{"id":"https://openalex.org/W3183230691","doi":"https://doi.org/10.1109/euvip50544.2021.9484036","title":"Leveraging Category Information for Single-Frame Visual Sound Source Separation","display_name":"Leveraging Category Information for Single-Frame Visual Sound Source Separation","publication_year":2021,"publication_date":"2021-06-23","ids":{"openalex":"https://openalex.org/W3183230691","doi":"https://doi.org/10.1109/euvip50544.2021.9484036","mag":"3183230691"},"language":"en","primary_location":{"id":"doi:10.1109/euvip50544.2021.9484036","is_oa":false,"landing_page_url":"https://doi.org/10.1109/euvip50544.2021.9484036","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 9th European Workshop on Visual Information Processing (EUVIP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5072533941","display_name":"Lingyu Zhu","orcid":"https://orcid.org/0000-0001-6707-6665"},"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":"Lingyu Zhu","raw_affiliation_strings":["Tampere University, Finland","Tampere University,Computer Vision Group,Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tampere University, Finland","institution_ids":["https://openalex.org/I166825849"]},{"raw_affiliation_string":"Tampere University,Computer Vision Group,Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088180438","display_name":"Esa Rahtu","orcid":"https://orcid.org/0000-0001-8767-0864"},"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":"Esa Rahtu","raw_affiliation_strings":["Tampere University, Finland","Tampere University,Computer Vision Group,Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tampere University, Finland","institution_ids":["https://openalex.org/I166825849"]},{"raw_affiliation_string":"Tampere University,Computer Vision Group,Finland","institution_ids":["https://openalex.org/I166825849"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I166825849"],"apc_list":null,"apc_paid":null,"fwci":1.0878,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.78382109,"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":"1","last_page":"6"},"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":0.9969000220298767,"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":0.9940000176429749,"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":0.7148864269256592},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5558453798294067},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5198686122894287},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.517398476600647},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.516330361366272},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4021334648132324},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3327394723892212},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3253107964992523},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.19793987274169922},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1224551796913147}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7148864269256592},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5558453798294067},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5198686122894287},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.517398476600647},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.516330361366272},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4021334648132324},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3327394723892212},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3253107964992523},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.19793987274169922},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1224551796913147},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/euvip50544.2021.9484036","is_oa":false,"landing_page_url":"https://doi.org/10.1109/euvip50544.2021.9484036","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 9th European Workshop on Visual Information Processing (EUVIP)","raw_type":"proceedings-article"},{"id":"pmh:oai:trepo.tuni.fi:10024/220681","is_oa":false,"landing_page_url":"https://trepo.tuni.fi/handle/10024/220681","pdf_url":null,"source":{"id":"https://openalex.org/S4306401860","display_name":"Tampere University Institutional Repository (Tampere University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I150589677","host_organization_name":"Tampere University of Applied Sciences","host_organization_lineage":["https://openalex.org/I150589677"],"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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2105582566","https://openalex.org/W2164899449","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2619697695","https://openalex.org/W2796992393","https://openalex.org/W2962865004","https://openalex.org/W2962960500","https://openalex.org/W2962969419","https://openalex.org/W2963115079","https://openalex.org/W2963163009","https://openalex.org/W2963218389","https://openalex.org/W2981816492","https://openalex.org/W2981851635","https://openalex.org/W2988200020","https://openalex.org/W3017343282","https://openalex.org/W3089887959","https://openalex.org/W3106362698","https://openalex.org/W3109606338","https://openalex.org/W3116298410","https://openalex.org/W3123318516","https://openalex.org/W4287608901","https://openalex.org/W4289665794","https://openalex.org/W6639824700","https://openalex.org/W6684193366","https://openalex.org/W6747045456","https://openalex.org/W6749767719","https://openalex.org/W6750591037","https://openalex.org/W6750599028","https://openalex.org/W6779411601","https://openalex.org/W6782004394","https://openalex.org/W6785011006"],"related_works":["https://openalex.org/W2071676784","https://openalex.org/W2909726438","https://openalex.org/W4292513318","https://openalex.org/W2067046791","https://openalex.org/W2909888262","https://openalex.org/W2287611352","https://openalex.org/W2021161555","https://openalex.org/W2056769785","https://openalex.org/W320684304","https://openalex.org/W2077498359"],"abstract_inverted_index":{"Visual":[0],"sound":[1,7,12,52,71],"source":[2,72],"separation":[3,53,76],"aims":[4],"at":[5,95,140],"identifying":[6],"components":[8],"from":[9,109],"a":[10,56],"given":[11],"mixture":[13],"with":[14,27,117],"the":[15,28,67,70,75,90,96,104,110,118],"presence":[16],"of":[17,30,69],"visual":[18,51],"cues.":[19],"Prior":[20],"works":[21],"have":[22],"demonstrated":[23],"impressive":[24],"results,":[25],"but":[26],"expense":[29],"large":[31],"multi-stage":[32],"architectures":[33],"and":[34],"complex":[35],"data":[36],"representations":[37],"(e.g.":[38],"optical":[39],"flow":[40],"trajectories).":[41],"In":[42],"contrast,":[43],"we":[44,81,86,101],"study":[45],"simple":[46],"yet":[47],"efficient":[48],"models":[49,62,84],"for":[50],"using":[54],"only":[55],"single":[57],"video":[58],"frame.":[59],"Furthermore,":[60],"our":[61,123],"are":[63,93,108],"able":[64],"to":[65,131],"exploit":[66],"information":[68],"category":[73,91],"in":[74],"process.":[77],"To":[78],"this":[79],"end,":[80],"propose":[82],"two":[83],"where":[85],"assume":[87],"that":[88,122],"i)":[89],"labels":[92],"available":[94,139],"training":[97,105],"time,":[98],"or":[99,112,127],"ii)":[100],"know":[102],"if":[103],"sample":[106],"pairs":[107],"same":[111],"different":[113],"category.":[114],"The":[115,136],"experiments":[116],"MUSIC":[119],"dataset":[120],"show":[121],"model":[124],"obtains":[125],"comparable":[126],"better":[128],"performance":[129],"compared":[130],"several":[132],"recent":[133],"baseline":[134],"methods.":[135],"code":[137],"is":[138],"https://github.com/ly-zhu/Leveraging-Category-Information-for-Single-Frame-Visual-Sound-Source-Separation.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}