{"id":"https://openalex.org/W2939726645","doi":"https://doi.org/10.1109/icassp.2019.8683142","title":"Seeing through Sounds: Predicting Visual Semantic Segmentation Results from Multichannel Audio Signals","display_name":"Seeing through Sounds: Predicting Visual Semantic Segmentation Results from Multichannel Audio Signals","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2939726645","doi":"https://doi.org/10.1109/icassp.2019.8683142","mag":"2939726645"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683142","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683142","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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/A5017607351","display_name":"Go Irie","orcid":"https://orcid.org/0000-0002-4309-4700"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Go Irie","raw_affiliation_strings":["NTT Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077540018","display_name":"Mirela O\u0161trek","orcid":null},"institutions":[{"id":"https://openalex.org/I181343428","display_name":"University of Zagreb","ror":"https://ror.org/00mv6sv71","country_code":"HR","type":"education","lineage":["https://openalex.org/I181343428"]}],"countries":["HR"],"is_corresponding":false,"raw_author_name":"Mirela Ostrek","raw_affiliation_strings":["The University of Zagreb"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Zagreb","institution_ids":["https://openalex.org/I181343428"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100645292","display_name":"Haochen Wang","orcid":"https://orcid.org/0000-0001-9886-2722"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Haochen Wang","raw_affiliation_strings":["The University of British Columbia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of British Columbia","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001243214","display_name":"Hirokazu Kameoka","orcid":"https://orcid.org/0000-0003-3102-0162"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hirokazu Kameoka","raw_affiliation_strings":["NTT Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102267134","display_name":"Akisato Kimura","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akisato Kimura","raw_affiliation_strings":["NTT Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029349765","display_name":"Takahito Kawanishi","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takahito Kawanishi","raw_affiliation_strings":["NTT Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061465935","display_name":"Kunio Kashino","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kunio Kashino","raw_affiliation_strings":["NTT Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2938,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.88788381,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3961","last_page":"3964"},"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":0.9994000196456909,"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":0.9904000163078308,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8330442905426025},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7452191114425659},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6631772518157959},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6029783487319946},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5669043064117432},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5174239873886108},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.515381932258606},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4704647958278656},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46581175923347473},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.44625434279441833},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4326499402523041},{"id":"https://openalex.org/keywords/bilinear-interpolation","display_name":"Bilinear interpolation","score":0.4132690131664276},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4100589156150818},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3804963529109955},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.06336155533790588}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8330442905426025},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7452191114425659},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6631772518157959},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6029783487319946},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5669043064117432},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5174239873886108},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.515381932258606},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4704647958278656},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46581175923347473},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.44625434279441833},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4326499402523041},{"id":"https://openalex.org/C205203396","wikidata":"https://www.wikidata.org/wiki/Q612143","display_name":"Bilinear interpolation","level":2,"score":0.4132690131664276},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4100589156150818},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3804963529109955},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.06336155533790588},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/icassp.2019.8683142","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683142","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.47999998927116394,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1575829986","https://openalex.org/W2032337854","https://openalex.org/W2046317813","https://openalex.org/W2052666245","https://openalex.org/W2161226030","https://openalex.org/W2342662179","https://openalex.org/W2395611524","https://openalex.org/W2511428026","https://openalex.org/W2619697695","https://openalex.org/W2729172879","https://openalex.org/W2963066677","https://openalex.org/W2963680395","https://openalex.org/W2963717374","https://openalex.org/W2964345931","https://openalex.org/W4256399001","https://openalex.org/W4398958419","https://openalex.org/W6740616720","https://openalex.org/W6869415701"],"related_works":["https://openalex.org/W2517104666","https://openalex.org/W2005437358","https://openalex.org/W1669643531","https://openalex.org/W2008656436","https://openalex.org/W2134924024","https://openalex.org/W2023558673","https://openalex.org/W2110230079","https://openalex.org/W1982826852","https://openalex.org/W2613186388","https://openalex.org/W2546942002"],"abstract_inverted_index":{"Sounds":[0],"provide":[1],"us":[2,15],"with":[3,52,100],"vast":[4],"amounts":[5],"of":[6,18,41,49],"information":[7],"about":[8],"surrounding":[9],"objects":[10],"and":[11,95,103],"can":[12,111],"even":[13],"remind":[14],"visual":[16,96],"images":[17,116],"them.":[19],"Is":[20],"it":[21],"possible":[22],"to":[23,67],"implement":[24],"this":[25,32],"noteworthy":[26],"human":[27],"ability":[28],"on":[29],"machines?":[30],"In":[31],"paper,":[33],"we":[34],"study":[35],"a":[36,60],"new":[37],"task":[38],"that":[39,64,87,108],"consists":[40],"predicting":[42],"image":[43],"recognition":[44],"results":[45,72],"in":[46],"the":[47,113],"form":[48],"semantic":[50,70],"segmentation":[51,71],"given":[53],"multichannel":[54],"audio":[55,75,94],"signals.":[56],"Our":[57],"approach":[58,110],"uses":[59],"convolutional":[61],"neural":[62],"network":[63],"is":[65,85],"designed":[66],"directly":[68],"output":[69],"by":[73],"taking":[74],"features":[76],"as":[77],"its":[78],"inputs.":[79],"A":[80],"bilinear":[81],"feature":[82],"fusion":[83],"scheme":[84],"incorporated":[86],"efficiently":[88],"models":[89],"underlying":[90],"higher-order":[91],"interactions":[92],"between":[93],"sources.":[97],"Experimental":[98],"evaluations":[99],"both":[101],"synthetic":[102],"real":[104],"sound":[105],"datasets":[106],"show":[107],"our":[109],"recover":[112],"desired":[114],"segmented":[115],"reasonably":[117],"well.":[118]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}