{"id":"https://openalex.org/W3161541317","doi":"https://doi.org/10.1109/icassp39728.2021.9415085","title":"A Curated Dataset of Urban Scenes for Audio-Visual Scene Analysis","display_name":"A Curated Dataset of Urban Scenes for Audio-Visual Scene Analysis","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3161541317","doi":"https://doi.org/10.1109/icassp39728.2021.9415085","mag":"3161541317"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9415085","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9415085","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100406235","display_name":"Shanshan Wang","orcid":"https://orcid.org/0000-0001-9530-6958"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Shanshan Wang","raw_affiliation_strings":["Tampere University, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079981416","display_name":"Annamaria Mesaros","orcid":"https://orcid.org/0000-0002-6640-9752"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Annamaria Mesaros","raw_affiliation_strings":["Tampere University, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059929826","display_name":"Toni Heittola","orcid":"https://orcid.org/0000-0002-8855-0415"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Toni Heittola","raw_affiliation_strings":["Tampere University, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049691461","display_name":"Tuomas Virtanen","orcid":"https://orcid.org/0000-0002-4604-9729"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tuomas Virtanen","raw_affiliation_strings":["Tampere University, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100406235"],"corresponding_institution_ids":["https://openalex.org/I166825849"],"apc_list":null,"apc_paid":null,"fwci":5.0922,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.96289363,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"626","last_page":"630"},"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":0.9984999895095825,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9829000234603882,"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/audio-visual","display_name":"Audio visual","score":0.8597500324249268},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7744539976119995},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.6914834976196289},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5414424538612366},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5009291172027588},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49782538414001465},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.48869994282722473},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.47563791275024414},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.45810747146606445},{"id":"https://openalex.org/keywords/scene-statistics","display_name":"Scene statistics","score":0.4358213245868683},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.40200552344322205},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3164695203304291},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.26141157746315},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.23160386085510254},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.11335700750350952},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08461755514144897},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.06346040964126587}],"concepts":[{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.8597500324249268},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7744539976119995},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.6914834976196289},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5414424538612366},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5009291172027588},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49782538414001465},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.48869994282722473},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47563791275024414},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.45810747146606445},{"id":"https://openalex.org/C197654239","wikidata":"https://www.wikidata.org/wiki/Q7430757","display_name":"Scene statistics","level":3,"score":0.4358213245868683},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.40200552344322205},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3164695203304291},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.26141157746315},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.23160386085510254},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.11335700750350952},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08461755514144897},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.06346040964126587},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp39728.2021.9415085","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9415085","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:trepo.tuni.fi:10024/220714","is_oa":false,"landing_page_url":"https://trepo.tuni.fi/handle/10024/220714","pdf_url":null,"source":{"id":"https://openalex.org/S7407055260","display_name":"Trepo - Institutional Repository of Tampere University","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.8600000143051147}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W1482998036","https://openalex.org/W1522301498","https://openalex.org/W1927052826","https://openalex.org/W2016053056","https://openalex.org/W2103235956","https://openalex.org/W2194775991","https://openalex.org/W2243105741","https://openalex.org/W2524365899","https://openalex.org/W2551572271","https://openalex.org/W2570915410","https://openalex.org/W2593116425","https://openalex.org/W2619697695","https://openalex.org/W2703895418","https://openalex.org/W2883935097","https://openalex.org/W2939574508","https://openalex.org/W2952746495","https://openalex.org/W2957789971","https://openalex.org/W2962865004","https://openalex.org/W2963115079","https://openalex.org/W2964121744","https://openalex.org/W2982346427","https://openalex.org/W3000312913","https://openalex.org/W3015530480","https://openalex.org/W3034658206","https://openalex.org/W4295723153","https://openalex.org/W6600983433","https://openalex.org/W6631190155","https://openalex.org/W6654335291","https://openalex.org/W6750599028","https://openalex.org/W6752516136","https://openalex.org/W6765212446"],"related_works":["https://openalex.org/W2098934641","https://openalex.org/W3011716530","https://openalex.org/W3096250625","https://openalex.org/W3135871143","https://openalex.org/W4382560817","https://openalex.org/W2347715673","https://openalex.org/W2405875744","https://openalex.org/W2020966186","https://openalex.org/W296599067","https://openalex.org/W4387698063"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,46],"curated":[4],"dataset":[5],"of":[6,15,58,70],"urban":[7],"scenes":[8],"for":[9,36,49,84,89],"audio-visual":[10,50],"scene":[11,51],"analysis":[12],"which":[13],"consists":[14],"carefully":[16],"selected":[17],"and":[18,39,53,60,87],"recorded":[19,24],"material.":[20],"The":[21],"data":[22],"was":[23],"in":[25,33],"multiple":[26,34],"European":[27],"cities,":[28],"using":[29],"the":[30,71,85,90],"same":[31],"equipment,":[32],"locations":[35],"each":[37],"scene,":[38],"is":[40],"openly":[41],"available.":[42],"We":[43],"also":[44],"present":[45],"case":[47],"study":[48],"recognition":[52],"show":[54],"that":[55],"joint":[56],"modeling":[57],"audio":[59],"visual":[61],"modalities":[62],"brings":[63],"significant":[64],"performance":[65],"gain":[66],"compared":[67,81],"to":[68,82],"state":[69],"art":[72],"uni-modal":[73],"systems.":[74,93],"Our":[75],"approach":[76],"obtained":[77],"an":[78],"84.8%":[79],"ac-curacy":[80],"75.8%":[83],"audio-only":[86],"68.4%":[88],"video-only":[91],"equivalent":[92]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":5}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}
