{"id":"https://openalex.org/W4409049130","doi":"https://doi.org/10.1109/wacv61042.2026.00709","title":"Zero-Shot Audio-Visual Editing via Cross-Modal Delta Denoising","display_name":"Zero-Shot Audio-Visual Editing via Cross-Modal Delta Denoising","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4409049130","doi":"https://doi.org/10.1109/wacv61042.2026.00709"},"language":"en","primary_location":{"id":"doi:10.1109/wacv61042.2026.00709","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00709","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":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.20782","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100825527","display_name":"Yan-Bo Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]},{"id":"https://openalex.org/I1333535994","display_name":"University of North Carolina Health Care","ror":"https://ror.org/00qz24g20","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1333535994"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan-Bo Lin","raw_affiliation_strings":["UNC Chapel Hill"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UNC Chapel Hill","institution_ids":["https://openalex.org/I114027177","https://openalex.org/I1333535994"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108030232","display_name":"Kevin Lin","orcid":"https://orcid.org/0000-0001-8944-1336"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kevin Lin","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050209478","display_name":"Zhengyuan Yang","orcid":"https://orcid.org/0000-0002-5808-0889"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhengyuan Yang","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100657555","display_name":"Linjie Li","orcid":"https://orcid.org/0000-0003-0867-8863"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Linjie Li","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080691386","display_name":"Jianfeng Wang","orcid":"https://orcid.org/0000-0002-3156-4429"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jianfeng Wang","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100913271","display_name":"Chung-Ching Lin","orcid":"https://orcid.org/0009-0003-6507-3657"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chung-Ching Lin","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005333910","display_name":"Xiaofei Wang","orcid":"https://orcid.org/0000-0002-8482-6138"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xiaofei Wang","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081800468","display_name":"Gedas Bertasius","orcid":"https://orcid.org/0000-0003-1800-4790"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]},{"id":"https://openalex.org/I1333535994","display_name":"University of North Carolina Health Care","ror":"https://ror.org/00qz24g20","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1333535994"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gedas Bertasius","raw_affiliation_strings":["UNC Chapel Hill"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UNC Chapel Hill","institution_ids":["https://openalex.org/I114027177","https://openalex.org/I1333535994"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033113012","display_name":"Lijuan Wang","orcid":"https://orcid.org/0000-0002-5705-876X"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lijuan Wang","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]}],"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":0.00487662,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7344","last_page":"7354"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9850999712944031,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9850999712944031,"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/T11309","display_name":"Music and Audio Processing","score":0.977400004863739,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9674999713897705,"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/audio-visual","display_name":"Audio visual","score":0.8396538496017456},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.757713794708252},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6811827421188354},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6028504967689514},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5351824164390564},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5018787384033203},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.40791118144989014},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3217123746871948},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31643012166023254},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.22732409834861755},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.1437361240386963},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.06698739528656006},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.06252989172935486},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.05672580003738403}],"concepts":[{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.8396538496017456},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.757713794708252},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6811827421188354},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6028504967689514},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5351824164390564},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5018787384033203},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.40791118144989014},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3217123746871948},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31643012166023254},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.22732409834861755},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.1437361240386963},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.06698739528656006},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.06252989172935486},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.05672580003738403},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00709","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00709","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"},{"id":"pmh:oai:arXiv.org:2503.20782","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.20782","pdf_url":"https://arxiv.org/pdf/2503.20782","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,"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.2503.20782","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.20782","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,"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:2503.20782","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.20782","pdf_url":"https://arxiv.org/pdf/2503.20782","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,"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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2271369634","https://openalex.org/W2366718574","https://openalex.org/W3147472394","https://openalex.org/W2047100085"],"abstract_inverted_index":{"In":[0],"this":[1,30],"paper,":[2],"we":[3,32,104],"introduce":[4],"zero-shot":[5,41,81,108],"audio-video":[6,42,115],"editing,":[7],"a":[8,20,34,50,107],"novel":[9],"task":[10],"that":[11,64,113],"requires":[12],"transforming":[13],"original":[14],"audio-visual":[15],"content":[16],"to":[17,117,135],"align":[18],"with":[19,49],"specified":[21],"textual":[22],"prompt":[23],"without":[24],"additional":[25],"model":[26],"training.":[27],"To":[28,100],"evaluate":[29],"task,":[31],"curate":[33],"benchmark":[35],"dataset,":[36],"AVED-Bench,":[37],"designed":[38],"explicitly":[39],"for":[40],"editing.":[43],"AVED-Bench":[44,129],"includes":[45],"110":[46],"videos,":[47],"each":[48],"10-second":[51],"duration,":[52],"spanning":[53],"11":[54],"categories":[55],"from":[56],"VGGSound.":[57],"It":[58],"offers":[59],"diverse":[60],"prompts":[61],"and":[62,70,83,90,120,130,143],"scenarios":[63],"require":[65],"precise":[66],"alignment":[67],"between":[68,92],"auditory":[69],"visual":[71],"elements,":[72],"enabling":[73],"robust":[74],"evaluation.":[75],"We":[76],"identify":[77],"limitations":[78],"in":[79,88,97],"existing":[80],"audio":[82],"video":[84],"editing":[85],"methods,":[86],"particularly":[87],"synchronization":[89],"coherence":[91],"modalities,":[93],"which":[94],"often":[95],"result":[96],"inconsistent":[98],"outcomes.":[99],"address":[101],"these":[102],"challenges,":[103],"propose":[105],"AVED,":[106],"cross-modal":[109],"delta":[110],"denoising":[111],"framework":[112],"leverages":[114],"interactions":[116],"achieve":[118],"synchronized":[119],"coherent":[121],"edits.":[122],"AVED":[123],"demonstrates":[124],"superior":[125],"results":[126,144],"on":[127],"both":[128],"the":[131],"recent":[132],"OAVE":[133],"dataset":[134],"validate":[136],"its":[137],"generalization":[138],"capabilities.":[139],"Our":[140],"codes,":[141],"data,":[142],"are":[145],"available":[146],"at":[147],"https://genjib.github.io/project_page/AVED/index.html":[148]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}