{"id":"https://openalex.org/W2093111229","doi":"https://doi.org/10.1145/1631272.1631344","title":"Visual localization of non-stationary sound sources","display_name":"Visual localization of non-stationary sound sources","publication_year":2009,"publication_date":"2009-10-19","ids":{"openalex":"https://openalex.org/W2093111229","doi":"https://doi.org/10.1145/1631272.1631344","mag":"2093111229"},"language":"en","primary_location":{"id":"doi:10.1145/1631272.1631344","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1631272.1631344","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM international conference on Multimedia","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/A5101979563","display_name":"Yuyu Liu","orcid":"https://orcid.org/0000-0002-4814-8616"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yuyu Liu","raw_affiliation_strings":["The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045996641","display_name":"Yoichi Sato","orcid":"https://orcid.org/0000-0003-0097-4537"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoichi Sato","raw_affiliation_strings":["The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101979563"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":1.7623,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.83946692,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"513","last_page":"516"},"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9958000183105469,"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/T11309","display_name":"Music and Audio Processing","score":0.9952999949455261,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6257719993591309},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.47661176323890686},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3602833151817322},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3203338086605072},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1157245934009552}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6257719993591309},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.47661176323890686},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3602833151817322},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3203338086605072},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1157245934009552}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1631272.1631344","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1631272.1631344","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1511045106","https://openalex.org/W1560013842","https://openalex.org/W2065428732","https://openalex.org/W2079145130","https://openalex.org/W2100461058","https://openalex.org/W2102767076","https://openalex.org/W2105582566","https://openalex.org/W2113800095","https://openalex.org/W2118877769","https://openalex.org/W2148659689","https://openalex.org/W2164899449","https://openalex.org/W2167709189","https://openalex.org/W2171819471","https://openalex.org/W2293807473"],"related_works":["https://openalex.org/W3107474891","https://openalex.org/W4211182446","https://openalex.org/W4235181573","https://openalex.org/W2740347147","https://openalex.org/W4252487970","https://openalex.org/W4245868110","https://openalex.org/W4255839737","https://openalex.org/W2775902113","https://openalex.org/W4233773735","https://openalex.org/W1971118083"],"abstract_inverted_index":{"Sound":[0],"source":[1,22,65,129],"can":[2],"be":[3,26],"visually":[4],"localized":[5],"by":[6,83],"analyzing":[7],"the":[8,20,39,53,60,63,67,85,88,108,115,132,137,144],"correlation":[9,86,97],"between":[10,87],"audio":[11],"and":[12],"visual":[13,55,81,134],"data.":[14],"To":[15],"correctly":[16],"analyze":[17],"this":[18,45],"correlation,":[19],"sound":[21,41,64,128],"is":[23,49,102],"required":[24],"to":[25,31,43,125],"stationary":[27],"in":[28,69,131],"a":[29,35,70,74,122,127],"scene":[30],"date.":[32],"We":[33],"introduce":[34],"technique":[36,124],"that":[37,57],"localizes":[38],"non-stationary":[40],"sources":[42],"overcome":[44],"limitation.":[46],"The":[47,111],"problem":[48],"formulated":[50],"as":[51],"finding":[52],"optimal":[54,80,116],"trajectories":[56,82,117],"best":[58],"represent":[59],"movement":[61],"of":[62,93,136,146],"over":[66],"pixels":[68],"spatio-temporal":[71],"volume.":[72],"Using":[73],"beam":[75],"search,":[76],"we":[77],"search":[78],"these":[79],"maximizing":[84],"newly":[89],"introduced":[90],"audiovisual":[91],"features":[92],"inconsistency.":[94],"An":[95],"incremental":[96],"evaluation":[98],"with":[99],"mutual":[100],"information":[101],"developed":[103],"here,":[104],"which":[105],"significantly":[106],"reduces":[107],"computational":[109],"cost.":[110],"correlations":[112],"computed":[113],"along":[114],"are":[118],"finally":[119],"incorporated":[120],"into":[121],"segmentation":[123],"localize":[126],"region":[130],"first":[133],"frame":[135],"current":[138],"time":[139],"window.":[140],"Experimental":[141],"results":[142],"demonstrate":[143],"effectiveness":[145],"our":[147],"method.":[148]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}