{"id":"https://openalex.org/W4405090236","doi":"https://doi.org/10.1109/iccv51701.2025.01485","title":"DIVE: Taming DINO for Subject-Driven Video Editing","display_name":"DIVE: Taming DINO for Subject-Driven Video Editing","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4405090236","doi":"https://doi.org/10.1109/iccv51701.2025.01485"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01485","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01485","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 (ICCV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2412.03347","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100741261","display_name":"Yi Huang","orcid":"https://orcid.org/0000-0001-7774-1024"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Huang","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101398340","display_name":"Wei Xiong","orcid":"https://orcid.org/0000-0001-8679-6086"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Xiong","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100420147","display_name":"He Zhang","orcid":"https://orcid.org/0000-0003-2304-9387"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"He Zhang","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102751044","display_name":"Chaoqi Chen","orcid":"https://orcid.org/0000-0002-5645-7718"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaoqi Chen","raw_affiliation_strings":["Shenzhen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen University","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039205892","display_name":"Jianzhuang Liu","orcid":"https://orcid.org/0000-0002-7960-9382"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianzhuang Liu","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001434453","display_name":"Mingfu Yan","orcid":"https://orcid.org/0009-0000-4820-0704"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingfu Yan","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102827652","display_name":"Shifeng Chen","orcid":"https://orcid.org/0000-0002-3858-0309"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shifeng Chen","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210145761"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":0.00115119,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"16004","last_page":"16014"},"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":0.9107000231742859,"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":0.9107000231742859,"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/T13999","display_name":"Digital Rights Management and Security","score":0.9070000052452087,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/subject","display_name":"Subject (documents)","score":0.8104701042175293},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5642147660255432},{"id":"https://openalex.org/keywords/video-editing","display_name":"Video editing","score":0.44922935962677},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.34498071670532227},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.34442538022994995},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.28467464447021484}],"concepts":[{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.8104701042175293},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5642147660255432},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.44922935962677},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.34498071670532227},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.34442538022994995},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.28467464447021484}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01485","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01485","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 (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2412.03347","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.03347","pdf_url":"https://arxiv.org/pdf/2412.03347","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2412.03347","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.03347","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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:2412.03347","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.03347","pdf_url":"https://arxiv.org/pdf/2412.03347","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4388258507","https://openalex.org/W2392013855","https://openalex.org/W4318064328","https://openalex.org/W2357926602","https://openalex.org/W3200517220","https://openalex.org/W2374569605","https://openalex.org/W2386062718"],"abstract_inverted_index":{"Building":[0],"on":[1,51,137],"the":[2,69,84,100,104,113,131,155],"success":[3],"of":[4,64,103,116,157],"diffusion":[5],"models":[6],"in":[7,47,67],"image":[8],"generation":[9],"and":[10,23],"editing,":[11,110],"video":[12,162],"editing":[13,46,85,148],"has":[14],"recently":[15],"gained":[16],"substantial":[17],"attention.":[18],"However,":[19],"maintaining":[20],"temporal":[21,90],"consistency":[22],"motion":[24,91,101,152],"alignment":[25],"still":[26],"remains":[27],"challenging.":[28],"To":[29],"address":[30],"these":[31],"issues,":[32],"this":[33],"paper":[34],"proposes":[35],"DINO-guided":[36],"Video":[37],"Editing":[38],"(DIVE),":[39],"a":[40,75,120],"framework":[41,144],"designed":[42],"to":[43,82,88,97,124,159,161],"facilitate":[44],"subject-driven":[45],"source":[48,105],"videos":[49,140],"conditioned":[50],"either":[52],"target":[53,132],"text":[54],"prompts":[55],"or":[56],"reference":[57,117],"images":[58,118],"with":[59,99,150],"specific":[60],"identities.":[61],"The":[62],"core":[63],"DIVE":[65,93,111],"lies":[66],"leveraging":[68],"powerful":[70],"semantic":[71],"features":[72,96,115],"extracted":[73],"from":[74],"pretrained":[76,121],"DINOv2":[77],"model":[78,123],"as":[79],"implicit":[80],"correspondences":[81],"guide":[83],"process.":[86],"Specifically,":[87],"ensure":[89],"consistency,":[92,153],"employs":[94],"DINO":[95,114,158],"align":[98],"trajectory":[102],"video.":[106],"For":[107],"precise":[108],"subject":[109],"incorporates":[112],"into":[119],"text-to-image":[122],"learn":[125],"Low-Rank":[126],"Adaptations":[127],"(LoRAs),":[128],"effectively":[129],"registering":[130],"subject's":[133],"identity.":[134],"Extensive":[135],"experiments":[136],"diverse":[138],"real-world":[139],"demonstrate":[141],"that":[142],"our":[143],"can":[145],"achieve":[146],"high-quality":[147],"results":[149],"robust":[151],"highlighting":[154],"potential":[156],"contribute":[160],"editing.":[163],"Project":[164],"page:":[165],"https://dino-video-editing.github.io":[166]},"counts_by_year":[],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}
