.26101","title":"RefVideo-6M: A Reliable Reference-Based Dataset for Instructional Video Editing","display_name":"RefVideo-6M: A Reliable Reference-Based Dataset for Instructional Video Editing","publication_year":2026,"publication_date":"2026-08-26","ids":{"openalex":"https://openalex.org/W7204456683","doi":"https://doi.org/10.48550/arxiv.2608.26101"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2608.26101","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.26101","pdf_url":"https://arxiv.org/pdf/2608.26101","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.26101","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003572809","display_name":"Bojia Zi","orcid":"https://orcid.org/0009-0003-6283-895X","observed_orcids":["https://orcid.org/0009-0003-6283-895X"]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":"CN","type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Zi, Bojia","raw_affiliation_strings":["Institute of Artificial Intelligence , China Telecom (TeleAI) ,","The Chinese University of Hong Kong (CUHK) ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence , China Telecom (TeleAI) ,","institution_ids":["https://openalex.org/I4387153335"]},{"raw_affiliation_string":"The Chinese University of Hong Kong (CUHK) ,","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125252474","display_name":"Xiaoyan Yang","orcid":"https://orcid.org/0009-0003-9666-4054","observed_orcids":["https://orcid.org/0009-0003-9666-4054"]},"institutions":[{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":"CN","type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang, Xiaoyan","raw_affiliation_strings":["Institute of Artificial Intelligence , China Telecom (TeleAI) ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence , China Telecom (TeleAI) ,","institution_ids":["https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123141303","display_name":"Yu Zhou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":"CN","type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou, Yu","raw_affiliation_strings":["Institute of Artificial Intelligence , China Telecom (TeleAI) ,","Sun Yat-sen University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence , China Telecom (TeleAI) ,","institution_ids":["https://openalex.org/I4387153335"]},{"raw_affiliation_string":"Sun Yat-sen University ,","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125232280","display_name":"Ruijie Sun","orcid":null,"observed_orcids":[]},"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"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":"CN","type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sun, Ruijie","raw_affiliation_strings":["Fudan University ,","Institute of Artificial Intelligence , China Telecom (TeleAI) ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University ,","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Institute of Artificial Intelligence , China Telecom (TeleAI) ,","institution_ids":["https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125233677","display_name":"Lihan Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":"CN","type":"company","lineage":["https://openalex.org/I4387153335"]},{"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":"Zhang, Lihan","raw_affiliation_strings":["Institute of Artificial Intelligence , China Telecom (TeleAI) ,","Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence , China Telecom (TeleAI) ,","institution_ids":["https://openalex.org/I4387153335"]},{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126971590","display_name":"Bin Liang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Liang, Bin","raw_affiliation_strings":["The Chinese University of Hong Kong (CUHK) ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong (CUHK) ,","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008208316","display_name":"Kam\u2010Fai Wong","orcid":"https://orcid.org/0000-0002-9427-5659","observed_orcids":["https://orcid.org/0000-0002-9427-5659"]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wong, Kam-Fai","raw_affiliation_strings":["The Chinese University of Hong Kong (CUHK) ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong (CUHK) ,","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122929890","display_name":"Haibin Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":"CN","type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huang, Haibin","raw_affiliation_strings":["Institute of Artificial Intelligence , China Telecom (TeleAI) ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence , China Telecom (TeleAI) ,","institution_ids":["https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122937668","display_name":"Chi Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Chi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5125178434","display_name":"Xuelong Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":"CN","type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Xuelong","raw_affiliation_strings":["Institute of Artificial Intelligence , China Telecom (TeleAI) ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence , China Telecom (TeleAI) ,","institution_ids":["https://openalex.org/I4387153335"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9994999766349792,"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":0.9994999766349792,"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":9.999999747378752e-05,"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/T12357","display_name":"Digital Media Forensic Detection","score":9.999999747378752e-05,"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":0.8349999785423279},{"id":"https://openalex.org/keywords/image-editing","display_name":"image editing","score":0.718999981880188},{"id":"https://openalex.org/keywords/visual-correspondence","display_name":"visual correspondence","score":0.5699999928474426}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8707000017166138},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7660999894142151},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.7648000121116638},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.7529000043869019},{"id":"https://openalex.org/C137402728","wikidata":"https://www.wikidata.org/wiki/Q1330119","display_name":"Non-linear editing system","level":5,"score":0.6044999957084656},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5760999917984009},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4465999901294708},{"id":"https://openalex.org/C87829876","wikidata":"https://www.wikidata.org/wiki/Q648877","display_name":"Post-production","level":2,"score":0.44020000100135803},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3944999873638153},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3314000070095062},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32100000977516174},{"id":"https://openalex.org/C2780967703","wikidata":"https://www.wikidata.org/wiki/Q2571389","display_name":"Collaborative editing","level":2,"score":0.31850001215934753},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.26829999685287476}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.26101","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.26101","pdf_url":"https://arxiv.org/pdf/2608.26101","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.26101","doi":"https://doi.org/10.48550/arxiv.2608.26101","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.26101","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.26101","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.26101","pdf_url":"https://arxiv.org/pdf/2608.26101","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4156000018119812,"display_name":"Quality education"}],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/4","score":0.7134627103805542,"display_name":"Quality education"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204456683.pdf","grobid_xml":"https://content.openalex.org/works/W7204456683.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2],"video":[3,78,149],"editing":[4,30,73,79,85,103,112,128,150,182],"have":[5],"been":[6],"largely":[7],"driven":[8],"by":[9,28],"large-scale":[10,71],"instruction-based":[11],"datasets.":[12],"However,":[13],"existing":[14,174],"datasets":[15,44,175],"still":[16],"suffer":[17],"from":[18],"two":[19],"critical":[20],"limitations.":[21],"First,":[22],"target":[23],"videos":[24,101],"are":[25,55],"commonly":[26],"produced":[27],"automatic":[29],"models,":[31],"which":[32],"may":[33],"introduce":[34,68],"visible":[35],"artifacts":[36],"and":[37,60,81,105,127,157,176,189],"unreliable":[38],"supervision":[39,172],"signals.":[40],"Second,":[41],"most":[42],"public":[43],"rely":[45],"primarily":[46],"on":[47,142],"textual":[48],"instructions,":[49],"while":[50],"lacking":[51],"visual":[52,121,136,186],"references":[53],"that":[54,97,166],"crucial":[56],"for":[57],"precise,":[58],"identity-preserving,":[59],"controllable":[61],"editing.":[62],"To":[63,87],"address":[64],"these":[65],"limitations,":[66],"we":[67,144],"RefVideo-6M,":[69,143],"a":[70,94,147],"reference-guided":[72,148],"dataset":[74,92,194],"containing":[75],"5":[76],"million":[77,83,120],"samples":[80],"1":[82],"image":[84],"samples.":[86],"ensure":[88],"reliable":[89,171],"supervision,":[90],"our":[91],"uses":[93],"construction":[95],"pipeline":[96],"treats":[98],"artifact-free":[99],"real":[100],"as":[102],"targets":[104],"generates":[106],"quality-filtered":[107],"input":[108],"conditions":[109],"with":[110,184],"multiple":[111],"experts.":[113],"In":[114],"addition,":[115],"it":[116],"provides":[117,168],"approximately":[118],"6":[119],"references,":[122],"covering":[123],"diverse":[124],"reference":[125,190],"types":[126],"scenarios,":[129],"thereby":[130],"enabling":[131],"models":[132,183],"to":[133,153],"learn":[134],"fine-grained":[135],"correspondence":[137],"beyond":[138],"text-only":[139],"instructions.":[140],"Based":[141],"further":[145],"train":[146],"model,":[151],"Ref-MoT,":[152],"evaluate":[154],"the":[155,160,178],"effectiveness":[156],"scalability":[158],"of":[159,180],"proposed":[161],"dataset.":[162],"Extensive":[163],"experiments":[164],"demonstrate":[165],"RefVideo-6M":[167],"substantially":[169],"more":[170],"than":[173],"enables":[177],"training":[179],"powerful":[181],"improved":[185],"quality,":[187],"controllability,":[188],"consistency.":[191],"The":[192],"open-source":[193],"is":[195],"available":[196],"at":[197],"https://huggingface.co/datasets/RefVideo6M/RefVideo6M.":[198]},"counts_by_year":[],"updated_date":"2026-10-07T09:51:55.459714","created_date":"2026-08-28T00:00:00"}
