{"id":"https://openalex.org/W2525577390","doi":"https://doi.org/10.1145/2964284.2964292","title":"Event Localization in Music Auto-tagging","display_name":"Event Localization in Music Auto-tagging","publication_year":2016,"publication_date":"2016-09-29","ids":{"openalex":"https://openalex.org/W2525577390","doi":"https://doi.org/10.1145/2964284.2964292","mag":"2525577390"},"language":"en","primary_location":{"id":"doi:10.1145/2964284.2964292","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2964284.2964292","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM international conference on Multimedia","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/A5101719938","display_name":"Jen-Yu Liu","orcid":"https://orcid.org/0000-0003-1299-6688"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]},{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jen-Yu Liu","raw_affiliation_strings":["National Taiwan University & Academia Sinica, Taipei, Taiwan Roc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University & Academia Sinica, Taipei, Taiwan Roc","institution_ids":["https://openalex.org/I16733864","https://openalex.org/I84653119"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061291906","display_name":"Yi\u2010Hsuan Yang","orcid":"https://orcid.org/0000-0002-2724-6161"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Hsuan Yang","raw_affiliation_strings":["Academia Sinica, Taipei, Taiwan Roc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica, Taipei, Taiwan Roc","institution_ids":["https://openalex.org/I84653119"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1048","last_page":"1057"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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":0.9965000152587891,"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/T10860","display_name":"Speech and Audio Processing","score":0.9958000183105469,"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":0.8486810326576233},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.700108528137207},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6364856958389282},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5365318059921265},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.5055406093597412},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49929308891296387},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.4872945547103882},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.424361914396286},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4184364974498749},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38490742444992065},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3646310567855835}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8486810326576233},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.700108528137207},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6364856958389282},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5365318059921265},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.5055406093597412},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49929308891296387},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.4872945547103882},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.424361914396286},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4184364974498749},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38490742444992065},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3646310567855835},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2964284.2964292","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2964284.2964292","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1546771929","https://openalex.org/W1635512741","https://openalex.org/W1923697677","https://openalex.org/W1931270512","https://openalex.org/W1945608308","https://openalex.org/W1950136256","https://openalex.org/W1974788265","https://openalex.org/W1994488211","https://openalex.org/W1995562189","https://openalex.org/W2004935438","https://openalex.org/W2016053056","https://openalex.org/W2059652044","https://openalex.org/W2081631398","https://openalex.org/W2083383166","https://openalex.org/W2102605133","https://openalex.org/W2114708606","https://openalex.org/W2116373735","https://openalex.org/W2127870748","https://openalex.org/W2144499799","https://openalex.org/W2152175008","https://openalex.org/W2156303437","https://openalex.org/W2160815625","https://openalex.org/W2162124943","https://openalex.org/W2168356304","https://openalex.org/W2169375076","https://openalex.org/W2188183693","https://openalex.org/W2188492526","https://openalex.org/W2221898772","https://openalex.org/W2242773987","https://openalex.org/W2296610835","https://openalex.org/W2296724634","https://openalex.org/W2341412280","https://openalex.org/W2395291588","https://openalex.org/W2395945925","https://openalex.org/W2406196141","https://openalex.org/W2618530766","https://openalex.org/W2619993508"],"related_works":["https://openalex.org/W2931688134","https://openalex.org/W2377919138","https://openalex.org/W2378857091","https://openalex.org/W2999756192","https://openalex.org/W103652678","https://openalex.org/W4226090359","https://openalex.org/W2059697060","https://openalex.org/W936373746","https://openalex.org/W4382701072","https://openalex.org/W300569899"],"abstract_inverted_index":{"In":[0,217],"music":[1,10,33,92,111,140,181,236],"auto-tagging,":[2],"people":[3,54],"develop":[4],"models":[5],"to":[6,66,69,79,131,174,196,219],"automatically":[7],"label":[8],"a":[9,32,37,88,110,122],"clip":[11,97],"with":[12,58,75],"attributes":[13,107],"such":[14,45,187],"as":[15],"instruments,":[16],"styles":[17],"or":[18],"acoustic":[19],"properties.":[20],"Many":[21],"of":[22,28,40,72,136,170,180,186,202,213,235],"these":[23,106],"tags":[24,46,137,189],"are":[25,94],"actually":[26],"descriptors":[27],"local":[29,188],"events":[30],"in":[31,47,95,109,119,138,147,158,190,205],"clip,":[34],"rather":[35],"than":[36],"holistic":[38],"description":[39],"the":[41,52,70,80,96,148,171,177,183,200,211,214,228],"whole":[42],"clip.":[43,112],"Localizing":[44],"time":[48],"can":[49,230],"potentially":[50],"innovate":[51],"way":[53],"retrieve":[55],"and":[56,103,182,207],"interact":[57],"music,":[59,206],"but":[60,165],"little":[61],"work":[62],"has":[63],"been":[64],"done":[65],"date":[67],"due":[68],"scarcity":[71],"labeled":[73,84],"data":[74,85],"granularity":[76],"specific":[77],"enough":[78],"frame":[81],"level.":[82],"Most":[83],"for":[86,91,161,176],"training":[87,149],"learning-based":[89],"model":[90,229],"auto-tagging":[93],"level,":[98],"providing":[99],"no":[100],"cues":[101],"when":[102],"how":[104],"long":[105],"appear":[108],"To":[113],"bridge":[114],"this":[115,120],"gap,":[116],"we":[117,166,222],"propose":[118,167],"paper":[121],"convolutional":[123],"neural":[124],"network":[125],"(CNN)":[126],"architecture":[127,173],"that":[128],"is":[129,153],"able":[130],"make":[132],"accurate":[133],"frame-level":[134],"predictions":[135],"unseen":[139],"clips":[141],"by":[142,155],"using":[143],"only":[144],"clip-level":[145],"annotations":[146],"phase.":[150],"Our":[151],"approach":[152],"motivated":[154],"recent":[156],"advances":[157],"computer":[159],"vision":[160],"localizing":[162],"visual":[163],"objects,":[164],"new":[168],"designs":[169],"CNN":[172],"account":[175],"temporal":[178],"information":[179],"variable":[184],"duration":[185],"time.":[191],"We":[192],"report":[193],"extensive":[194],"experiments":[195,210],"gain":[197],"insights":[198],"into":[199],"problem":[201],"event":[203],"localization":[204],"validate":[208],"through":[209],"effectiveness":[212],"proposed":[215],"approach.":[216],"addition":[218],"quantitative":[220],"evaluations,":[221],"also":[223],"present":[224],"qualitative":[225],"analyses":[226],"showing":[227],"indeed":[231],"learn":[232],"certain":[233],"characteristics":[234],"tags.":[237]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":9}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}