{"id":"https://openalex.org/W4239639716","doi":"https://doi.org/10.1145/3264869","title":"Proceedings of the 2018 Workshop on Audio-Visual Scene Understanding for Immersive Multimedia","display_name":"Proceedings of the 2018 Workshop on Audio-Visual Scene Understanding for Immersive Multimedia","publication_year":2018,"publication_date":"2018-10-17","ids":{"openalex":"https://openalex.org/W4239639716","doi":"https://doi.org/10.1145/3264869"},"language":"en","primary_location":{"id":"doi:10.1145/3264869","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3264869","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"proceedings"},"type":"paratext","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":true,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.996399998664856,"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":0.996399998664856,"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":0.9853000044822693,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9729999899864197,"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/multimedia","display_name":"Multimedia","score":0.7384182810783386},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.7069790959358215},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7065888047218323},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4966936707496643},{"id":"https://openalex.org/keywords/presentation","display_name":"Presentation (obstetrics)","score":0.4696834683418274},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.43113577365875244},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.34532517194747925},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.10668307542800903},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07276540994644165}],"concepts":[{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.7384182810783386},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7069790959358215},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7065888047218323},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4966936707496643},{"id":"https://openalex.org/C2777601897","wikidata":"https://www.wikidata.org/wiki/Q3409113","display_name":"Presentation (obstetrics)","level":2,"score":0.4696834683418274},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.43113577365875244},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.34532517194747925},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.10668307542800903},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07276540994644165},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3264869","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3264869","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"proceedings"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2495546752","https://openalex.org/W2011311868","https://openalex.org/W2289868279","https://openalex.org/W2970176078","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W4315836293","https://openalex.org/W4243888788","https://openalex.org/W2157165686","https://openalex.org/W1975359510"],"abstract_inverted_index":{"It":[0],"is":[1,26,127],"our":[2,36],"great":[3],"pleasure":[4],"to":[5,8,74,87,91,105,116],"welcome":[6],"you":[7],"the":[9,27,72,108,151,170,195,201],"2018":[10],"ACM":[11],"Multimedia":[12,20,141],"Workshop":[13],"on":[14,65],"Audio-Visual":[15,137],"Scene":[16],"Understanding":[17],"for":[18,51,135,140],"Immersive":[19],"-":[21],"AVSU":[22],"2018.":[23,182],"Audio-visual":[24],"data":[25],"most":[28],"familiar":[29],"format":[30],"of":[31,111,197],"multimedia":[32,80,123],"information":[33],"acquired":[34],"in":[35,47,68,78,94,99,121,150,153,177,180,200],"daily":[37],"life,":[38],"but":[39],"audio":[40,100],"and":[41,82,101,104,143,161,166,186],"video":[42],"processing":[43,115],"have":[44],"been":[45],"researched":[46,98],"separate":[48],"research":[49,67],"areas":[50],"long":[52],"time":[53],"ignoring":[54],"their":[55],"synergy":[56],"when":[57],"they":[58],"work":[59],"together.":[60],"Integrated":[61],"audio-visual":[62,113],"processing,":[63],"building":[64],"leading":[66],"each":[69],"domain,":[70],"has":[71],"potential":[73,110],"contribute":[75],"significant":[76],"advances":[77],"immersive":[79],"production":[81],"reproduction.":[83],"This":[84,125],"workshop":[85,126,147,174],"aims":[86],"provide":[88],"a":[89,118],"forum":[90],"exchange":[92],"ideas":[93],"scene":[95],"understanding":[96],"techniques":[97],"visual":[102],"communities,":[103],"ultimately":[106],"unlock":[107],"creative":[109],"joint":[112],"signal":[114],"deliver":[117],"step":[119],"change":[120],"various":[122],"applications.":[124],"following":[128],"two":[129],"successful":[130],"UK-Korea":[131],"Focal":[132],"Point":[133],"Workshops":[134],"Deep":[136],"Representation":[138],"Learning":[139],"Perception":[142],"Reproduction.":[144],"The":[145,172],"first":[146],"was":[148,175],"held":[149,176],"UK":[152],"conjunction":[154],"with":[155],"CVMP":[156],"2017.":[157],"3":[158],"demo":[159],"systems":[160],"4":[162],"talks":[163,188],"were":[164,189],"presented,":[165],"40":[167],"people":[168,184],"attended":[169],"workshop.":[171],"second":[173],"South":[178],"Korea":[179],"early":[181],"60":[183],"attended,":[185],"7":[187],"given":[190],"by":[191],"invited":[192],"speakers":[193],"including":[194],"CTO":[196],"G'Audio":[198],"Lab":[199],"USA.":[202]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}