{"id":"https://openalex.org/W4401608286","doi":"https://doi.org/10.1109/tpami.2024.3444029","title":"Enhancing Sound Source Localization via False Negative Elimination","display_name":"Enhancing Sound Source Localization via False Negative Elimination","publication_year":2024,"publication_date":"2024-08-15","ids":{"openalex":"https://openalex.org/W4401608286","doi":"https://doi.org/10.1109/tpami.2024.3444029","pmid":"https://pubmed.ncbi.nlm.nih.gov/39146158"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2024.3444029","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/tpami.2024.3444029","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2408.16448","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000009166","display_name":"Zengjie Song","orcid":"https://orcid.org/0000-0002-7914-3252"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zengjie Song","raw_affiliation_strings":["School of Mathematics and Statistics, Xi’an Jiaotong University, Xi’an, China"],"affiliations":[{"raw_affiliation_string":"School of Mathematics and Statistics, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024880206","display_name":"Jiangshe Zhang","orcid":"https://orcid.org/0000-0002-8395-1180"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangshe Zhang","raw_affiliation_strings":["School of Mathematics and Statistics, Xi’an Jiaotong University, Xi’an, China"],"affiliations":[{"raw_affiliation_string":"School of Mathematics and Statistics, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100393131","display_name":"Yuxi Wang","orcid":"https://orcid.org/0000-0003-1579-2357"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxi Wang","raw_affiliation_strings":["Center for Artificial Intelligence and Robotics, Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Center for Artificial Intelligence and Robotics, Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences, Hong Kong SAR, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050140194","display_name":"Junsong Fan","orcid":"https://orcid.org/0000-0001-6989-2711"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junsong Fan","raw_affiliation_strings":["Center for Artificial Intelligence and Robotics, Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Center for Artificial Intelligence and Robotics, Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences, Hong Kong SAR, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028016065","display_name":"Zhaoxiang Zhang","orcid":"https://orcid.org/0000-0003-2648-3875"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaoxiang Zhang","raw_affiliation_strings":["New Laboratory of Pattern Recognition, State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","Center for Artificial Intelligence and Robotics, Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences, Hong Kong SAR, China","University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"New Laboratory of Pattern Recognition, State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Center for Artificial Intelligence and Robotics, Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences, Hong Kong SAR, China","institution_ids":["https://openalex.org/I4210116924","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5000009166"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":0.3544,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53926507,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"46","issue":"12","first_page":"10499","last_page":"10514"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9983999729156494,"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/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9700000286102295,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8057509660720825},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6882392764091492},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5630589127540588},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.542330265045166},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.531633734703064},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5123125314712524},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.47871828079223633},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.4600292444229126},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4330671429634094},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.421941876411438},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3876362442970276},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3479641377925873},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3414364457130432},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.09368309378623962}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8057509660720825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6882392764091492},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5630589127540588},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.542330265045166},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.531633734703064},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5123125314712524},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.47871828079223633},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.4600292444229126},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4330671429634094},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.421941876411438},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3876362442970276},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3479641377925873},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3414364457130432},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.09368309378623962},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpami.2024.3444029","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/tpami.2024.3444029","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:39146158","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39146158","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:arXiv.org:2408.16448","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.16448","pdf_url":"https://arxiv.org/pdf/2408.16448","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2408.16448","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.16448","pdf_url":"https://arxiv.org/pdf/2408.16448","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1246013875","display_name":null,"funder_award_id":"2024A1515010919","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G130652162","display_name":null,"funder_award_id":"202304","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1477544716","display_name":null,"funder_award_id":"Guangdong","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1658981422","display_name":null,"funder_award_id":"xzy012023047","