{"id":"https://openalex.org/W3015432252","doi":"https://doi.org/10.1109/icassp40776.2020.9054280","title":"Learning Differentiable Sparse and Low Rank Networks for Audio-Visual Object Localization","display_name":"Learning Differentiable Sparse and Low Rank Networks for Audio-Visual Object Localization","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015432252","doi":"https://doi.org/10.1109/icassp40776.2020.9054280","mag":"3015432252"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054280","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054280","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/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":true,"raw_author_name":"Jie Pu","raw_affiliation_strings":["Department of Computing, Imperial College, London, UK"],"affiliations":[{"raw_affiliation_string":"Department 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/I200777214","display_name":"National and Kapodistrian University of Athens","ror":"https://ror.org/04gnjpq42","country_code":"GR","type":"education","lineage":["https://openalex.org/I200777214"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Yannis Panagakis","raw_affiliation_strings":["Department of Informatics and Telecommunications, University of Athens, Greece"],"affiliations":[{"raw_affiliation_string":"Department of Informatics and Telecommunications, University of Athens, Greece","institution_ids":["https://openalex.org/I200777214"]}]},{"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"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Maja Pantic","raw_affiliation_strings":["Department of Computing, Imperial College, London, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computing, Imperial College, London, UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102721941"],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":0.5282,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.58849157,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"8668","last_page":"8672"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7618532180786133},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.6464957594871521},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.5783872604370117},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5769637823104858},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5104300379753113},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5077870488166809},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4446121156215668},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4432346820831299},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4398176074028015},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43752801418304443},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.43516650795936584},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3531748056411743},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.32009029388427734},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10431423783302307}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7618532180786133},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.6464957594871521},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.5783872604370117},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5769637823104858},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5104300379753113},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5077870488166809},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4446121156215668},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4432346820831299},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4398176074028015},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43752801418304443},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.43516650795936584},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3531748056411743},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32009029388427734},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10431423783302307},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054280","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054280","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4770326006","display_name":null,"funder_award_id":"EP/N007743/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W33208438","https://openalex.org/W1665214252","https://openalex.org/W1669104078","https://openalex.org/W1890623278","https://openalex.org/W1906770428","https://openalex.org/W2099151709","https://openalex.org/W2103972604","https://openalex.org/W2116861100","https://openalex.org/W2118103795","https://openalex.org/W2118375674","https://openalex.org/W2129812935","https://openalex.org/W2135046866","https://openalex.org/W2145962650","https://openalex.org/W2146444479","https://openalex.org/W2147704751","https://openalex.org/W2154992274","https://openalex.org/W2164098335","https://openalex.org/W2342749827","https://openalex.org/W2660943524","https://openalex.org/W2788495591","https://openalex.org/W2889134685","https://openalex.org/W2904140938","https://openalex.org/W2946304400","https://openalex.org/W2972675027","https://openalex.org/W4288351536","https://openalex.org/W6637242042","https://openalex.org/W6677645113","https://openalex.org/W6682766550","https://openalex.org/W6748845858","https://openalex.org/W6754103055","https://openalex.org/W6756969035","https://openalex.org/W6762973898"],"related_works":["https://openalex.org/W4285277090","https://openalex.org/W4327738859","https://openalex.org/W2348722996","https://openalex.org/W2334570605","https://openalex.org/W3181683615","https://openalex.org/W4286826125","https://openalex.org/W1633485514","https://openalex.org/W2068608913","https://openalex.org/W1604739066","https://openalex.org/W2115878407"],"abstract_inverted_index":{"Parsimonious":[0],"modelling,":[1],"including":[2],"sparsity":[3],"and":[4,15,30,57,80,97,128],"low":[5],"rankness,":[6],"has":[7],"becomes":[8],"a":[9,46,65],"cornerstone":[10],"in":[11,108],"modern":[12],"machine":[13],"learning":[14],"signal":[16],"processing.":[17],"However,":[18],"these":[19],"modelling":[20],"techniques":[21],"have":[22],"limited":[23],"capabity":[24],"to":[25,36,49],"learn":[26,64],"from":[27,68],"large-scale":[28],"data,":[29],"often":[31],"require":[32],"some":[33],"pre-defined":[34],"parameters":[35],"define":[37],"their":[38],"optimization":[39,93],"procedure.":[40],"In":[41,71],"this":[42],"paper,":[43],"we":[44,73],"propose":[45],"novel":[47],"method":[48,105,124],"design":[50,74],"specific":[51],"deep":[52],"neural":[53],"networks":[54],"for":[55,78],"sparse":[56,79,96,127],"low-rank":[58,81,98,129],"models,":[59],"where":[60],"the":[61,86,92,103,109,118,122],"network":[62,76,87],"can":[63],"data-adaptive":[66],"model":[67],"training":[69],"data.":[70],"particular,":[72],"differentiable":[75],"units":[77],"matrices.":[82],"Each":[83],"layer":[84],"of":[85,91,95,102,111,121],"represents":[88],"one":[89],"iteration":[90],"process":[94],"models.":[99,130],"The":[100],"effectiveness":[101],"proposed":[104,123],"is":[106],"evaluated":[107],"task":[110],"audio-visual":[112],"object":[113],"localization.":[114],"Experimental":[115],"results":[116],"indicate":[117],"superior":[119],"performance":[120],"over":[125],"traditional":[126]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}