{"id":"https://openalex.org/W2963807156","doi":"https://doi.org/10.1109/cvpr.2018.00374","title":"Visual to Sound: Generating Natural Sound for Videos in the Wild","display_name":"Visual to Sound: Generating Natural Sound for Videos in the Wild","publication_year":2018,"publication_date":"2018-06-01","ids":{"openalex":"https://openalex.org/W2963807156","doi":"https://doi.org/10.1109/cvpr.2018.00374","mag":"2963807156"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr.2018.00374","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2018.00374","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","raw_type":"proceedings-article"},"type":"article","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/A5110374716","display_name":"Yipin Zhou","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yipin Zhou","raw_affiliation_strings":["University of North Carolina at Chapel Hill"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of North Carolina at Chapel Hill","institution_ids":["https://openalex.org/I114027177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068625652","display_name":"Zhaowen Wang","orcid":"https://orcid.org/0000-0002-4605-2506"},"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":"Zhaowen Wang","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/A5100400043","display_name":"Fang Chen","orcid":"https://orcid.org/0000-0003-4971-8729"},"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":"Chen Fang","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/A5113663962","display_name":"Trung Bui","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":"Trung Bui","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008309880","display_name":"Tamara L. Berg","orcid":"https://orcid.org/0000-0002-1272-3359"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tamara L. Berg","raw_affiliation_strings":["University of North Carolina at Chapel Hill"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of North Carolina at Chapel Hill","institution_ids":["https://openalex.org/I114027177"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":17.1259,"has_fulltext":false,"cited_by_count":210,"citation_normalized_percentile":{"value":0.9947859,"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":"3550","last_page":"3558"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9973999857902527,"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/computer-science","display_name":"Computer science","score":0.8019303679466248},{"id":"https://openalex.org/keywords/sight","display_name":"Sight","score":0.5830700397491455},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.580707848072052},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.563970685005188},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5105994343757629},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.4887406826019287},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.47627633810043335},{"id":"https://openalex.org/keywords/natural-sounds","display_name":"Natural sounds","score":0.46519172191619873},{"id":"https://openalex.org/keywords/virtual-reality","display_name":"Virtual reality","score":0.46356236934661865},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45785486698150635},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45155441761016846},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4305148720741272},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4277116060256958},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.41645291447639465},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1545061469078064},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08085110783576965}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8019303679466248},{"id":"https://openalex.org/C1517167","wikidata":"https://www.wikidata.org/wiki/Q1134322","display_name":"Sight","level":2,"score":0.5830700397491455},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.580707848072052},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.563970685005188},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5105994343757629},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4887406826019287},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.47627633810043335},{"id":"https://openalex.org/C2780646970","wikidata":"https://www.wikidata.org/wiki/Q6980787","display_name":"Natural sounds","level":2,"score":0.46519172191619873},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.46356236934661865},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45785486698150635},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45155441761016846},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4305148720741272},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4277116060256958},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.41645291447639465},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1545061469078064},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08085110783576965},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr.2018.00374","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2018.00374","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","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":45,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W1522301498","https://openalex.org/W1600722501","https://openalex.org/W1686810756","https://openalex.org/W2016053056","https://openalex.org/W2033959528","https://openalex.org/W2064675550","https://openalex.org/W2099471712","https://openalex.org/W2102003408","https://openalex.org/W2108598243","https://openalex.org/W2117418893","https://openalex.org/W2129142580","https://openalex.org/W2130942839","https://openalex.org/W2150658333","https://openalex.org/W2156303437","https://openalex.org/W2157331557","https://openalex.org/W2511428026","https://openalex.org/W2519091744","https://openalex.org/W2524365899","https://openalex.org/W2556930864","https://openalex.org/W2584032004","https://openalex.org/W2593116425","https://openalex.org/W2619697695","https://openalex.org/W2780568882","https://openalex.org/W2901997113","https://openalex.org/W2949382160","https://openalex.org/W2949888546","https://openalex.org/W2962756039","https://openalex.org/W2962835968","https://openalex.org/W2963066677","https://openalex.org/W2964121744","https://openalex.org/W2964345931","https://openalex.org/W4293665662","https://openalex.org/W4320013936","https://openalex.org/W6600983433","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6675380101","https://openalex.org/W6679436768","https://openalex.org/W6682864246","https://openalex.org/W6725104640","https://openalex.org/W6729831399","https://openalex.org/W6729977899","https://openalex.org/W6732429163","https://openalex.org/W6756197946"],"related_works":["https://openalex.org/W3214178347","https://openalex.org/W2353119552","https://openalex.org/W2364379655","https://openalex.org/W2808673637","https://openalex.org/W2408516727","https://openalex.org/W4312089944","https://openalex.org/W2031813887","https://openalex.org/W2355100508","https://openalex.org/W2169277706","https://openalex.org/W2071981547"],"abstract_inverted_index":{"As":[0,81],"two":[1,32],"of":[2,47,108,113],"the":[3,24,45,127,139],"five":[4],"traditional":[5],"human":[6,38],"senses":[7],"(sight,":[8],"hearing,":[9],"taste,":[10],"smell,":[11],"and":[12,15,119,133],"touch),":[13],"vision":[14],"sound":[16,49,63],"are":[17,130],"basic":[18],"sources":[19],"through":[20],"which":[21],"humans":[22],"understand":[23],"world.":[25],"Often":[26],"correlated":[27],"during":[28],"natural":[29],"events,":[30],"these":[31],"modalities":[33],"combine":[34],"to":[35,72,92],"jointly":[36],"affect":[37],"perception.":[39],"In":[40],"this":[41,86],"paper,":[42],"we":[43,88],"pose":[44],"task":[46],"generating":[48],"given":[50,97],"visual":[51,79,140],"input.":[52],"Such":[53],"capabilities":[54],"could":[55],"help":[56],"enable":[57],"applications":[58],"in":[59,85],"virtual":[60,65],"reality":[61],"(generating":[62],"for":[64,76],"scenes":[66],"automatically)":[67],"or":[68,74],"provide":[69],"additional":[70],"accessibility":[71],"images":[73],"videos":[75,109],"people":[77],"with":[78,138],"impairments.":[80],"a":[82,106,111],"first":[83],"step":[84],"direction,":[87],"apply":[89],"learning-based":[90],"methods":[91],"generate":[93],"raw":[94],"waveform":[95],"samples":[96],"input":[98],"video":[99],"frames.":[100],"We":[101],"evaluate":[102],"our":[103],"models":[104],"on":[105],"dataset":[107],"containing":[110],"variety":[112],"sounds":[114,118,120,129],"(such":[115],"as":[116],"ambient":[117],"from":[121],"people/animals).":[122],"Our":[123],"experiments":[124],"show":[125],"that":[126],"generated":[128],"fairly":[131],"realistic":[132],"have":[134],"good":[135],"temporal":[136],"synchronization":[137],"inputs.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":21},{"year":2023,"cited_by_count":38},{"year":2022,"cited_by_count":21},{"year":2021,"cited_by_count":37},{"year":2020,"cited_by_count":30},{"year":2019,"cited_by_count":31},{"year":2018,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
