{"id":"https://openalex.org/W4402090583","doi":"https://doi.org/10.1145/3691344","title":"Edit Temporal-Consistent Videos with Image Diffusion Model","display_name":"Edit Temporal-Consistent Videos with Image Diffusion Model","publication_year":2024,"publication_date":"2024-08-31","ids":{"openalex":"https://openalex.org/W4402090583","doi":"https://doi.org/10.1145/3691344"},"language":"en","primary_location":{"id":"doi:10.1145/3691344","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3691344","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3691344","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3691344","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016974436","display_name":"Yuanzhi Wang","orcid":"https://orcid.org/0000-0003-2594-2574"},"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":true,"raw_author_name":"Yuanzhi Wang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","School of Computer Science and Engineering, Nanjing University of Science and Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100355406","display_name":"Yong Li","orcid":"https://orcid.org/0000-0002-6521-5921"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yong Li","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Hong Kong, China","Department of Computer Science, City University of Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]},{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100718904","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","School of Computer Science and Engineering, Nanjing University of Science and Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077965912","display_name":"Xin Liu","orcid":"https://orcid.org/0009-0005-9804-7206"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Liu","raw_affiliation_strings":["SeetaCloud, Nanjing, China","SeetaCloud, China"],"affiliations":[{"raw_affiliation_string":"SeetaCloud, Nanjing, China","institution_ids":[]},{"raw_affiliation_string":"SeetaCloud, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113360387","display_name":"A.J. Dai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anbo Dai","raw_affiliation_strings":["SeetaCloud, Nanjing, China","SeetaCloud, China"],"affiliations":[{"raw_affiliation_string":"SeetaCloud, Nanjing, China","institution_ids":[]},{"raw_affiliation_string":"SeetaCloud, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065680386","display_name":"Antoni B. Chan","orcid":"https://orcid.org/0000-0002-2886-2513"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Antoni B. Chan","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Hong Kong, China","Department of Computer Science, City University of Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]},{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025396815","display_name":"Zhen Cui","orcid":"https://orcid.org/0000-0002-0543-4196"},"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":"Zhen Cui","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","School of Computer Science and Engineering, Nanjing University of Science and Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5016974436"],"corresponding_institution_ids":["https://openalex.org/I36399199"],"apc_list":null,"apc_paid":null,"fwci":2.3371,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.89806003,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"20","issue":"12","first_page":"1","last_page":"16"},"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":0.9993000030517578,"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":0.9993000030517578,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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":0.9940999746322632,"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/computer-science","display_name":"Computer science","score":0.8647623062133789},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4799485504627228},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.45442014932632446},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.42957356572151184},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42265939712524414},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.414157509803772}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8647623062133789},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4799485504627228},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.45442014932632446},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42957356572151184},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42265939712524414},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.414157509803772},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3691344","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3691344","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3691344","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},{"is_oa":true,"landing_page_url":"https://scholars.cityu.edu.hk/en/publications/edit-temporal-consistent-videos-with-image-diffusion-model","pdf_url":null,"source":{"id":"https://openalex.org/S7407055387","display_name":"CityU