{"id":"https://openalex.org/W2900266657","doi":"https://doi.org/10.1109/waspaa.2019.8937237","title":"Identify, Locate and Separate: Audio-Visual Object Extraction in Large Video Collections Using Weak Supervision","display_name":"Identify, Locate and Separate: Audio-Visual Object Extraction in Large Video Collections Using Weak Supervision","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2900266657","doi":"https://doi.org/10.1109/waspaa.2019.8937237","mag":"2900266657"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa.2019.8937237","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2019.8937237","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1811.04000","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001145583","display_name":"Sanjeel Parekh","orcid":"https://orcid.org/0000-0002-2251-7436"},"institutions":[{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]},{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Sanjeel Parekh","raw_affiliation_strings":["Institut Polytechnique de Paris,LTCI, T\u00e9l\u00e9com Paris,France","Institut Polytechnique de Paris,LTCI, T\u00e9lecom Paris,France"],"affiliations":[{"raw_affiliation_string":"Institut Polytechnique de Paris,LTCI, T\u00e9l\u00e9com Paris,France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I12356871"]},{"raw_affiliation_string":"Institut Polytechnique de Paris,LTCI, T\u00e9lecom Paris,France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I12356871"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073788938","display_name":"Alexey Ozerov","orcid":"https://orcid.org/0000-0003-4834-5166"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexey Ozerov","raw_affiliation_strings":["Cesson S\u00e9vign\u00e9,InterDigital,France"],"affiliations":[{"raw_affiliation_string":"Cesson S\u00e9vign\u00e9,InterDigital,France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060031161","display_name":"Slim Essid","orcid":"https://orcid.org/0000-0002-0028-327X"},"institutions":[{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]},{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Slim Essid","raw_affiliation_strings":["Institut Polytechnique de Paris,LTCI, T\u00e9l\u00e9com Paris,France","Institut Polytechnique de Paris,LTCI, T\u00e9lecom Paris,France"],"affiliations":[{"raw_affiliation_string":"Institut Polytechnique de Paris,LTCI, T\u00e9l\u00e9com Paris,France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I12356871"]},{"raw_affiliation_string":"Institut Polytechnique de Paris,LTCI, T\u00e9lecom Paris,France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I12356871"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041584595","display_name":"Ngoc Q. K. Duong","orcid":"https://orcid.org/0000-0002-7627-8194"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ngoc Q. K. Duong","raw_affiliation_strings":["Cesson S\u00e9vign\u00e9,InterDigital,France"],"affiliations":[{"raw_affiliation_string":"Cesson S\u00e9vign\u00e9,InterDigital,France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076170578","display_name":"Patrick P\u00e9rez","orcid":"https://orcid.org/0000-0002-8124-1206"},"institutions":[{"id":"https://openalex.org/I220619192","display_name":"Valeo (France)","ror":"https://ror.org/04ryqpf83","country_code":"FR","type":"company","lineage":["https://openalex.org/I220619192"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Patrick Perez","raw_affiliation_strings":["Valeo.ai,Paris,France"],"affiliations":[{"raw_affiliation_string":"Valeo.ai,Paris,France","institution_ids":["https://openalex.org/I220619192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055423112","display_name":"Ga\u00ebl Richard","orcid":"https://orcid.org/0000-0002-4960-0010"},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Gael Richard","raw_affiliation_strings":["Institut Polytechnique de Paris,LTCI, T\u00e9l\u00e9com Paris,France","Institut Polytechnique de Paris,LTCI, T\u00e9lecom Paris,France"],"affiliations":[{"raw_affiliation_string":"Institut Polytechnique de Paris,LTCI, T\u00e9l\u00e9com Paris,France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I12356871"]},{"raw_affiliation_string":"Institut Polytechnique de Paris,LTCI, T\u00e9lecom Paris,France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I12356871"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5001145583"],"corresponding_institution_ids":["https://openalex.org/I12356871","https://openalex.org/I4210165912"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00460292,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"268","last_page":"272"},"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":0.9991000294685364,"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":0.988099992275238,"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/computer-science","display_name":"Computer