{"id":"https://openalex.org/W7160318186","doi":"https://doi.org/10.1109/wacv61042.2026.00594","title":"Align Video Diffusion Model with Online Video-Centric Preference Optimization","display_name":"Align Video Diffusion Model with Online Video-Centric Preference Optimization","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160318186","doi":"https://doi.org/10.1109/wacv61042.2026.00594"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00594","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00594","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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/A5053014122","display_name":"jingzhen zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiacheng Zhang","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135356146","display_name":"Jie Wu","orcid":"https://orcid.org/0009-0006-5333-011X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jie Wu","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135349264","display_name":"Weifeng Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weifeng Chen","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135321296","display_name":"Yatai Ji","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yatai Ji","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135340703","display_name":"Xuefeng Xiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuefeng Xiao","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135371030","display_name":"Weilin Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weilin Huang","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135298375","display_name":"Kai Han","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kai Han","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":"6142","last_page":"6152"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10741","display_name":"Video Coding and Compression Technologies","score":0.24570000171661377,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10741","display_name":"Video Coding and Compression Technologies","score":0.24570000171661377,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11165","display_name":"Image and Video Quality Assessment","score":0.09669999778270721,"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":0.06610000133514404,"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/preference","display_name":"Preference","score":0.3978999853134155},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.3246000111103058},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2621000111103058},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.2590000033378601},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.2565999925136566}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5827000141143799},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39820000529289246},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.3978999853134155},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3246000111103058},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.25920000672340393},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.24500000476837158},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.24210000038146973}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00594","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00594","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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":19,"referenced_works":["https://openalex.org/W3204588463","https://openalex.org/W4312933868","https://openalex.org/W4386071957","https://openalex.org/W4390872297","https://openalex.org/W4390872556","https://openalex.org/W4390873135","https://openalex.org/W4402660110","https://openalex.org/W4402670418","https://openalex.org/W4402716201","https://openalex.org/W4402727736","https://openalex.org/W4402727910","https://openalex.org/W4402753770","https://openalex.org/W4402753790","https://openalex.org/W4404782905","https://openalex.org/W4404965692","https://openalex.org/W4405695475","https://openalex.org/W4413146701","https://openalex.org/W7133195264","https://openalex.org/W7133217041"],"related_works":[],"abstract_inverted_index":{"Video":[0],"diffusion":[1,244],"models":[2,133,151],"(VDMs)":[3],"have":[4,31],"demonstrated":[5],"remarkable":[6],"capabilities":[7],"in":[8,51,111,187],"text-to-video":[9],"(T2V)":[10],"generation.":[11,43],"Despite":[12],"their":[13],"success,":[14],"VDMs":[15],"still":[16],"suffer":[17],"from":[18,75],"degraded":[19],"image":[20,53],"quality":[21,130],"and":[22,81,85,193,216],"flickering":[23],"artifacts.":[24],"To":[25],"address":[26],"these":[27,45],"issues,":[28],"some":[29],"approaches":[30],"introduced":[32],"preference":[33,61,73,91,120,166,214,218,239],"learning":[34,74,92,211,240],"to":[35,39,115,123,157],"exploit":[36],"human":[37,138],"feedback":[38,79,82,100,161],"enhance":[40],"the":[41,49,52,68,71,99,105,124,165,182,198,204,224],"video":[42,72,119,129,141,243],"However,":[44],"methods":[46,113],"primarily":[47],"adopt":[48],"routine":[50],"domain":[54],"without":[55],"an":[56,171],"in-depth":[57],"investigation":[58],"into":[59],"video-specific":[60],"optimization.":[62],"In":[63,127],"this":[64,145],"paper,":[65],"we":[66,102,147,169],"reexamine":[67],"design":[69],"of":[70,140,155,184],"two":[76],"key":[77],"aspects:":[78],"source":[80],"tuning":[83,167],"methodology,":[84,168],"present":[86],"OnlineVPO,":[87],"a":[88,117,153,231],"more":[89,159,236],"efficient":[90],"framework":[93],"tailored":[94,175],"specifically":[95],"for":[96,162,176,242],"VDMs.":[97,163,177],"On":[98],"source,":[101],"found":[103],"that":[104],"image-level":[106],"reward":[107],"model":[108,227],"commonly":[109],"used":[110],"existing":[112,199],"fails":[114],"provide":[116,158],"human-aligned":[118],"signal":[121],"due":[122],"modality":[125],"gap.":[126],"contrast,":[128],"assessment":[131],"(VQA)":[132],"show":[134],"superior":[135,185],"alignment":[136],"with":[137,190,197],"perception":[139],"quality.":[142],"Building":[143],"on":[144,223],"insight,":[146],"propose":[148],"leveraging":[149],"VQA":[150],"as":[152,230],"proxy":[154],"humans":[156],"modality-aligned":[160],"Regarding":[164],"introduce":[170],"online":[172,213],"DPO":[173],"algorithm":[174,241],"It":[178],"not":[179],"only":[180],"enjoys":[181],"benefits":[183],"scalability":[186],"optimizing":[188],"videos":[189],"higher":[191],"resolution":[192],"longer":[194],"duration":[195],"compared":[196],"method,":[200],"but":[201],"also":[202],"mitigates":[203],"insufficient":[205],"optimization":[206],"issue":[207],"caused":[208],"by":[209],"off-policy":[210],"via":[212],"generation":[215],"curriculum":[217],"update":[219],"designs.":[220],"Extensive":[221],"experiments":[222],"open-source":[225],"video-diffusion":[226],"demonstrate":[228],"OnlineVPO":[229],"simple":[232],"yet":[233],"effective":[234],"and,":[235],"importantly,":[237],"scalable":[238],"models.":[245]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-05-06T00:00:00"}
