{"id":"https://openalex.org/W2777181663","doi":"https://doi.org/10.48550/arxiv.1712.06651","title":"Objects that Sound","display_name":"Objects that Sound","publication_year":2017,"publication_date":"2017-12-18","ids":{"openalex":"https://openalex.org/W2777181663","doi":"https://doi.org/10.48550/arxiv.1712.06651","mag":"2777181663"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1712.06651","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1712.06651","pdf_url":"https://arxiv.org/pdf/1712.06651","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,"listed_in":[],"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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1712.06651","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015666723","display_name":"Relja Arandjelovi\u0107","orcid":"https://orcid.org/0000-0002-9232-4023","observed_orcids":["https://orcid.org/0000-0002-9232-4023"]},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Arandjelovi\u0107, Relja","raw_affiliation_strings":["DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057678172","display_name":"Andrew Zisserman","orcid":"https://orcid.org/0000-0002-8945-8573","observed_orcids":["https://orcid.org/0000-0002-8945-8573"]},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zisserman, Andrew","raw_affiliation_strings":["VGG , Department of Engineering Science , University of Oxford","University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VGG , Department of Engineering Science , University of Oxford","institution_ids":["https://openalex.org/I40120149"]},{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":24,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8070999979972839,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8070999979972839,"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":0.10040000081062317,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.0364999994635582,"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-correspondence","display_name":"audio-visual correspondence","score":0.8489999771118164},{"id":"https://openalex.org/keywords/cross-modal-retrieval","display_name":"cross-modal retrieval","score":0.9120000004768372},{"id":"https://openalex.org/keywords/sound-localization","display_name":"sound localization","score":0.7319999933242798},{"id":"https://openalex.org/keywords/self-supervised-learning","display_name":"self-supervised learning","score":0.7139999866485596},{"id":"https://openalex.org/keywords/optical-flow","display_name":"optical flow","score":0.7129999995231628},{"id":"https://openalex.org/keywords/shortcut-learning","display_name":"shortcut learning","score":0.6890000104904175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8506751656532288},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6850624680519104},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.6385480761528015},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6263752579689026},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6093697547912598},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5518848299980164},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5252732038497925},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.490652471780777},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.46966636180877686},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.43547362089157104},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.42128676176071167},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3476681709289551},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.22616267204284668},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.11916947364807129},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11169809103012085},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.0846271812915802},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:1712.06651","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1712.06651","pdf_url":"https://arxiv.org/pdf/1712.06651","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,"listed_in":[],"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":"mag:2777181663","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1712.06651","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,"listed_in":[],"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1712.06651","doi":"https://doi.org/10.48550/arxiv.1712.06651","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1712.06651","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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1712.06651","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1712.06651","pdf_url":"https://arxiv.org/pdf/1712.06651","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,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2777181663.pdf","grobid_xml":"https://content.openalex.org/works/W2777181663.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W219040644","https://openalex.org/W343636949","https://openalex.org/W1514535095","https://openalex.org/W1666447063","https://openalex.org/W1686810756","https://openalex.org/W1994488211","https://openalex.org/W2097117768","https://openalex.org/W2105582566","https://openalex.org/W2110119381","https://openalex.org/W2123024445","https://openalex.org/W2127025755","https://openalex.org/W2137471889","https://openalex.org/W2148349024","https://openalex.org/W2156303437","https://openalex.org/W2157364932","https://openalex.org/W2179042386","https://openalex.org/W2295107390","https://openalex.org/W2321533354","https://openalex.org/W2326925005","https://openalex.org/W2342877626","https://openalex.org/W2511428026","https://openalex.org/W2544224704","https://openalex.org/W2550462002","https://openalex.org/W2593116425","https://openalex.org/W2750912449","https://openalex.org/W2796992393","https://openalex.org/W2902135157","https://openalex.org/W2949117887","https://openalex.org/W2951590555","https://openalex.org/W2962865004","https://openalex.org/W2963389687","https://openalex.org/W2964121744","https://openalex.org/W2964308564"],"related_works":["https://openalex.org/W4294690647","https://openalex.org/W4300574098","https://openalex.org/W4390872419","https://openalex.org/W4387421702","https://openalex.org/W2986131686","https://openalex.org/W3136482419","https://openalex.org/W4282044994","https://openalex.org/W3092714093","https://openalex.org/W2619697695","https://openalex.org/W4386096474"],"abstract_inverted_index":{"In":[0],"this":[1,72],"paper":[2],"our":[3],"objectives":[4,47],"are,":[5],"first,":[6],"networks":[7],"that":[8,19,29,34,79,106,114,137,155,159],"can":[9,30,80,111,164],"embed":[10],"audio":[11,41,107],"and":[12,25,86,108,120,149,176],"visual":[13,109,135],"inputs":[14],"into":[15],"a":[16,27,64,139,146,179],"common":[17],"space":[18],"is":[20,63],"suitable":[21],"for":[22,83,127,133],"cross-modal":[23,67,84],"retrieval;":[24,122],"second,":[26],"network":[28,77],"localize":[31],"the":[32,40,59,88,96,101,128,134,156,169,189],"object":[33,158],"sounds":[35,160],"in":[36,91,188],"an":[37,92,162],"image,":[38,93,141],"given":[39],"signal.":[42],"We":[43,99],"achieve":[44],"both":[45,116],"these":[46],"by":[48,94],"training":[49],"from":[50,69],"unlabelled":[51],"video":[52],"using":[53,95],"only":[54,168],"audio-visual":[55],"correspondence":[56],"(AVC)":[57],"as":[58],"objective":[60],"function.":[61],"This":[62],"form":[65],"of":[66],"self-supervision":[68],"video.":[70],"To":[71],"end,":[73],"we":[74],"design":[75],"new":[76],"architectures":[78,126],"be":[81,112,165],"trained":[82],"retrieval":[85],"localizing":[87],"sound":[89],"source":[90],"AVC":[97,129],"task.":[98],"make":[100],"following":[102],"contributions:":[103],"(i)":[104],"show":[105,154],"embeddings":[110],"learnt":[113],"enable":[115],"within-mode":[117],"(e.g.":[118],"audio-to-audio)":[119],"between-mode":[121],"(ii)":[123],"explore":[124],"various":[125],"task,":[130],"including":[131],"those":[132],"stream":[136],"ingest":[138],"single":[140,147],"or":[142,145,173],"multiple":[143],"images,":[144],"image":[148,163],"multi-frame":[150],"optical":[151],"flow;":[152],"(iii)":[153],"semantic":[157],"within":[161],"localized":[166],"(using":[167],"sound,":[170],"no":[171],"motion":[172],"flow":[174],"information);":[175],"(iv)":[177],"give":[178],"cautionary":[180],"tale":[181],"on":[182],"how":[183],"to":[184],"avoid":[185],"undesirable":[186],"shortcuts":[187],"data":[190],"preparation.":[191]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":9}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2018-01-05T00:00:00"}