{"id":"https://openalex.org/W4414360378","doi":"https://doi.org/10.24963/ijcai.2025/1118","title":"ExVideo: Extending Video Diffusion Models via Parameter-Efficient Post-Tuning","display_name":"ExVideo: Extending Video Diffusion Models via Parameter-Efficient Post-Tuning","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360378","doi":"https://doi.org/10.24963/ijcai.2025/1118"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/1118","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/1118","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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/A5040636331","display_name":"Zhongjie Duan","orcid":"https://orcid.org/0000-0002-5973-8240"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Zhongjie Duan","raw_affiliation_strings":["Alibaba Group","East China Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]},{"raw_affiliation_string":"East China Normal University","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112375500","display_name":"Hong Zhang","orcid":"https://orcid.org/0000-0002-7544-0786"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Hong Zhang","raw_affiliation_strings":["Alibaba Group","Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]},{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113261115","display_name":"Wenmeng Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenmeng Zhou","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114734448","display_name":"Cen Chen","orcid":"https://orcid.org/0000-0003-0325-1705"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cen Chen","raw_affiliation_strings":["East China Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046576694","display_name":"Yaliang Li","orcid":"https://orcid.org/0000-0002-4204-6096"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yaliang Li","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100733296","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0002-0043-4904"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104162468","display_name":"Yingda Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yingda Chen","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":"10063","last_page":"10071"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.9595999717712402,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9595999717712402,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9447000026702881,"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/T11304","display_name":"Advanced Neuroimaging Techniques and Applications","score":0.9196000099182129,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6315000057220459},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.460099995136261},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.4415000081062317},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.43130001425743103},{"id":"https://openalex.org/keywords/view-synthesis","display_name":"View synthesis","score":0.41019999980926514},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4050000011920929},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4011000096797943},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.3716999888420105}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8062000274658203},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6315000057220459},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4681999981403351},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.460099995136261},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.4415000081062317},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.43130001425743103},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.41019999980926514},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4050000011920929},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4011000096797943},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3804999887943268},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3716999888420105},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.3465000092983246},{"id":"https://openalex.org/C117090137","wikidata":"https://www.wikidata.org/wiki/Q7927977","display_name":"Video post-processing","level":5,"score":0.31279999017715454},{"id":"https://openalex.org/C23431618","wikidata":"https://www.wikidata.org/wiki/Q1404672","display_name":"Multiview Video Coding","level":4,"score":0.28940001130104065},{"id":"https://openalex.org/C30814859","wikidata":"https://www.wikidata.org/wiki/Q4119603","display_name":"Video denoising","level":5,"score":0.2892000079154968},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2870999872684479},{"id":"https://openalex.org/C106030495","wikidata":"https://www.wikidata.org/wiki/Q1797012","display_name":"Video compression picture types","level":4,"score":0.2809999883174896},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.2766999900341034},{"id":"https://openalex.org/C108803254","wikidata":"https://www.wikidata.org/wiki/Q857512","display_name":"Smacker video","level":4,"score":0.26829999685287476},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.2671000063419342},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2612000107765198},{"id":"https://openalex.org/C2988634675","wikidata":"https://www.wikidata.org/wiki/Q34508","display_name":"Video recording","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/1118","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/1118","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recently,":[0],"advancements":[1],"in":[2,20,166,182],"video":[3,31,40,48,60,75,167],"synthesis":[4,10,41,61,76],"have":[5,12,191],"attracted":[6],"significant":[7],"attention.":[8],"Video":[9,130],"models":[11,19,42],"demonstrated":[13],"the":[14,28,71,114,136,163,171,177,193,197],"practical":[15],"applicability":[16],"of":[17,30,73,116,147,154,185],"diffusion":[18],"creating":[21],"dynamic":[22],"visual":[23],"content.":[24],"Despite":[25],"these":[26],"advancements,":[27],"extension":[29,96],"lengths":[32],"remains":[33],"constrained":[34],"by":[35],"computational":[36],"resources.":[37],"Most":[38],"existing":[39],"are":[43],"limited":[44],"to":[45,69,80,139,142],"generating":[46,183],"short":[47],"clips.":[49],"In":[50,92],"this":[51],"paper,":[52],"we":[53,94,121],"propose":[54],"a":[55,157],"novel":[56],"post-tuning":[57,119],"methodology":[58],"for":[59],"models,":[62,77],"called":[63],"ExVideo.":[64],"This":[65],"approach":[66,134],"is":[67],"designed":[68],"enhance":[70],"capability":[72],"current":[74],"allowing":[78],"them":[79],"produce":[81],"content":[82],"over":[83],"extended":[84,125],"temporal":[85,100,107],"durations":[86],"while":[87],"incurring":[88],"lower":[89],"training":[90,155],"expenditures.":[91],"particular,":[93],"design":[95],"strategies":[97],"across":[98],"common":[99],"model":[101,126,178,199],"architectures":[102],"respectively,":[103],"including":[104],"3D":[105],"convolution,":[106],"attention,":[108],"and":[109,176,188,196],"positional":[110],"embedding.":[111],"To":[112],"evaluate":[113],"efficacy":[115],"our":[117],"proposed":[118],"approach,":[120],"trained":[122],"ExSVD,":[123],"an":[124],"based":[127],"on":[128,156],"Stable":[129],"Diffusion":[131],"model.":[132],"Our":[133],"enhances":[135],"model's":[137,172],"capacity":[138],"generate":[140],"up":[141],"5x":[143],"its":[144,180],"original":[145],"number":[146],"frames,":[148],"requiring":[149],"only":[150],"1.5k":[151],"GPU":[152],"hours":[153],"dataset":[158],"comprising":[159],"40k":[160],"videos.":[161],"Importantly,":[162],"substantial":[164],"increase":[165],"length":[168],"doesn't":[169],"compromise":[170],"innate":[173],"generalization":[174],"capabilities,":[175],"showcases":[179],"advantages":[181],"videos":[184],"diverse":[186],"styles":[187],"resolutions.":[189],"We":[190],"released":[192],"source":[194],"code":[195],"enhanced":[198],"publicly.":[200]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
