{"id":"https://openalex.org/W4413144830","doi":"https://doi.org/10.1109/cvpr52734.2025.01749","title":"Video-Guided Foley Sound Generation with Multimodal Controls","display_name":"Video-Guided Foley Sound Generation with Multimodal Controls","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413144830","doi":"https://doi.org/10.1109/cvpr52734.2025.01749"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.01749","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01749","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5100324480","display_name":"Ziyang Chen","orcid":"https://orcid.org/0000-0001-8358-6083"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziyang Chen","raw_affiliation_strings":["University of Michigan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023673004","display_name":"Prem Seetharaman","orcid":null},"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":"Prem Seetharaman","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/A5053907649","display_name":"Bryan Russell","orcid":"https://orcid.org/0000-0001-8656-543X"},"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":"Bryan Russell","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/A5110542743","display_name":"Oriol Nieto","orcid":null},"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":"Oriol Nieto","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/A5075237025","display_name":"D. G. Bourgin","orcid":null},"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":"David Bourgin","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/A5103210329","display_name":"Andrew Owens","orcid":"https://orcid.org/0000-0002-3535-025X"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Owens","raw_affiliation_strings":["University of Michigan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037548450","display_name":"Justin Salamon","orcid":"https://orcid.org/0000-0001-6345-4593"},"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":"Justin Salamon","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":21.1094,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.99623076,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"18770","last_page":"18781"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9606000185012817,"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/T10860","display_name":"Speech and Audio Processing","score":0.9606000185012817,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7110294103622437},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5922465920448303},{"id":"https://openalex.org/keywords/foley","display_name":"Foley","score":0.5644063353538513},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.34469735622406006},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.18099305033683777}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7110294103622437},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5922465920448303},{"id":"https://openalex.org/C110446960","wikidata":"https://www.wikidata.org/wiki/Q762316","display_name":"Foley","level":2,"score":0.5644063353538513},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.34469735622406006},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.18099305033683777},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.01749","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01749","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"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/W2523036031","https://openalex.org/W4237383858","https://openalex.org/W3211743321","https://openalex.org/W2016968289","https://openalex.org/W2021759681","https://openalex.org/W2011071567","https://openalex.org/W4256291417"],"abstract_inverted_index":{"Generating":[0],"sound":[1,9,22,36,78,92],"effects":[2,10,93],"for":[3,34,99,158],"videos":[4,98],"often":[5],"requires":[6],"creating":[7],"artistic":[8],"that":[11,38,138],"diverge":[12],"significantly":[13],"from":[14,91],"real-life":[15],"sources":[16],"and":[17,45,51,120,133,149],"flexible":[18],"control":[19],"in":[20,108],"the":[21],"design.":[23],"To":[24],"address":[25],"this":[26],"problem,":[27],"we":[28,136],"introduce":[29],"MultiFoley,":[30],"a":[31,48,52,75,80],"model":[32,106],"designed":[33],"video-guided":[35],"generation":[37],"supports":[39],"multimodal":[40],"conditioning":[41],"through":[42],"text,":[43],"audio,":[44],"video.":[46],"Given":[47],"silent":[49],"video":[50,115,159],"text":[53],"prompt,":[54],"MultiFoley":[55,83,139],"allows":[56,85],"users":[57,86],"to":[58,87],"create":[59],"clean":[60],"sounds":[61,72,144],"(e.g.,":[62,73],"skateboard":[63],"wheels":[64],"spinning":[65],"without":[66],"wind":[67],"noise)":[68],"or":[69,96],"more":[70],"whimsical":[71],"making":[74],"lion\u2019s":[76],"roar":[77],"like":[79],"cat\u2019s":[81],"meow).":[82],"also":[84],"choose":[88],"reference":[89],"audio":[90,119,128],"(SFX)":[94],"libraries":[95],"partial":[97],"conditioning.":[100],"A":[101],"key":[102],"novelty":[103],"of":[104],"our":[105,155],"lies":[107],"its":[109],"joint":[110],"training":[111],"on":[112],"both":[113],"internet":[114],"datasets":[116],"with":[117],"low-quality":[118],"professional":[121],"SFX":[122],"recordings,":[123],"enabling":[124],"high-quality,":[125],"full-bandwidth":[126],"(48kHz)":[127],"generation.":[129],"Through":[130],"automated":[131],"evaluations":[132],"human":[134],"studies,":[135],"demonstrate":[137],"successfully":[140],"generates":[141],"synchronized":[142],"high-quality":[143],"across":[145],"varied":[146],"conditional":[147],"inputs":[148],"outperforms":[150],"existing":[151],"methods.":[152],"Please":[153],"see":[154],"project":[156],"page":[157],"results:":[160],"https://ificl.github.io/MultiFoley/":[161]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
