{"id":"https://openalex.org/W4372267673","doi":"https://doi.org/10.1109/icassp49357.2023.10097234","title":"MarginNCE: Robust Sound Localization with a Negative Margin","display_name":"MarginNCE: Robust Sound Localization with a Negative Margin","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372267673","doi":"https://doi.org/10.1109/icassp49357.2023.10097234"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10097234","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097234","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5113983179","display_name":"Sooyoung Park","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"]},{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Sooyoung Park","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,South Korea","Electronics and Telecommunications Research Institute, South Korea","Korea Advanced Institute of Science and Technology, South Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Electronics and Telecommunications Research Institute, South Korea","institution_ids":["https://openalex.org/I142401562"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","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":["Korea Advanced Institute of Science and Technology,South Korea","Korea Advanced Institute of Science and Technology, South Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038723822","display_name":"Joon Son Chung","orcid":"https://orcid.org/0000-0001-7741-7275"},"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":"Joon Son Chung","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,South Korea","Korea Advanced Institute of Science and Technology, South Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5113983179"],"corresponding_institution_ids":["https://openalex.org/I142401562","https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":2.3827,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.89394409,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9984999895095825,"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":0.9965999722480774,"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/margin","display_name":"Margin (machine learning)","score":0.8243514895439148},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7340449094772339},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5551651120185852},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5542016625404358},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5399989485740662},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.49997997283935547},{"id":"https://openalex.org/keywords/acoustic-source-localization","display_name":"Acoustic source localization","score":0.47729742527008057},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.443794846534729},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38767585158348083},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.20379012823104858},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.08428415656089783}],"concepts":[{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.8243514895439148},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7340449094772339},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5551651120185852},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5542016625404358},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5399989485740662},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.49997997283935547},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.47729742527008057},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.443794846534729},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38767585158348083},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.20379012823104858},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.08428415656089783},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10097234","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097234","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W2796992393","https://openalex.org/W2842511635","https://openalex.org/W2890052321","https://openalex.org/W2950388022","https://openalex.org/W2963680395","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/W3015371781","https://openalex.org/W3023351797","https://openalex.org/W3034658206","https://openalex.org/W3034742263","https://openalex.org/W3035333188","https://openalex.org/W3080420240","https://openalex.org/W3096431533","https://openalex.org/W3096805028","https://openalex.org/W3105352633","https://openalex.org/W3108367559","https://openalex.org/W3116298410","https://openalex.org/W3170088426","https://openalex.org/W3190580390","https://openalex.org/W4212847156","https://openalex.org/W4221161766","https://openalex.org/W4224925617","https://openalex.org/W4283709432","https://openalex.org/W4289665794","https://openalex.org/W4293665662","https://openalex.org/W4296594718","https://openalex.org/W4297808394","https://openalex.org/W4312653918","https://openalex.org/W6729831399","https://openalex.org/W6750591037","https://openalex.org/W6754048563","https://openalex.org/W6754782314","https://openalex.org/W6773226109","https://openalex.org/W6782004394","https://openalex.org/W6783539077","https://openalex.org/W6784429643","https://openalex.org/W6809915981","https://openalex.org/W6843326755"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2074916782","https://openalex.org/W2625296515","https://openalex.org/W3125011624","https://openalex.org/W3137890128","https://openalex.org/W1508631387","https://openalex.org/W2370917603","https://openalex.org/W4245955731"],"abstract_inverted_index":{"The":[0],"goal":[1],"of":[2,22,111,157],"this":[3,54,92],"work":[4,93],"is":[5,94],"to":[6,72,84,95,161],"localize":[7],"sound":[8,23,115],"sources":[9],"in":[10,19,57,91,104,114,165,169],"visual":[11,33,65],"scenes":[12],"with":[13,131],"a":[14,99,120,132,158,166],"self-supervised":[15],"approach.":[16],"Contrastive":[17],"learning":[18,106],"the":[20,27,36,40,85,109,128,148,155],"context":[21],"source":[24,42,116],"localization":[25],"leverages":[26],"natural":[28],"correspondence":[29],"between":[30],"audio":[31,63],"and":[32,64],"signals":[34,67],"where":[35],"audio-visual":[37],"pairs":[38,50,77],"from":[39],"same":[41],"are":[43,51],"assumed":[44],"as":[45],"positive,":[46],"while":[47],"randomly":[48],"selected":[49],"negatives.":[52],"However,":[53],"approach":[55,124,141],"brings":[56],"noisy":[58,112],"correspondences;":[59],"for":[60],"example,":[61],"positive":[62,86],"pair":[66],"that":[68,78,97,139,154],"may":[69,79],"be":[70],"unrelated":[71],"each":[73],"other,":[74],"or":[75,144],"negative":[76,133,159],"contain":[80],"semantically":[81],"similar":[82],"samples":[83],"one.":[87],"Our":[88],"key":[89],"contribution":[90],"show":[96,138],"using":[98],"less":[100],"strict":[101],"decision":[102],"boundary":[103],"contrastive":[105,129],"can":[107],"alleviate":[108],"effect":[110],"correspondences":[113],"localization.":[117],"We":[118],"propose":[119],"simple":[121],"yet":[122],"effective":[123],"by":[125],"slightly":[126],"modifying":[127],"loss":[130],"margin.":[134],"Extensive":[135],"experimental":[136],"results":[137,164],"our":[140],"gives":[142],"on-par":[143],"better":[145],"performance":[146],"than":[147],"state-of-the-art":[149],"methods.":[150],"Furthermore,":[151],"we":[152],"demonstrate":[153],"introduction":[156],"margin":[160],"existing":[162],"methods":[163],"consistent":[167],"improvement":[168],"performance.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}
