{"id":"https://openalex.org/W4410770645","doi":"https://doi.org/10.1109/tpami.2025.3573994","title":"Toward Interactive Sound Source Localization: Better Align Sight and Sound!","display_name":"Toward Interactive Sound Source Localization: Better Align Sight and Sound!","publication_year":2025,"publication_date":"2025-05-27","ids":{"openalex":"https://openalex.org/W4410770645","doi":"https://doi.org/10.1109/tpami.2025.3573994","pmid":"https://pubmed.ncbi.nlm.nih.gov/40424104"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3573994","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3573994","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":["crossref","pubmed"],"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":true,"raw_author_name":"Arda Senocak","raw_affiliation_strings":["School of Electrical Engineering, KAIST, Daejeon, South Korea","School of Electrical Engineering, KAIST, Daejeon, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0001-9141-3270","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"School of Electrical Engineering, KAIST, Daejeon, Republic of 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":["School of Electrical Engineering, KAIST, Daejeon, South Korea","School of Electrical Engineering, KAIST, Daejeon, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0000-5638-1832","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"School of Electrical Engineering, KAIST, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070712855","display_name":"Junsik Kim","orcid":"https://orcid.org/0000-0003-2555-5232"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junsik Kim","raw_affiliation_strings":["School of Engineering and Applied Sciences, Harvard University, Boston, MA, USA"],"raw_orcid":"https://orcid.org/0000-0003-2555-5232","affiliations":[{"raw_affiliation_string":"School of Engineering and Applied Sciences, Harvard University, Boston, MA, USA","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078114111","display_name":"Tae-Hyun Oh","orcid":"https://orcid.org/0000-0003-0468-1571"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Tae-Hyun Oh","raw_affiliation_strings":["Department of Electrical Engineering, POSTECH, Pohang, South Korea","Department of Electrical Engineering, POSTECH, Pohang, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0003-0468-1571","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, POSTECH, Pohang, South Korea","institution_ids":["https://openalex.org/I123900574"]},{"raw_affiliation_string":"Department of Electrical Engineering, POSTECH, Pohang, Republic of Korea","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043151044","display_name":"Hanspeter Pfister","orcid":"https://orcid.org/0000-0002-3620-2582"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hanspeter Pfister","raw_affiliation_strings":["School of Engineering and Applied Sciences, Harvard University, Boston, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3620-2582","affiliations":[{"raw_affiliation_string":"School of Engineering and Applied Sciences, Harvard University, Boston, MA, USA","institution_ids":["https://openalex.org/I136199984"]}]},{"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":["School of Electrical Engineering, KAIST, Daejeon, South Korea","School of Electrical Engineering, KAIST, Daejeon, Republic of 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"]},{"raw_affiliation_string":"School of Electrical Engineering, KAIST, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5070707693"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":1.2753,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.78559361,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"47","issue":"9","first_page":"7643","last_page":"7659"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9763000011444092,"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":0.9763000011444092,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9746000170707703,"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/T12759","display_name":"Vehicle Noise and Vibration Control","score":0.9624999761581421,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.7565039396286011},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6358259320259094},{"id":"https://openalex.org/keywords/acoustic-source-localization","display_name":"Acoustic source localization","score":0.5710189938545227},{"id":"https://openalex.org/keywords/sound-localization","display_name":"Sound localization","score":0.5057849884033203},{"id":"https://openalex.org/keywords/sight","display_name":"Sight","score":0.46334749460220337},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.440359503030777},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43908724188804626},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40898266434669495},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3979976177215576},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08439773321151733}],"concepts":[{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.7565039396286011},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6358259320259094},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.5710189938545227},{"id":"https://openalex.org/C68236139","wikidata":"https://www.wikidata.org/wiki/Q765652","display_name":"Sound