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G2082826544","display_name":null,"funder_award_id":"Postdoctoral","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2376276132","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G2545145071","display_name":null,"funder_award_id":"12201490","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3899757686","display_name":null,"funder_award_id":"12371512","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G395608454","display_name":null,"funder_award_id":"12301656","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4210075541","display_name":null,"funder_award_id":"62276208","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5104420917","display_name":null,"funder_award_id":"2023058","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6748661587","display_name":null,"funder_award_id":"12326607","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7633792650","display_name":null,"funder_award_id":"51501091","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4401608286.pdf"},"referenced_works_count":78,"referenced_works":["https://openalex.org/W1999478155","https://openalex.org/W2065274193","https://openalex.org/W2105582566","https://openalex.org/W2106488367","https://openalex.org/W2108598243","https://openalex.org/W2119885245","https://openalex.org/W2194775991","https://openalex.org/W2222512263","https://openalex.org/W2286419477","https://openalex.org/W2511428026","https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2619697695","https://openalex.org/W2798991696","https://openalex.org/W2842511635","https://openalex.org/W2888218464","https://openalex.org/W2944828972","https://openalex.org/W2962865004","https://openalex.org/W2962960500","https://openalex.org/W2963680395","https://openalex.org/W2982619606","https://openalex.org/W2986131686","https://openalex.org/W2989980422","https://openalex.org/W2990500698","https://openalex.org/W3002904085","https://openalex.org/W3009561768","https://openalex.org/W3015371781","https://openalex.org/W3035524453","https://openalex.org/W3046890131","https://openalex.org/W3104591054","https://openalex.org/W3106743555","https://openalex.org/W3108367559","https://openalex.org/W3108655343","https://openalex.org/W3110446398","https://openalex.org/W3116298410","https://openalex.org/W3145385912","https://openalex.org/W3162322471","https://openalex.org/W3169318522","https://openalex.org/W3170088426","https://openalex.org/W3170837227","https://openalex.org/W3171007011","https://openalex.org/W3175300676","https://openalex.org/W3188558905","https://openalex.org/W3190580390","https://openalex.org/W4200436929","https://openalex.org/W4214504406","https://openalex.org/W4224925617","https://openalex.org/W4226314236","https://openalex.org/W4245551807","https://openalex.org/W4283709432","https://openalex.org/W4297808394","https://openalex.org/W4310255405","https://openalex.org/W4312505596","https://openalex.org/W4312926266","https://openalex.org/W4381567848","https://openalex.org/W4386075532","https://openalex.org/W6620707391","https://openalex.org/W6637373629","https://openalex.org/W6684193366","https://openalex.org/W6729831399","https://openalex.org/W6748775516","https://openalex.org/W6754048563","https://openalex.org/W6757817989","https://openalex.org/W6760212410","https://openalex.org/W6770805772","https://openalex.org/W6772892956","https://openalex.org/W6774670964","https://openalex.org/W6776700526","https://openalex.org/W6777265123","https://openalex.org/W6779844698","https://openalex.org/W6779977557","https://openalex.org/W6780191644","https://openalex.org/W6780730929","https://openalex.org/W6783539077","https://openalex.org/W6785011006","https://openalex.org/W6791742336","https://openalex.org/W6797016505","https://openalex.org/W6809915981"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W3119773509","https://openalex.org/W3208297503","https://openalex.org/W2889153461","https://openalex.org/W2964117661","https://openalex.org/W4388405611","https://openalex.org/W2619127353"],"abstract_inverted_index":{"Sound":[0],"source":[1],"localization":[2],"aims":[3],"to":[4,36,46,109,129,143,152,184,213],"localize":[5],"objects":[6],"emitting":[7],"the":[8,24,37,42,58,131,174,186,192,198,203,206,211],"sound":[9],"in":[10,31],"visual":[11,47,59,69,117,154,162],"scenes.":[12],"Recent":[13],"works":[14],"obtaining":[15],"impressive":[16],"results":[17],"typically":[18],"rely":[19],"on":[20],"contrastive":[21,100,178],"learning.":[22,133],"However,":[23],"common":[25],"practice":[26],"of":[27,66,176,194,205],"randomly":[28],"sampling":[29],"negatives":[30,52,166],"prior":[32],"arts":[33],"can":[34],"lead":[35],"false":[38,145,158],"negative":[39],"issue,":[40,78],"where":[41],"sounds":[43],"semantically":[44,111],"similar":[45],"instance":[48],"are":[49],"sampled":[50],"as":[51,139],"and":[53,68,98,116,156,164,217],"incorrectly":[54],"pushed":[55],"away":[56],"from":[57,170],"anchor/query.":[60],"As":[61],"a":[62,81,120,140],"result,":[63],"this":[64,77,135],"misalignment":[65],"audio":[67,115,165],"features":[70,155],"could":[71],"yield":[72],"inferior":[73],"performance.":[74],"To":[75],"address":[76],"we":[79,201],"propose":[80],"novel":[82],"audio-visual":[83,177,214],"learning":[84,92,96,101],"framework":[85],"which":[86],"is":[87,127,150],"instantiated":[88],"with":[89],"two":[90],"individual":[91],"schemes:":[93],"self-supervised":[94],"predictive":[95,121],"(SSPL)":[97],"semantic-aware":[99],"(SACL).":[102],"SSPL":[103,137],"explores":[104],"image-audio":[105],"positive":[106],"pairs":[107],"alone":[108],"discover":[110],"coherent":[112],"similarities":[113],"between":[114],"features,":[118],"while":[119],"coding":[122],"module":[123],"for":[124,167],"feature":[125],"alignment":[126],"introduced":[128],"facilitate":[130],"positive-only":[132],"In":[134],"regard":[136],"acts":[138],"negative-free":[141],"method":[142],"eliminate":[144],"negatives.":[146],"By":[147],"contrast,":[148],"SACL":[149,172],"designed":[151],"compact":[153],"remove":[157],"negatives,":[159],"providing":[160],"reliable":[161],"anchor":[163],"contrast.":[168],"Different":[169],"SSPL,":[171],"releases":[173],"potential":[175],"learning,":[179],"offering":[180],"an":[181],"effective":[182],"alternative":[183],"achieve":[185],"same":[187],"goal.":[188],"Comprehensive":[189],"experiments":[190],"demonstrate":[191],"superiority":[193],"our":[195],"approach":[196,212],"over":[197],"state-of-the-arts.":[199],"Furthermore,":[200],"highlight":[202],"versatility":[204],"learned":[207],"representation":[208],"by":[209],"extending":[210],"event":[215],"classification":[216],"object":[218],"detection":[219],"tasks.":[220]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-25T14:56:36.534964","created_date":"2025-10-10T00:00:00"}