{"id":"https://openalex.org/W4224919395","doi":"https://doi.org/10.1109/icassp43922.2022.9747644","title":"Urban Sound &amp; Sight: Dataset And Benchmark For Audio-Visual Urban Scene Understanding","display_name":"Urban Sound &amp; Sight: Dataset And Benchmark For Audio-Visual Urban Scene Understanding","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224919395","doi":"https://doi.org/10.1109/icassp43922.2022.9747644"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747644","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747644","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://repositori.upf.edu/bitstreams/961894d3-9570-4de8-a4d9-913ede655b8b/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021235229","display_name":"Magdalena Fuentes","orcid":"https://orcid.org/0000-0003-4506-6639"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Magdalena Fuentes","raw_affiliation_strings":["New York University,New York,NY","New York University, New York, NY"],"affiliations":[{"raw_affiliation_string":"New York University,New York,NY","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"New York University, New York, NY","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012732932","display_name":"Bea Steers","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bea Steers","raw_affiliation_strings":["New York University,New York,NY","New York University, New York, NY"],"affiliations":[{"raw_affiliation_string":"New York University,New York,NY","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"New York University, New York, NY","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075959503","display_name":"Pablo Zinemanas","orcid":"https://orcid.org/0000-0002-9372-730X"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Pompeu Fabra University","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Pablo Zinemanas","raw_affiliation_strings":["Universitat Pompeu Fabra,Barcelona,Spain","Universitat Pompeu Fabra, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Universitat Pompeu Fabra,Barcelona,Spain","institution_ids":["https://openalex.org/I170486558"]},{"raw_affiliation_string":"Universitat Pompeu Fabra, Barcelona, Spain","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023777950","display_name":"Mart\u00edn Rocamora","orcid":"https://orcid.org/0000-0003-3183-9717"},"institutions":[{"id":"https://openalex.org/I180910786","display_name":"Universidad de la Rep\u00fablica","ror":"https://ror.org/030bbe882","country_code":"UY","type":"education","lineage":["https://openalex.org/I180910786"]}],"countries":["UY"],"is_corresponding":false,"raw_author_name":"Martin Rocamora","raw_affiliation_strings":["Universidad de la Rep&#x00FA;blica,Montevideo,Uruguay"],"affiliations":[{"raw_affiliation_string":"Universidad de la Rep&#x00FA;blica,Montevideo,Uruguay","institution_ids":["https://openalex.org/I180910786"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061125165","display_name":"Luca Bondi","orcid":"https://orcid.org/0000-0003-3974-7542"},"institutions":[{"id":"https://openalex.org/I4210120115","display_name":"Robert Bosch (United States)","ror":"https://ror.org/02venad53","country_code":"US","type":"company","lineage":["https://openalex.org/I4210120115","https://openalex.org/I889804353"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luca Bondi","raw_affiliation_strings":["Bosch Research,Pittsburgh,PA,USA","Bosch Research, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Bosch Research,Pittsburgh,PA,USA","institution_ids":["https://openalex.org/I4210120115"]},{"raw_affiliation_string":"Bosch Research, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I4210120115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113780845","display_name":"Julia Wilkins","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julia Wilkins","raw_affiliation_strings":["New York University,New York,NY","New York University, New York, NY"],"affiliations":[{"raw_affiliation_string":"New York University,New York,NY","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"New York University, New York, NY","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029562650","display_name":"Qianyi Shi","orcid":"https://orcid.org/0000-0003-1149-1231"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qianyi Shi","raw_affiliation_strings":["New York University,New York,NY","New York University, New York, NY"],"affiliations":[{"raw_affiliation_string":"New York University,New York,NY","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"New York University, New York, NY","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100531286","display_name":"Yao Hou","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yao Hou","raw_affiliation_strings":["New York University,New York,NY","New York University, New York, NY"],"affiliations":[{"raw_affiliation_string":"New York University,New York,NY","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"New York University, New York, NY","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110454109","display_name":"Samarjit Das","orcid":null},"institutions":[{"id":"https://openalex.org/I4210120115","display_name":"Robert Bosch (United States)","ror":"https://ror.org/02venad53","country_code":"US","type":"company","lineage":["https://openalex.org/I4210120115","https://openalex.org/I889804353"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samarjit Das","raw_affiliation_strings":["Bosch Research,Pittsburgh,PA,USA","Bosch Research, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Bosch Research,Pittsburgh,PA,USA","institution_ids":["https://openalex.org/I4210120115"]},{"raw_affiliation_string":"Bosch Research, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I4210120115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006479715","display_name":"Xavier Serra","orcid":"https://orcid.org/0000-0003-1395-2345"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Pompeu Fabra University","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Xavier Serra","raw_affiliation_strings":["Universitat Pompeu Fabra,Barcelona,Spain","Universitat Pompeu Fabra, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Universitat Pompeu Fabra,Barcelona,Spain","institution_ids":["https://openalex.org/I170486558"]},{"raw_affiliation_string":"Universitat Pompeu Fabra, Barcelona, Spain","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031398497","display_name":"Juan Pablo Bello","orcid":"https://orcid.org/0000-0001-8561-5204"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juan Pablo Bello","raw_affiliation_strings":["New York University,New