Scholars","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"WANG, Y, LI, Y, ZHANG, X, LIU, X, DAI, A, CHAN, A B & CUI, Z 2024, 'Edit Temporal-Consistent Videos with Image Diffusion Model', ACM Transactions on Multimedia Computing, Communications and Applications, vol. 20, no. 12, 368. https://doi.org/10.1145/3691344","raw_type":"article"},{"id":"pmh:oai:pure.atira.dk:publications/845ef954-2dbd-4743-8325-47be873ed2d3","is_oa":true,"landing_page_url":"https://hdl.handle.net/2031/845ef954-2dbd-4743-8325-47be873ed2d3","pdf_url":null,"source":{"id":"https://openalex.org/S7407055387","display_name":"CityU Scholars","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"WANG, Y, LI, Y, ZHANG, X, LIU, X, DAI, A, CHAN, A B & CUI, Z 2024, 'Edit Temporal-Consistent Videos with Image Diffusion Model', ACM Transactions on Multimedia Computing, Communications and Applications, vol. 20, no. 12, 368. https://doi.org/10.1145/3691344","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1145/3691344","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3691344","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3691344","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4402090583.pdf"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2765811365","https://openalex.org/W2819579046","https://openalex.org/W2962770929","https://openalex.org/W3035574324","https://openalex.org/W3135367836","https://openalex.org/W3216352822","https://openalex.org/W4206046513","https://openalex.org/W4281485151","https://openalex.org/W4291433229","https://openalex.org/W4312872987","https://openalex.org/W4312933868","https://openalex.org/W4319316769","https://openalex.org/W4361271773","https://openalex.org/W4384069384","https://openalex.org/W4386057725","https://openalex.org/W4386066731","https://openalex.org/W4386071957","https://openalex.org/W4386072096","https://openalex.org/W4386075631","https://openalex.org/W4386076532","https://openalex.org/W4386113271","https://openalex.org/W4390871782","https://openalex.org/W4390872007","https://openalex.org/W4390872556","https://openalex.org/W4390872681","https://openalex.org/W4390872862","https://openalex.org/W4390873054","https://openalex.org/W4390873135","https://openalex.org/W4390874580","https://openalex.org/W4391884092","https://openalex.org/W4402709859","https://openalex.org/W6602344735","https://openalex.org/W6739901393","https://openalex.org/W6767384525","https://openalex.org/W6779823529","https://openalex.org/W6810793953"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Large-scale":[0],"text-to-image":[1],"(T2I)":[2],"diffusion":[3],"models":[4],"have":[5,35],"been":[6,37],"extended":[7],"for":[8,60,76,142],"text-guided":[9,62],"video":[10,15,63,96,143,160,164],"editing,":[11],"yielding":[12],"impressive":[13],"zero-shot":[14],"editing":[16,165],"performance.":[17],"Nonetheless,":[18],"the":[19,30,56,68,90,94,105,121,125,131,135,140,171],"generated":[20,136],"videos":[21,34,137],"usually":[22],"show":[23],"spatial":[24,77],"irregularities":[25],"and":[26,102,107,149,163],"temporal":[27,31,57,84,91,122,132,161],"inconsistencies":[28],"as":[29],"characteristics":[32],"of":[33,70,93,134],"not":[36],"faithfully":[38,88],"modeled.":[39],"In":[40,65],"this":[41],"article,":[42],"we":[43,80],"propose":[44],"an":[45],"elegant":[46],"yet":[47],"effective":[48],"Temporal-Consistent":[49],"Video":[50],"Editing":[51],"(TCVE)":[52],"method":[53],"to":[54,67,87,99],"mitigate":[55],"inconsistency":[58],"challenge":[59],"robust":[61],"editing.":[64],"addition":[66],"utilization":[69],"a":[71,82,110],"pretrained":[72,126],"T2I":[73],"2D":[74,127],"Unet":[75,85,123],"content":[78,144],"manipulation,":[79],"establish":[81,100],"dedicated":[83],"architecture":[86],"capture":[89],"coherence":[92,101],"input":[95],"sequences.":[97],"Furthermore,":[98],"interrelation":[103],"between":[104],"spatial-focused":[106],"temporal-focused":[108],"components,":[109],"cohesive":[111],"spatial-temporal":[112],"modeling":[113],"unit":[114,118],"is":[115],"formulated.":[116],"This":[117],"effectively":[119],"interconnects":[120],"with":[124],"Unet,":[128],"thereby":[129],"enhancing":[130],"consistency":[133,162],"while":[138],"preserving":[139],"capacity":[141],"manipulation.":[145],"Quantitative":[146],"experimental":[147],"results":[148,151],"visualization":[150],"demonstrate":[152],"that":[153],"TCVE":[154],"achieves":[155],"state-of-the-art":[156],"performance":[157],"in":[158,170],"both":[159],"capability,":[166],"surpassing":[167],"existing":[168],"benchmarks":[169],"field.":[172],"Codes":[173],"are":[174],"released":[175],"at":[176],"https://github.com/mdswyz/TCVE":[177],".":[178]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}