localization","level":2,"score":0.5057849884033203},{"id":"https://openalex.org/C1517167","wikidata":"https://www.wikidata.org/wiki/Q1134322","display_name":"Sight","level":2,"score":0.46334749460220337},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.440359503030777},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43908724188804626},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40898266434669495},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3979976177215576},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08439773321151733},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3573994","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3573994","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:40424104","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40424104","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}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":67,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2157364932","https://openalex.org/W2511428026","https://openalex.org/W2593116425","https://openalex.org/W2604379605","https://openalex.org/W2619697695","https://openalex.org/W2737258237","https://openalex.org/W2798991696","https://openalex.org/W2842511635","https://openalex.org/W2962960500","https://openalex.org/W2963115079","https://openalex.org/W2963680395","https://openalex.org/W2963775347","https://openalex.org/W2964109005","https://openalex.org/W2982619606","https://openalex.org/W2986131686","https://openalex.org/W2992308087","https://openalex.org/W3015371781","https://openalex.org/W3023351797","https://openalex.org/W3035524453","https://openalex.org/W3108367559","https://openalex.org/W3110268547","https://openalex.org/W3149106692","https://openalex.org/W3158714121","https://openalex.org/W3170088426","https://openalex.org/W3171007011","https://openalex.org/W3175300676","https://openalex.org/W3190580390","https://openalex.org/W4212847156","https://openalex.org/W4224925617","https://openalex.org/W4226314236","https://openalex.org/W4283709432","https://openalex.org/W4284898017","https://openalex.org/W4309674289","https://openalex.org/W4310255405","https://openalex.org/W4312653918","https://openalex.org/W4312933868","https://openalex.org/W4313123347","https://openalex.org/W4319299730","https://openalex.org/W4372266917","https://openalex.org/W4372267673","https://openalex.org/W4386071700","https://openalex.org/W4386071707","https://openalex.org/W4386075532","https://openalex.org/W4386076291","https://openalex.org/W4386076492","https://openalex.org/W4390872419","https://openalex.org/W4390873539","https://openalex.org/W4390874575","https://openalex.org/W4402727869","https://openalex.org/W4402753794","https://openalex.org/W4403386295","https://openalex.org/W4411244512","https://openalex.org/W6729831399","https://openalex.org/W6754048563","https://openalex.org/W6774670964","https://openalex.org/W6783539077","https://openalex.org/W6784660784","https://openalex.org/W6790672419","https://openalex.org/W6791353385","https://openalex.org/W6803728867","https://openalex.org/W6809915981","https://openalex.org/W6839415613","https://openalex.org/W6843326755","https://openalex.org/W6849659693","https://openalex.org/W6857401808","https://openalex.org/W6857730641"],"related_works":["https://openalex.org/W4312089944","https://openalex.org/W3011070339","https://openalex.org/W2108013559","https://openalex.org/W2288611238","https://openalex.org/W1485388545","https://openalex.org/W2349923422","https://openalex.org/W2998173332","https://openalex.org/W2317500761","https://openalex.org/W2159006459","https://openalex.org/W2143986816"],"abstract_inverted_index":{"Recent":[0],"studies":[1,83],"on":[2,10,124,228],"learning-based":[3],"sound":[4,31,52,136,154,181,202,217],"source":[5,32,137,155,182,203,218],"localization":[6,11,121,126,156,183,204,219],"have":[7],"primarily":[8],"focused":[9],"performance.":[12,208],"However,":[13],"prior":[14],"work":[15,210],"and":[16,72,84,100,118,128,157,171,205,231,237],"existing":[17,67,230],"benchmarks":[18,233],"often":[19],"overlook":[20],"a":[21,94,141],"crucial":[22],"aspect:":[23],"cross-modal":[24,64,73,105,108,129,159,190,198,206],"interaction,":[25],"which":[26,195],"is":[27,36],"essential":[28],"for":[29,38],"interactive":[30,135,153,180],"localization.":[33],"This":[34,209],"interaction":[35,65,106,191,207],"vital":[37],"understanding":[39,74],"semantically":[40],"matched":[41],"or":[42,50],"mismatched":[43],"audio-visual":[44],"events,":[45],"such":[46],"as":[47],"silent":[48],"objects":[49],"true":[51],"sources":[53],"among":[54],"multiple":[55],"objects.":[56],"In":[57],"this":[58],"work,":[59],"we":[60,92,111,139,150],"comprehensively":[61],"examine":[62],"the":[63,78,212],"of":[66,81,216,225],"methods,":[68,122],"benchmarks,":[69],"evaluation":[70,114,172,239],"metrics,":[71],"tasks.":[75],"We":[76],"identify":[77],"overlooked":[79],"points":[80],"previous":[82,176],"make":[85],"several":[86],"contributions":[87],"to":[88,116,132,187,220],"address":[89],"them.":[90],"First,":[91],"propose":[93],"learning":[95],"framework":[96],"that":[97,175],"incorporates":[98],"retrieval-based":[99],"hand-crafted":[101],"augmentation":[102],"techniques,":[103],"enhancing":[104],"through":[107],"alignment.":[109],"Second,":[110],"introduce":[112],"new":[113,142,169,232,236],"metrics":[115,173],"accurately":[117],"rigorously":[119],"assess":[120],"focusing":[123],"both":[125,152,229,235],"performance":[127],"interaction.":[130],"Third,":[131],"thoroughly":[133],"analyze":[134],"localization,":[138],"present":[140],"semi-synthetic":[143],"benchmark":[144,170],"with":[145,179,222],"diverse":[146],"categorical":[147],"combinations.":[148],"Finally,":[149],"evaluate":[151],"auxiliary":[158],"retrieval":[160],"tasks,":[161,184],"benchmarking":[162],"competing":[163,226],"methods":[164,177,227],"alongside":[165],"our":[166],"own.":[167],"Our":[168,193],"reveal":[174],"struggle":[178],"largely":[185],"due":[186],"their":[188],"limited":[189],"capabilities.":[192],"method,":[194],"features":[196],"enhanced":[197],"alignment,":[199],"demonstrates":[200],"superior":[201],"provides":[211],"most":[213],"comprehensive":[214],"analysis":[215],"date,":[221],"extensive":[223],"validation":[224],"using":[234],"standard":[238],"metrics.":[240]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}