{"id":"https://openalex.org/W2660943524","doi":"https://doi.org/10.1109/icassp.2017.7952687","title":"Audio-visual object localization and separation using low-rank and sparsity","display_name":"Audio-visual object localization and separation using low-rank and sparsity","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2660943524","doi":"https://doi.org/10.1109/icassp.2017.7952687","mag":"2660943524"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7952687","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952687","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5102721941","display_name":"Jie Pu","orcid":"https://orcid.org/0000-0002-5813-1201"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jie Pu","raw_affiliation_strings":["Deparment of Computing, Imperial College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deparment of Computing, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050734738","display_name":"Yannis Panagakis","orcid":"https://orcid.org/0000-0003-0153-5210"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yannis Panagakis","raw_affiliation_strings":["Deparment of Computing, Imperial College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deparment of Computing, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009475700","display_name":"Stavros Petridis","orcid":"https://orcid.org/0000-0001-7478-9479"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Stavros Petridis","raw_affiliation_strings":["Deparment of Computing, Imperial College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deparment of Computing, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016033078","display_name":"Maja Panti\u0107","orcid":"https://orcid.org/0000-0002-3620-5986"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]},{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["GB","NL"],"is_corresponding":false,"raw_author_name":"Maja Pantic","raw_affiliation_strings":["Deparment of Computing, Imperial College London, UK","EEMCS, University of Twente, NL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deparment of Computing, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"EEMCS, University of Twente, NL","institution_ids":["https://openalex.org/I94624287"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6216,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.9220555,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2901","last_page":"2905"},"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.998199999332428,"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"}},{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.9980000257492065,"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":0.7453080415725708},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6510301232337952},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6333597898483276},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.5677706599235535},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5100403428077698},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5095217823982239},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.502823531627655},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.502408504486084},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4901729226112366},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4810636043548584},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4737071692943573},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.47309496998786926},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.462811142206192},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38752102851867676},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13131946325302124},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.10136538743972778}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7453080415725708},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6510301232337952},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6333597898483276},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.5677706599235535},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5100403428077698},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5095217823982239},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.502823531627655},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.502408504486084},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4901729226112366},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4810636043548584},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4737071692943573},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.47309496998786926},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.462811142206192},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38752102851867676},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13131946325302124},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.10136538743972778},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2017.7952687","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952687","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:ris.utwente.nl:openaire_cris_publications/0f38c937-356b-407b-9bce-d736c36c96a3","is_oa":false,"landing_page_url":"https://research.utwente.nl/en/publications/0f38c937-356b-407b-9bce-d736c36c96a3","pdf_url":null,"source":{"id":"https://openalex.org/S4406922991","display_name":"University of Twente Research Information","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pu, J, Panagakis, Y, Petridis, S & Pantic, M 2017, Audio-visual object localization and separation using low-rank and sparsity. in 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings., 7952687, IEEE, pp. 2901-2905, 42nd IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017, New Orleans, Louisiana, United States, 5/03/17. https://doi.org/10.1109/ICASSP.2017.7952687","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:eprints.mdx.ac.uk:23780","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400025","display_name":"Middlesex University Research Repository (Middlesex University Of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I60488453","host_organization_name":"Middlesex University","host_organization_lineage":["https://openalex.org/I60488453"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"},{"id":"pmh:oai:spiral.imperial.ac.uk:10044/1/55084","is_oa":false,"landing_page_url":"http://hdl.handle.net/10044/1/55084","pdf_url":null,"source":{"id":"https://openalex.org/S4306401396","display_name":"Spiral (Imperial College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I47508984","host_organization_name":"Imperial College London","host_organization_lineage":["https://openalex.org/I47508984"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2905","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W290456254","https://openalex.org/W1518556865","https://openalex.org/W1890623278","https://openalex.org/W2013854956","https://openalex.org/W2018832332","https://openalex.org/W2028781966","https://openalex.org/W2065274193","https://openalex.org/W2065760681","https://openalex.org/W2096391593","https://openalex.org/W2103972604","https://openalex.org/W2105582566","https://openalex.org/W2127851351","https://openalex.org/W2145962650","https://openalex.org/W2147704751","https://openalex.org/W2148659689","https://openalex.org/W2159898352","https://openalex.org/W2164098335","https://openalex.org/W2168010845","https://openalex.org/W2170502958","https://openalex.org/W2171819471","https://openalex.org/W2342749827","https://openalex.org/W2912522929","https://openalex.org/W4285719527","https://openalex.org/W6610552112"],"related_works":["https://openalex.org/W1509813908","https://openalex.org/W2031820693","https://openalex.org/W3024816962","https://openalex.org/W973023320","https://openalex.org/W1910172735","https://openalex.org/W2118307209","https://openalex.org/W2107364365","https://openalex.org/W3112881379","https://openalex.org/W2002298560","https://openalex.org/W2019256813"],"abstract_inverted_index":{"The":[0,81,187],"ability":[1],"to":[2,54,67,88,100],"localize":[3],"visual":[4,40,92,110,143,177],"objects":[5],"that":[6],"are":[7],"associated":[8,147],"with":[9],"an":[10,78],"audio":[11,20,43,94,108,150,180,185],"source":[12,73,141],"and":[13,75,93,96,109,145,165,179,182],"at":[14],"the":[15,19,39,69,90,102,107,125,129,134,139,146,160,172,191,194],"same":[16],"time":[17],"seperate":[18],"signal":[21,29],"is":[22,168],"a":[23,120,155],"corner":[24],"stone":[25],"in":[26,77,86,98,142,149,175],"several":[27],"audio-visual":[28,72],"processing":[30],"applications.":[31],"Past":[32],"efforts":[33],"usually":[34],"focused":[35],"on":[36],"localizing":[37],"only":[38],"objects,":[41],"without":[42],"separation":[44,76,181],"abilities.":[45],"Besides,":[46],"they":[47],"often":[48],"rely":[49],"computational":[50],"expensive":[51],"pre-processing":[52],"steps":[53],"segment":[55],"images":[56],"pixels":[57],"into":[58,119],"object":[59],"regions":[60],"before":[61],"applying":[62],"localization":[63,74,178],"approaches.":[64],"We":[65,170],"aim":[66],"address":[68],"problem":[70],"of":[71,122,162,193],"unsupervised":[79],"manner.":[80],"proposed":[82,173,195],"approach":[83],"employs":[84],"low-rank":[85,126],"order":[87,99],"model":[89,115],"background":[91,130],"information":[95],"sparsity":[97],"extract":[101],"sparsely":[103],"correlated":[104,136],"components":[105,137],"between":[106],"modalities.":[111],"In":[112],"particular,":[113],"this":[114,153],"decomposes":[116],"each":[117],"dataset":[118],"sum":[121],"two":[123],"terms:":[124],"matrices":[127],"capturing":[128],"uncorrelated":[131],"information,":[132],"while":[133],"sparse":[135],"modelling":[138],"sound":[140,148],"modality":[144],"modality.":[151],"To":[152],"end":[154],"novel":[156],"optimization":[157],"problem,":[158],"involving":[159],"minimization":[161],"nuclear":[163],"norms":[164],"matrix":[166],"\u21131-norms":[167],"solved.":[169],"evaluated":[171],"method":[174],"1)":[176],"2)":[183],"visual-assisted":[184],"denoising.":[186],"experimental":[188],"results":[189],"demonstrate":[190],"effectiveness":[192],"method.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":6}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}