{"id":"https://openalex.org/W2888525151","doi":"https://doi.org/10.1145/3264869.3264876","title":"An Audio-Visual Method for Room Boundary Estimation and Material Recognition","display_name":"An Audio-Visual Method for Room Boundary Estimation and Material Recognition","publication_year":2018,"publication_date":"2018-10-17","ids":{"openalex":"https://openalex.org/W2888525151","doi":"https://doi.org/10.1145/3264869.3264876","mag":"2888525151"},"language":"en","primary_location":{"id":"doi:10.1145/3264869.3264876","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3264869.3264876","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 Workshop on Audio-Visual Scene Understanding for Immersive Multimedia","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/A5012558214","display_name":"Luca Remaggi","orcid":"https://orcid.org/0000-0002-4133-7043"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Luca Remaggi","raw_affiliation_strings":["University of Surrey, Guildford, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Surrey, Guildford, United Kingdom","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668564","display_name":"Hansung Kim","orcid":"https://orcid.org/0000-0003-4907-0491"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hansung Kim","raw_affiliation_strings":["University of Surrey, Guildford, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Surrey, Guildford, United Kingdom","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022165330","display_name":"Philip J. B. Jackson","orcid":"https://orcid.org/0000-0001-7933-5935"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Philip J. B. Jackson","raw_affiliation_strings":["University of Surrey, Guildford, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Surrey, Guildford, United Kingdom","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016376222","display_name":"Adrian Hilton","orcid":"https://orcid.org/0000-0003-4223-238X"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Adrian Hilton","raw_affiliation_strings":["University of Surrey, Guildford, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Surrey, Guildford, United Kingdom","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5012558214"],"corresponding_institution_ids":["https://openalex.org/I28290843"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.08611382,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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":0.9991999864578247,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9966999888420105,"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/T11309","display_name":"Music and Audio Processing","score":0.9955999851226807,"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":0.7041702270507812},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6535429358482361},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5350306034088135},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5103530287742615},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5000655651092529},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.4818621575832367},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.4747629165649414},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40657711029052734},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.2032671868801117},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15536656975746155},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10130992531776428}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7041702270507812},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6535429358482361},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5350306034088135},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5103530287742615},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5000655651092529},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.4818621575832367},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.4747629165649414},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40657711029052734},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2032671868801117},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15536656975746155},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10130992531776428},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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":4,"locations":[{"id":"doi:10.1145/3264869.3264876","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3264869.3264876","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 Workshop on Audio-Visual Scene Understanding for Immersive Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:alma.44SUR_INST:11138932670002346","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4210197018","display_name":"View","issn_l":"2688-268X","issn":["2688-268X","2688-3988"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:eprints.soton.ac.uk:440624","is_oa":false,"landing_page_url":"https://eprints.soton.ac.uk/440624/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401019","display_name":"ePrints Soton (University of Southampton)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I43439940","host_organization_name":"University of Southampton","host_organization_lineage":["https://openalex.org/I43439940"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"},{"id":"pmh:oai:epubs.surrey.ac.uk:848909","is_oa":false,"landing_page_url":"http://epubs.surrey.ac.uk/848909/1/An%20Audio-Visual%20Method%20for%20Room%20Boundary%20Estimation%20and%20Material%20Recognition.