{"id":"https://openalex.org/W7134237118","doi":"https://doi.org/10.1007/s11263-025-02687-x","title":"Hearing and Seeing Through CLIP: A Framework for Self-Supervised Sound Source Localization","display_name":"Hearing and Seeing Through CLIP: A Framework for Self-Supervised Sound Source Localization","publication_year":2026,"publication_date":"2026-03-09","ids":{"openalex":"https://openalex.org/W7134237118","doi":"https://doi.org/10.1007/s11263-025-02687-x"},"language":"en","primary_location":{"id":"doi:10.1007/s11263-025-02687-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-025-02687-x","pdf_url":null,"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://doi.org/10.1007/s11263-025-02687-x","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/I27494661","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81","country_code":"KR","type":"government","lineage":["https://openalex.org/I27494661","https://openalex.org/I2801339556","https://openalex.org/I4387152098"]},{"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":"Sooyoung Park","raw_affiliation_strings":["Graduate School of Artificial Intelligence, UNIST, Ulsan, South Korea","Media Coding Research Section, Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0009-0007-4138-3561","affiliations":[{"raw_affiliation_string":"Graduate School of Artificial Intelligence, UNIST, Ulsan, South Korea","institution_ids":["https://openalex.org/I48566637"]},{"raw_affiliation_string":"Media Coding Research Section, Daejeon, South Korea","institution_ids":["https://openalex.org/I27494661"]}]},{"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":"https://openalex.org/A5128501030","display_name":"Joon Son Chung","orcid":null},"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":true,"raw_author_name":"Joon Son Chung","raw_affiliation_strings":["Graduate School of Artificial Intelligence, UNIST, Ulsan, South Korea"],"raw_orcid":"https://orcid.org/0000-0001-7741-7275","affiliations":[{"raw_affiliation_string":"Graduate School of Artificial Intelligence, UNIST, Ulsan, South Korea","institution_ids":["https://openalex.org/I48566637"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5128501030"],"corresponding_institution_ids":["https://openalex.org/I48566637"],"apc_list":{"value":2890,"currency":"EUR","value_usd":3690},"apc_paid":{"value":2890,"currency":"EUR","value_usd":3690},"fwci":27.5769,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.98961562,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"134","issue":"4","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":0.42250001430511475,"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":0.42250001430511475,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.2085999995470047,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.10180000215768814,"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/generalization","display_name":"Generalization","score":0.8208000063896179},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.48980000615119934},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44999998807907104},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3427000045776367},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.30329999327659607},{"id":"https://openalex.org/keywords/depth-sounding","display_name":"Depth sounding","score":0.2892000079154968}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.8208000063896179},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7694000005722046},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6301000118255615},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.48980000615119934},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44999998807907104},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43130001425743103},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3822000026702881},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3662000000476837},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3427000045776367},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C55510283","wikidata":"https://www.wikidata.org/wiki/Q1382947","display_name":"Depth sounding","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.2766000032424927},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.26330000162124634}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11263-025-02687-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-025-02687-x","pdf_url":null,"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/s11263-025-02687-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-025-02687-x","pdf_url":null,"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W2963115079","https://openalex.org/W2963680395","https://openalex.org/W2986131686","https://openalex.org/W3015371781","https://openalex.org/W3108367559","https://openalex.org/W3110268547","https://openalex.org/W3170088426","https://openalex.org/W3176445421","https://openalex.org/W3210447534","https://openalex.org/W4212847156","https://openalex.org/W4224925617","https://openalex.org/W4226314236","https://openalex.org/W4283709432","https://openalex.org/W4310255405","https://openalex.org/W4312420092","https://openalex.org/W4312653918","https://openalex.org/W4312926266","https://openalex.org/W4312956471","https://openalex.org/W4313052647","https://openalex.org/W4313123347","https://openalex.org/W4319299730","https://openalex.org/W4319300466","https://openalex.org/W4372260310","https://openalex.org/W4372267673","https://openalex.org/W4385567053","https://openalex.org/W4385822589","https://openalex.org/W4385823492","https://openalex.org/W4386071707","https://openalex.org/W4386072368","https://openalex.org/W4386075532","https://openalex.org/W4386075567","https://openalex.org/W4386075766","https://openalex.org/W4390872419","https://openalex.org/W4394597165","https://openalex.org/W4402727181","https://openalex.org/W4402727869","https://openalex.org/W4402753794","https://openalex.org/W4402781078","https://openalex.org/W4404784428","https://openalex.org/W4410770645","https://openalex.org/W4411244512","https://openalex.org/W4413156999","https://openalex.org/W7133239261"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Large-scale":[1],"vision-language":[2],"models":[3],"demonstrate":[4,141],"strong":[5,153],"multimodal":[6,99],"alignment":[7,95],"and":[8,79,109,151],"generalization":[9,154],"across":[10,137],"diverse":[11,139],"tasks.":[12],"Among":[13],"them,":[14],"CLIP":[15,33],"stands":[16],"out":[17],"as":[18],"one":[19],"of":[20,32,97],"the":[21,30,82,128],"most":[22],"successful":[23],"approaches.":[24],"In":[25],"this":[26],"work,":[27],"we":[28],"extend":[29],"application":[31],"to":[34,68,105,132],"sound":[35],"source":[36],"localization,":[37],"proposing":[38],"a":[39,49,86],"self-supervised":[40],"method":[41,104],"operates":[42],"without":[43],"explicit":[44],"text":[45,59],"input.":[46],"We":[47,115],"introduce":[48],"framework":[50],"that":[51,94,121,142],"maps":[52],"audios":[53],"into":[54,127],"tokens":[55],"compatible":[56],"with":[57,81],"CLIP\u2019s":[58],"encoder,":[60],"producing":[61],"audio-driven":[62],"embeddings.":[63],"These":[64],"embeddings":[65,84],"are":[66,77],"used":[67],"generate":[69,106],"sounding":[70,113],"region":[71],"masks,":[72],"from":[73],"which":[74],"visual":[75],"features":[76],"extracted":[78],"aligned":[80],"audio":[83],"through":[85],"contrastive":[87],"audio-visual":[88,124],"correspondence":[89],"objective.":[90],"Our":[91],"findings":[92],"show":[93],"knowledge":[96],"pre-trained":[98],"foundation":[100],"model":[101,129],"enables":[102],"our":[103,143],"more":[107],"complete":[108],"compact":[110],"localization":[111],"for":[112],"objects.":[114],"further":[116],"propose":[117],"an":[118],"LLM-guided":[119],"extension":[120],"distills":[122],"object-aware":[123],"scene":[125],"understanding":[126],"during":[130],"training":[131],"enhance":[133],"alignment.":[134],"Extensive":[135],"experiments":[136],"five":[138],"tasks":[140],"method,":[144],"in":[145,155],"all":[146],"variants,":[147],"outperforms":[148],"state-of-the-art":[149],"approaches":[150],"achieves":[152],"zero-shot":[156],"settings.":[157]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-03-10T00:00:00"}