science","score":0.8047810792922974},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6316300630569458},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5873780846595764},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5851233601570129},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5631440281867981},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.5289281010627747},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5029012560844421},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.46868470311164856},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.4390425980091095},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40845948457717896},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3992694020271301},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.3422502875328064},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.25687748193740845},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.23710983991622925},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.06153795123100281}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8047810792922974},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6316300630569458},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5873780846595764},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5851233601570129},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5631440281867981},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.5289281010627747},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5029012560844421},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.46868470311164856},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.4390425980091095},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40845948457717896},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3992694020271301},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.3422502875328064},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.25687748193740845},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.23710983991622925},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.06153795123100281},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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":5,"locations":[{"id":"doi:10.1109/waspaa.2019.8937237","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2019.8937237","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1811.04000","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.04000","pdf_url":"https://arxiv.org/pdf/1811.04000","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:HAL:hal-01914532v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-01914532","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2018","raw_type":"Preprints, Working Papers, ..."},{"id":"pmh:oai:HAL:hal-02380780v1","is_oa":false,"landing_page_url":"https://telecom-paris.hal.science/hal-02380780","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","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":"IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), Oct 2019, New Paltz, United States","raw_type":"Conference papers"},{"id":"doi:10.48550/arxiv.1811.04000","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1811.04000","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1811.04000","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.04000","pdf_url":"https://arxiv.org/pdf/1811.04000","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W7746136","https://openalex.org/W1511170870","https://openalex.org/W1536680647","https://openalex.org/W1927251054","https://openalex.org/W2039844283","https://openalex.org/W2086384421","https://openalex.org/W2108598243","https://openalex.org/W2110119381","https://openalex.org/W2113990625","https://openalex.org/W2115447976","https://openalex.org/W2127851351","https://openalex.org/W2444070604","https://openalex.org/W2524365899","https://openalex.org/W2526050071","https://openalex.org/W2619623002","https://openalex.org/W2619947201","https://openalex.org/W2632052911","https://openalex.org/W2783473931","https://openalex.org/W2963099423","https://openalex.org/W2963603913","https://openalex.org/W4289665794","https://openalex.org/W6600313631","https://openalex.org/W6680012447","https://openalex.org/W6698113398","https://openalex.org/W6702387769","https://openalex.org/W6749633790","https://openalex.org/W6749767719","https://openalex.org/W6750599028","https://openalex.org/W6751130187","https://openalex.org/W6955071965","https://openalex.org/W7071105756"],"related_works":["https://openalex.org/W2997685131","https://openalex.org/W2996889020","https://openalex.org/W2795478783","https://openalex.org/W2939663618","https://openalex.org/W3172173832","https://openalex.org/W2968808972","https://openalex.org/W2908965201","https://openalex.org/W2483684792","https://openalex.org/W3104797222","https://openalex.org/W34233450","https://openalex.org/W3118120400","https://openalex.org/W3128592932","https://openalex.org/W3118548710","https://openalex.org/W3116298410","https://openalex.org/W3203164940","https://openalex.org/W2981353300","https://openalex.org/W3034742263","https://openalex.org/W3167773216","https://openalex.org/W2963715927","https://openalex.org/W3025520547"],"abstract_inverted_index":{"We":[0,78],"tackle":[1],"the":[2,50,58],"problem":[3],"of":[4,45,73],"audio-visual":[5,19],"scene":[6],"analysis":[7],"for":[8,49],"weakly-labeled":[9],"data.":[10],"To":[11],"this":[12],"end,":[13],"we":[14],"build":[15],"upon":[16],"our":[17],"previous":[18],"representation":[20],"learning":[21,61],"framework":[22],"to":[23],"perform":[24],"object":[25,83],"classification":[26],"in":[27],"noisy":[28],"acoustic":[29],"environments":[30],"and":[31],"integrate":[32],"audio":[33,51],"source":[34],"enhancement":[35],"capability.":[36],"This":[37],"is":[38,55,65],"made":[39],"possible":[40],"by":[41],"a":[42,70],"novel":[43],"use":[44],"non-negative":[46],"matrix":[47],"factorization":[48],"modality.":[52],"Our":[53],"approach":[54],"founded":[56],"on":[57],"multiple":[59],"instance":[60],"paradigm.":[62],"Its":[63],"effectiveness":[64],"established":[66],"through":[67],"experiments":[68],"over":[69],"challenging":[71],"dataset":[72],"music":[74],"instrument":[75],"performance":[76],"videos.":[77],"also":[79],"show":[80],"encouraging":[81],"visual":[82],"localization":[84],"results.":[85]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2018-11-16T00:00:00"}