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400680","display_name":"Surrey Research Insight Open Access (The University of Surrey)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28290843","host_organization_name":"University of Surrey","host_organization_lineage":["https://openalex.org/I28290843"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3034362336","display_name":null,"funder_award_id":"EP/P022529/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G3186182679","display_name":null,"funder_award_id":"EP/L000539/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G4179231495","display_name":null,"funder_award_id":"EP/M028321/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G88623513","display_name":"S3A: Future Spatial Audio for an Immersive Listener Experience at Home","funder_award_id":"EP/L000539/1","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W586860715","https://openalex.org/W1569827162","https://openalex.org/W1583969828","https://openalex.org/W1686810756","https://openalex.org/W1824657313","https://openalex.org/W1875842236","https://openalex.org/W1923184257","https://openalex.org/W1937507046","https://openalex.org/W1957167950","https://openalex.org/W1977422919","https://openalex.org/W1983038426","https://openalex.org/W1989689139","https://openalex.org/W1991023844","https://openalex.org/W1997013925","https://openalex.org/W2004918195","https://openalex.org/W2024668293","https://openalex.org/W2033513078","https://openalex.org/W2046481736","https://openalex.org/W2048801232","https://openalex.org/W2048989926","https://openalex.org/W2067503923","https://openalex.org/W2071527584","https://openalex.org/W2075019799","https://openalex.org/W2104974755","https://openalex.org/W2122122381","https://openalex.org/W2130695501","https://openalex.org/W2136329566","https://openalex.org/W2148983977","https://openalex.org/W2160014001","https://openalex.org/W2170505850","https://openalex.org/W2216928620","https://openalex.org/W2293524877","https://openalex.org/W2345333930","https://openalex.org/W2517209484","https://openalex.org/W2537586743","https://openalex.org/W2539881804","https://openalex.org/W2551540143","https://openalex.org/W2553843898","https://openalex.org/W2560722161","https://openalex.org/W2608754794","https://openalex.org/W2613360184","https://openalex.org/W2724657720","https://openalex.org/W2735025588","https://openalex.org/W2764198839","https://openalex.org/W2771343701","https://openalex.org/W2788444396","https://openalex.org/W2963881378","https://openalex.org/W2964180491","https://openalex.org/W2997591727","https://openalex.org/W3021938204","https://openalex.org/W3022709808","https://openalex.org/W4206434639","https://openalex.org/W4231290138","https://openalex.org/W4241946090","https://openalex.org/W4253570578","https://openalex.org/W4256010046","https://openalex.org/W6638373262"],"related_works":["https://openalex.org/W1891287906","https://openalex.org/W1969923398","https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2755342338","https://openalex.org/W2229312674","https://openalex.org/W3116076068","https://openalex.org/W2048756857","https://openalex.org/W2008268297","https://openalex.org/W4304891817"],"abstract_inverted_index":{"In":[0,34],"applications":[1],"such":[2],"as":[3,66],"virtual":[4],"and":[5,10,31,80,116,135,141,145],"augmented":[6],"reality,":[7],"a":[8,48,88,129],"plausible":[9],"coherent":[11],"audio-visual":[12,40],"reproduction":[13],"can":[14],"be":[15],"achieved":[16],"by":[17,57,73,106,128],"deeply":[18],"understanding":[19],"the":[20,28,78,104,139],"reference":[21,142],"scene":[22,29,44],"acoustics.":[23],"This":[24],"requires":[25],"knowledge":[26],"of":[27],"geometry":[30],"related":[32],"materials.":[33],"this":[35],"paper,":[36],"we":[37,85],"present":[38],"an":[39],"approach":[41],"for":[42],"acoustic":[43,58,61],"understanding.":[45],"We":[46],"propose":[47],"novel":[49],"material":[50],"recognition":[51],"algorithm,":[52],"that":[53,84],"exploits":[54],"information":[55,75],"carried":[56],"signals.":[59],"The":[60,68,118],"absorption":[62],"coefficients":[63],"are":[64,100,121],"selected":[65],"features.":[67],"training":[69],"dataset":[70],"was":[71],"constructed":[72],"combining":[74],"available":[76],"in":[77,87,110],"literature,":[79],"additional":[81],"labeled":[82],"data":[83,108],"recorded":[86,109],"small":[89],"room":[90,125,143],"having":[91,113],"short":[92],"reverberation":[93],"time":[94],"(RT60).":[95],"Classic":[96],"machine":[97],"learning":[98],"methods":[99],"used":[101],"to":[102,123],"validate":[103],"model,":[105],"employing":[107],"five":[111],"rooms,":[112],"different":[114],"sizes":[115],"RT60s.":[117],"estimated":[119,140],"materials":[120],"utilized":[122],"label":[124],"boundaries,":[126],"reconstructed":[127],"vision-based":[130],"method.":[131],"Results":[132],"show":[133],"89%":[134],"80%":[136],"agreement":[137],"between":[138],"volumes":[144],"materials,":[146],"respectively.":[147]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}