{"id":"https://openalex.org/W7153441372","doi":"https://doi.org/10.1007/s11263-026-02836-w","title":"Correction: Hearing and Seeing Through CLIP: A Framework for Self-Supervised Sound Source Localization","display_name":"Correction: Hearing and Seeing Through CLIP: A Framework for Self-Supervised Sound Source Localization","publication_year":2026,"publication_date":"2026-04-11","ids":{"openalex":"https://openalex.org/W7153441372","doi":"https://doi.org/10.1007/s11263-026-02836-w"},"language":"en","primary_location":{"id":"doi:10.1007/s11263-026-02836-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-026-02836-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-026-02836-w.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11263-026-02836-w.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123409703","display_name":"Sooyoung Park","orcid":null},"institutions":[{"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"]},{"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":"Sooyoung Park","raw_affiliation_strings":["Media Coding Research Section, ETRI, Daejeon, South Korea","School of Electrical Engineering, KAIST, Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0009-0007-4138-3561","affiliations":[{"raw_affiliation_string":"Media Coding Research Section, ETRI, Daejeon, South Korea","institution_ids":["https://openalex.org/I142401562"]},{"raw_affiliation_string":"School of Electrical Engineering, KAIST, Daejeon, 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/I48566637","display_name":"Ulsan National Institute of Science and Technology","ror":"https://ror.org/017cjz748","country_code":"KR","type":"education","lineage":["https://openalex.org/I48566637"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Arda Senocak","raw_affiliation_strings":["Graduate School of Artificial Intelligence, UNIST, Ulsan, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Artificial Intelligence, UNIST, Ulsan, South Korea","institution_ids":["https://openalex.org/I48566637"]}]},{"author_position":"last","author":{"id":null,"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":true,"raw_author_name":"Joon Son Chung","raw_affiliation_strings":["School of Electrical Engineering, KAIST, Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0000-0001-7741-7275","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":{"value":2890,"currency":"EUR","value_usd":3690},"apc_paid":{"value":2890,"currency":"EUR","value_usd":3690},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.58838928,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"134","issue":"5","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.5640000104904175,"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":0.5640000104904175,"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":0.1378999948501587,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.09049999713897705,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/sound-localization","display_name":"Sound localization","score":0.4348999857902527},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42489999532699585},{"id":"https://openalex.org/keywords/acoustic-source-localization","display_name":"Acoustic source localization","score":0.421099990606308},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.3765999972820282},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.3700999915599823},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.3411000072956085}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6294999718666077},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5546000003814697},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5074999928474426},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4848000109195709},{"id":"https://openalex.org/C68236139","wikidata":"https://www.wikidata.org/wiki/Q765652","display_name":"Sound localization","level":2,"score":0.4348999857902527},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42489999532699585},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.421099990606308},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.3765999972820282},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.3700999915599823},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3411000072956085},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3337000012397766},{"id":"https://openalex.org/C38129911","wikidata":"https://www.wikidata.org/wiki/Q4820038","display_name":"Auditory scene analysis","level":3,"score":0.3028999865055084},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.2906000018119812},{"id":"https://openalex.org/C73208851","wikidata":"https://www.wikidata.org/wiki/Q5157303","display_name":"Computational auditory scene analysis","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C2985998994","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Source model","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11263-026-02836-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-026-02836-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-026-02836-w.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11263-026-02836-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-026-02836-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-026-02836-w.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W7153441372.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Remove":[0],"the":[1],"incorrect":[2],"closing":[3],"bracket":[4],"in":[5],"\"Alignment":[6],"TPAMI25":[7],")":[8],"\".":[9],"[Correct:":[10],"\"":[11]},"counts_by_year":[],"updated_date":"2026-05-22T06:13:13.366637","created_date":"2026-04-12T00:00:00"}