York,NY","New York University, New York, NY"],"affiliations":[{"raw_affiliation_string":"New York University,New York,NY","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"New York University, New York, NY","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5021235229"],"corresponding_institution_ids":["https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":0.9777,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.75976071,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"141","last_page":"145"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9976000189781189,"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":0.9933000206947327,"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":0.7211925983428955},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6703975796699524},{"id":"https://openalex.org/keywords/sight","display_name":"Sight","score":0.6354016065597534},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6245127320289612},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.4656314253807068},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3389896750450134},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.20132040977478027},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.14536955952644348},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.1372896432876587}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7211925983428955},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6703975796699524},{"id":"https://openalex.org/C1517167","wikidata":"https://www.wikidata.org/wiki/Q1134322","display_name":"Sight","level":2,"score":0.6354016065597534},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6245127320289612},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.4656314253807068},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3389896750450134},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.20132040977478027},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.14536955952644348},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.1372896432876587},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/icassp43922.2022.9747644","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747644","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:repositori.upf.edu:10230/53526","is_oa":true,"landing_page_url":"http://hdl.handle.net/10230/53526","pdf_url":"https://repositori.upf.edu/bitstreams/961894d3-9570-4de8-a4d9-913ede655b8b/download","source":{"id":"https://openalex.org/S4306402615","display_name":"Repositori digital de la UPF (Universitat Pompeu Fabra)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I170486558","host_organization_name":"Universitat Pompeu Fabra","host_organization_lineage":["https://openalex.org/I170486558"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:repositori.upf.edu:10230/53526","is_oa":true,"landing_page_url":"http://hdl.handle.net/10230/53526","pdf_url":"https://repositori.upf.edu/bitstreams/961894d3-9570-4de8-a4d9-913ede655b8b/download","source":{"id":"https://openalex.org/S4306402615","display_name":"Repositori digital de la UPF (Universitat Pompeu Fabra)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I170486558","host_organization_name":"Universitat Pompeu Fabra","host_organization_lineage":["https://openalex.org/I170486558"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4224919395.pdf","grobid_xml":"https://content.openalex.org/works/W4224919395.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W343636949","https://openalex.org/W2108598243","https://openalex.org/W2250436945","https://openalex.org/W2340897893","https://openalex.org/W2487365028","https://openalex.org/W2509065397","https://openalex.org/W2566935005","https://openalex.org/W2593116425","https://openalex.org/W2729018917","https://openalex.org/W2771361008","https://openalex.org/W2810934215","https://openalex.org/W2939574508","https://openalex.org/W2981630388","https://openalex.org/W2982428733","https://openalex.org/W2989980422","https://openalex.org/W2998139081","https://openalex.org/W3096431533","https://openalex.org/W3098357269","https://openalex.org/W3101577715","https://openalex.org/W3106250896","https://openalex.org/W3161541317","https://openalex.org/W3170088426","https://openalex.org/W3176465185","https://openalex.org/W3178592608","https://openalex.org/W3197827948","https://openalex.org/W4293584584","https://openalex.org/W6611801654","https://openalex.org/W6722836162","https://openalex.org/W6747045456","https://openalex.org/W6750227808","https://openalex.org/W6750599028","https://openalex.org/W6784429643","https://openalex.org/W6785652829"],"related_works":["https://openalex.org/W3214178347","https://openalex.org/W2353119552","https://openalex.org/W2364379655","https://openalex.org/W2808673637","https://openalex.org/W2408516727","https://openalex.org/W2990201137","https://openalex.org/W4247920850","https://openalex.org/W2383259906","https://openalex.org/W637378572","https://openalex.org/W2378211422"],"abstract_inverted_index":{"Automatic":[0],"audio-visual":[1,50],"urban":[2],"traffic":[3],"understanding":[4],"is":[5],"a":[6,48],"growing":[7],"area":[8,39],"of":[9,15,27,64,72,75,82,94,124],"research":[10,36],"with":[11,79,89],"many":[12],"potential":[13],"applications":[14],"value":[16],"to":[17,35,117],"industry,":[18],"academia,":[19],"and":[20,32,62,91,96,103,115],"the":[21,25,60,68,109,113,122,127],"public":[22],"sector.":[23],"Yet,":[24],"lack":[26],"well-curated":[28],"resources":[29],"for":[30,58,121],"training":[31],"evaluating":[33],"models":[34],"in":[37,67,126],"this":[38,45],"hinders":[40],"their":[41],"development.":[42],"To":[43],"address":[44],"we":[46],"present":[47],"curated":[49],"dataset,":[51],"Urban":[52],"Sound":[53],"&":[54],"Sight":[55],"(Urbansas),":[56],"developed":[57],"investigating":[59],"detection":[61],"localization":[63,123],"sounding":[65],"vehicles":[66,125],"wild.":[69],"Urbansas":[70],"consists":[71],"12":[73],"hours":[74,81],"unlabeled":[76],"data":[77],"along":[78],"3":[80],"manually":[83],"annotated":[84],"data,":[85],"including":[86],"bounding":[87],"boxes":[88],"classes":[90],"unique":[92],"id":[93],"vehicles,":[95],"strong":[97],"audio":[98,130],"labels":[99],"featuring":[100],"vehicle":[101],"types":[102],"indicating":[104],"off-screen":[105],"sounds.":[106],"We":[107],"discuss":[108],"challenges":[110],"presented":[111],"by":[112],"dataset":[114],"how":[116],"use":[118],"its":[119],"annotations":[120],"wild":[128],"through":[129],"models.":[131]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2026-03-17T17:19:04.345684","created_date":"2025-10-10T00:00:00"}
