{"id":"https://openalex.org/W4415151869","doi":"https://doi.org/10.1109/iccv51701.2025.01477","title":"CAFA: A Controllable Automatic Foley Artist","display_name":"CAFA: A Controllable Automatic Foley Artist","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415151869","doi":"https://doi.org/10.1109/iccv51701.2025.01477"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01477","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01477","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","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/2504.06778","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119987360","display_name":"Roi Benita","orcid":null},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Roi Benita","raw_affiliation_strings":["Technion"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technion","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119987361","display_name":"Michael Finkelson","orcid":null},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Michael Finkelson","raw_affiliation_strings":["Hebrew University of Jerusalem"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hebrew University of Jerusalem","institution_ids":["https://openalex.org/I197251160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060032514","display_name":"Tavi Halperin","orcid":"https://orcid.org/0000-0001-9288-5392"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tavi Halperin","raw_affiliation_strings":["Lightricks"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lightricks","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080945641","display_name":"Gleb Sterkin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gleb Sterkin","raw_affiliation_strings":["Lightricks"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lightricks","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005191803","display_name":"Yossi Adi","orcid":"https://orcid.org/0000-0003-2237-3898"},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yossi Adi","raw_affiliation_strings":["Hebrew University of Jerusalem"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hebrew University of Jerusalem","institution_ids":["https://openalex.org/I197251160"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.42206367,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"15917","last_page":"15926"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9915000200271606,"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"}},"topics":[{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9915000200271606,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.984499990940094,"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/T12290","display_name":"Human Motion and Animation","score":0.9093000292778015,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/foley","display_name":"Foley","score":0.5924000144004822},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.40849998593330383},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.3935999870300293},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.3668000102043152},{"id":"https://openalex.org/keywords/adapter","display_name":"Adapter (computing)","score":0.35100001096725464},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3490000069141388},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.3325999975204468},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.3215999901294708}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.807699978351593},{"id":"https://openalex.org/C110446960","wikidata":"https://www.wikidata.org/wiki/Q762316","display_name":"Foley","level":2,"score":0.5924000144004822},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4724000096321106},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.40849998593330383},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.3935999870300293},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.3668000102043152},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.35100001096725464},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3490000069141388},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.3325999975204468},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.3215999901294708},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.321399986743927},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.3100000023841858},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.30730000138282776},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3010999858379364},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C150202949","wikidata":"https://www.wikidata.org/wiki/Q107602","display_name":"Pointer (user interface)","level":2,"score":0.2955999970436096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2883000075817108},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01477","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01477","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2504.06778","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.06778","pdf_url":"https://arxiv.org/pdf/2504.06778","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.2504.06778","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.06778","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:2504.06778","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.06778","pdf_url":"https://arxiv.org/pdf/2504.06778","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415151869.pdf","grobid_xml":"https://content.openalex.org/works/W4415151869.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Foley":[0,100],"is":[1,56,121],"a":[2,18,102,113,124,132],"key":[3],"element":[4],"in":[5,38,50,71,165,182],"video":[6,20,129,155],"production,":[7],"refers":[8],"to":[9,17,57,60],"the":[10,30,44,51,78,85,90,149,153,173],"process":[11],"of":[12,32,167],"adding":[13],"an":[14],"audio":[15,62,111,150],"signal":[16],"silent":[19],"while":[21],"ensuring":[22,72],"semantic":[23,142,168],"and":[24,36,108,127,144,170,184],"temporal":[25],"alignment.":[26],"In":[27,92],"recent":[28],"years,":[29],"rise":[31],"personalized":[33],"content":[34],"creation":[35],"advancements":[37],"automatic":[39],"video-to-audio":[40],"models":[41],"have":[42],"increased":[43],"demand":[45],"for":[46,112],"greater":[47],"user":[48],"control":[49],"process.":[52],"One":[53],"possible":[54],"approach":[55],"incorporate":[58],"text":[59,79,118],"guide":[61],"generation.":[63],"While":[64],"supported":[65],"by":[66,117],"existing":[67],"methods,":[68],"challenges":[69],"remain":[70],"compatibility":[73],"between":[74],"modalities,":[75],"particularly":[76],"when":[77],"introduces":[80],"additional":[81],"information":[82,130],"or":[83],"contradicts":[84],"sounds":[86],"naturally":[87],"inferred":[88],"from":[89],"visuals.":[91],"this":[93],"work,":[94],"we":[95],"introduce":[96,145],"CAFA":[97,120],"(Controllable":[98],"Automatic":[99],"Artist)":[101],"video-and-text-to-audio":[103],"model":[104,126],"that":[105,160],"generates":[106],"semantically":[107],"temporally":[109],"aligned":[110],"given":[114],"video,":[115],"guided":[116],"input.":[119],"built":[122],"upon":[123],"text-to-audio":[125],"integrates":[128],"through":[131],"modality":[133],"adapter":[134],"mechanism.":[135],"By":[136],"incorporating":[137],"text,":[138],"users":[139],"can":[140],"refine":[141],"details":[143],"creative":[146],"variations,":[147],"guiding":[148],"synthesis":[151],"beyond":[152],"expected":[154],"contextual":[156],"cues.":[157],"Experiments":[158],"show":[159],"besides":[161],"its":[162],"superior":[163],"quality":[164],"terms":[166],"alignment":[169],"audio-visual":[171],"synchronization":[172],"proposed":[174],"method":[175],"enable":[176],"high":[177],"textual":[178],"controllability":[179],"as":[180],"demonstrated":[181],"subjective":[183],"objective":[185],"evaluations.":[186]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-14T00:00:00"}
