{"id":"https://openalex.org/W4224925617","doi":"https://doi.org/10.1109/icassp43922.2022.9747867","title":"Learning Sound Localization Better from Semantically Similar Samples","display_name":"Learning Sound Localization Better from Semantically Similar Samples","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224925617","doi":"https://doi.org/10.1109/icassp43922.2022.9747867"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747867","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747867","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5070707693","display_name":"Arda Senocak","orcid":"https://orcid.org/0000-0001-9141-3270"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Arda Senocak","raw_affiliation_strings":["KAIST,Daejeon,Korea","KAIST, Daejeon, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,Daejeon,Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"KAIST, Daejeon, Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014059162","display_name":"Hyeonggon Ryu","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyeonggon Ryu","raw_affiliation_strings":["KAIST,Daejeon,Korea","KAIST, Daejeon, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,Daejeon,Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"KAIST, Daejeon, Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008585354","display_name":"Junsik Kim","orcid":"https://orcid.org/0000-0002-0287-9640"},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junsik Kim","raw_affiliation_strings":["Harvard University,Cambridge,MA,USA","Harvard University, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University,Cambridge,MA,USA","institution_ids":["https://openalex.org/I2801851002"]},{"raw_affiliation_string":"Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012455275","display_name":"In So Kweon","orcid":"https://orcid.org/0000-0001-9626-5983"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"In So Kweon","raw_affiliation_strings":["KAIST,Daejeon,Korea","KAIST, Daejeon, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,Daejeon,Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"KAIST, Daejeon, Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.147,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.94082468,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4863","last_page":"4867"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991000294685364,"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":0.9991000294685364,"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/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/false-positive-paradox","display_name":"False positive paradox","score":0.890413224697113},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7300211787223816},{"id":"https://openalex.org/keywords/true-positive-rate","display_name":"True positive rate","score":0.562564492225647},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5598181486129761},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5586634874343872},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.447092741727829},{"id":"https://openalex.org/keywords/false-positives-and-false-negatives","display_name":"False positives and false negatives","score":0.4334738850593567},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4291646480560303},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4285605847835541},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42560383677482605},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.41645267605781555},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3836444616317749},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.07251006364822388}],"concepts":[{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.890413224697113},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7300211787223816},{"id":"https://openalex.org/C2989486834","wikidata":"https://www.wikidata.org/wiki/Q3808900","display_name":"True positive rate","level":2,"score":0.562564492225647},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5598181486129761},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5586634874343872},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.447092741727829},{"id":"https://openalex.org/C112789634","wikidata":"https://www.wikidata.org/wiki/Q18207010","display_name":"False positives and false negatives","level":3,"score":0.4334738850593567},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4291646480560303},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4285605847835541},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42560383677482605},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.41645267605781555},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3836444616317749},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.07251006364822388},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747867","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747867","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6499999761581421,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W2157364932","https://openalex.org/W2194775991","https://openalex.org/W2842511635","https://openalex.org/W2950388022","https://openalex.org/W2962899219","https://openalex.org/W2962960500","https://openalex.org/W2963115079","https://openalex.org/W2963680395","https://openalex.org/W2963775347","https://openalex.org/W2964109005","https://openalex.org/W2971680695","https://openalex.org/W2981851635","https://openalex.org/W2982619606","https://openalex.org/W2986131686","https://openalex.org/W2988200020","https://openalex.org/W3002552512","https://openalex.org/W3002904085","https://openalex.org/W3004505825","https://openalex.org/W3015371781","https://openalex.org/W3017343282","https://openalex.org/W3034658206","https://openalex.org/W3034742263","https://openalex.org/W3035333188","https://openalex.org/W3094454579","https://openalex.org/W3096431533","https://openalex.org/W3105352633","https://openalex.org/W3116298410","https://openalex.org/W3170088426","https://openalex.org/W3174854700","https://openalex.org/W3182657421","https://openalex.org/W3190580390","https://openalex.org/W4289665794","https://openalex.org/W4293665662","https://openalex.org/W4297808394","https://openalex.org/W4310255405","https://openalex.org/W6729831399","https://openalex.org/W6754782314","https://openalex.org/W6772892956","https://openalex.org/W6773226109","https://openalex.org/W6783539077","https://openalex.org/W6784429643","https://openalex.org/W6784660784","https://openalex.org/W6792929434"],"related_works":["https://openalex.org/W1557094818","https://openalex.org/W2183246718","https://openalex.org/W1973412793","https://openalex.org/W3129715955","https://openalex.org/W2099261052","https://openalex.org/W4287692494","https://openalex.org/W4248223603","https://openalex.org/W2951146195","https://openalex.org/W2127533281","https://openalex.org/W4226048087"],"abstract_inverted_index":{"The":[0],"objective":[1,91],"of":[2,97],"this":[3],"work":[4],"is":[5,62],"to":[6,72,109],"localize":[7],"the":[8,26,73,95,110],"sound":[9],"sources":[10],"in":[11],"visual":[12],"scenes.":[13],"Existing":[14],"audio-visual":[15,23,45],"works":[16],"employ":[17],"contrastive":[18,89],"learning":[19,90],"by":[20,82],"assigning":[21],"corresponding":[22,74],"pairs":[24,34,40],"from":[25],"same":[27],"source":[28],"as":[29,35,57],"positives":[30,66,81],"while":[31],"randomly":[32],"mismatched":[33],"negatives.":[36,58],"However,":[37],"these":[38,48,79],"negative":[39],"may":[41],"contain":[42],"semantically":[43,49],"matched":[44],"information.":[46],"Thus,":[47],"correlated":[50],"pairs,":[51],"\"hard":[52],"positives\",":[53],"are":[54],"mistakenly":[55],"grouped":[56],"Our":[59,76],"key":[60],"contribution":[61],"showing":[63,106],"that":[64],"hard":[65,80],"can":[67],"give":[68],"similar":[69],"response":[70,85],"maps":[71,86],"pairs.":[75],"approach":[77,99],"incorporates":[78],"adding":[83],"their":[84],"into":[87],"a":[88],"directly.":[92],"We":[93],"demonstrate":[94],"effectiveness":[96],"our":[98],"on":[100],"VGG-SS":[101],"and":[102],"SoundNet-Flickr":[103],"test":[104],"sets,":[105],"favorable":[107],"performance":[108],"state-of-the-art":[111],"methods.":[112]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}