{"id":"https://openalex.org/W4304080535","doi":"https://doi.org/10.1145/3503161.3548097","title":"Adaptive Hierarchical Pooling for Weakly-supervised Sound Event Detection","display_name":"Adaptive Hierarchical Pooling for Weakly-supervised Sound Event Detection","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304080535","doi":"https://doi.org/10.1145/3503161.3548097"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548097","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548097","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on 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/A5008699574","display_name":"Lijian Gao","orcid":"https://orcid.org/0000-0002-6458-0660"},"institutions":[{"id":"https://openalex.org/I115592961","display_name":"Jiangsu University","ror":"https://ror.org/03jc41j30","country_code":"CN","type":"education","lineage":["https://openalex.org/I115592961"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lijian Gao","raw_affiliation_strings":["Jiangsu University, Zhenjiang, China"],"affiliations":[{"raw_affiliation_string":"Jiangsu University, Zhenjiang, China","institution_ids":["https://openalex.org/I115592961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055387407","display_name":"Ling Zhou","orcid":"https://orcid.org/0009-0004-1935-7808"},"institutions":[{"id":"https://openalex.org/I115592961","display_name":"Jiangsu University","ror":"https://ror.org/03jc41j30","country_code":"CN","type":"education","lineage":["https://openalex.org/I115592961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ling Zhou","raw_affiliation_strings":["Jiangsu University, Zhenjiang, China"],"affiliations":[{"raw_affiliation_string":"Jiangsu University, Zhenjiang, China","institution_ids":["https://openalex.org/I115592961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068470372","display_name":"Qirong Mao","orcid":"https://orcid.org/0000-0002-0616-4431"},"institutions":[{"id":"https://openalex.org/I115592961","display_name":"Jiangsu University","ror":"https://ror.org/03jc41j30","country_code":"CN","type":"education","lineage":["https://openalex.org/I115592961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qirong Mao","raw_affiliation_strings":["Jiangsu University, Zhenjiang, China"],"affiliations":[{"raw_affiliation_string":"Jiangsu University, Zhenjiang, China","institution_ids":["https://openalex.org/I115592961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112047383","display_name":"Ming Dong","orcid":"https://orcid.org/0000-0003-4197-7267"},"institutions":[{"id":"https://openalex.org/I185443292","display_name":"Wayne State University","ror":"https://ror.org/01070mq45","country_code":"US","type":"education","lineage":["https://openalex.org/I185443292"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ming Dong","raw_affiliation_strings":["Wayne State University, Detroit, MI, USA"],"affiliations":[{"raw_affiliation_string":"Wayne State University, Detroit, MI, USA","institution_ids":["https://openalex.org/I185443292"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5008699574"],"corresponding_institution_ids":["https://openalex.org/I115592961"],"apc_list":null,"apc_paid":null,"fwci":0.6129,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.66034755,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1779","last_page":"1787"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9986000061035156,"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":0.9896000027656555,"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/pooling","display_name":"Pooling","score":0.9022636413574219},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.773032546043396},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7729797959327698},{"id":"https://openalex.org/keywords/generality","display_name":"Generality","score":0.6819737553596497},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6705591678619385},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5945717096328735},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.47681304812431335},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4331502616405487},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42029333114624023}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.9022636413574219},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.773032546043396},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7729797959327698},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.6819737553596497},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6705591678619385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5945717096328735},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.47681304812431335},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4331502616405487},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42029333114624023},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"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:10.1145/3503161.3548097","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548097","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2263590167","display_name":null,"funder_award_id":"U1836220,62176106","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2408239454","https://openalex.org/W2593116425","https://openalex.org/W2799258971","https://openalex.org/W2883135409","https://openalex.org/W2932805122","https://openalex.org/W2963610932","https://openalex.org/W2964891022","https://openalex.org/W2965036688","https://openalex.org/W2966527417","https://openalex.org/W2981942095","https://openalex.org/W2995348821","https://openalex.org/W3006275583","https://openalex.org/W3015295955","https://openalex.org/W3015387077","https://openalex.org/W3015594652","https://openalex.org/W3015792128","https://openalex.org/W3017521796","https://openalex.org/W3049446265","https://openalex.org/W3123416659","https://openalex.org/W3124216180","https://openalex.org/W3125993195","https://openalex.org/W3143835353","https://openalex.org/W3160845765","https://openalex.org/W3162400960","https://openalex.org/W3178592608","https://openalex.org/W3182910640","https://openalex.org/W3197827948","https://openalex.org/W3200870442","https://openalex.org/W6600753396"],"related_works":["https://openalex.org/W2045049461","https://openalex.org/W1978893398","https://openalex.org/W2201908702","https://openalex.org/W4381094582","https://openalex.org/W2369625323","https://openalex.org/W2364579609","https://openalex.org/W1977906818","https://openalex.org/W1522139108","https://openalex.org/W4323323165","https://openalex.org/W2745033168"],"abstract_inverted_index":{"In":[0,54],"Weakly-supervised":[1],"Sound":[2],"Event":[3],"Detection":[4],"(WSED),":[5],"the":[6,13,23,35,47,50,68,108,115],"ground":[7],"truth":[8],"of":[9,17,49,70,117],"training":[10],"data":[11],"contains":[12],"presence":[14],"or":[15],"absence":[16],"each":[18],"sound":[19],"event":[20],"only":[21],"at":[22],"clip-level":[24],"(i.e.,":[25],"no":[26],"frame-level":[27],"annotations).":[28],"Recently,":[29],"WSED":[30,131],"has":[31,121],"been":[32],"formulated":[33],"under":[34],"multi-instance":[36],"learning":[37],"framework,":[38],"and":[39,76,88,112],"a":[40,84],"critical":[41],"component":[42],"within":[43],"this":[44,55],"formulation":[45],"is":[46],"design":[48],"temporal":[51],"pooling":[52,62,72,79,92,110],"function.":[53],"paper,":[56],"we":[57],"propose":[58],"an":[59],"adaptive":[60],"hierarchical":[61,86],"(HiPool)":[63],"for":[64],"WSED,":[65],"which":[66],"combines":[67],"advantages":[69],"max":[71],"in":[73,80],"audio":[74,81],"tagging":[75],"weighted":[77],"average":[78],"localization":[82],"through":[83,94],"novel":[85],"structure":[87],"learns":[89],"event-wise":[90],"optimal":[91],"functions":[93],"continuous":[95],"relaxation-based":[96],"joint":[97],"optimization.":[98],"Extensive":[99],"experiments":[100],"on":[101],"benchmark":[102],"datasets":[103],"show":[104],"that":[105],"HiPool":[106,119],"outperforms":[107],"current":[109],"methods":[111],"greatly":[113],"improves":[114],"performance":[116],"WSED.":[118],"also":[120],"great":[122],"generality":[123],"-":[124],"ready":[125],"to":[126],"be":[127],"plugged":[128],"into":[129],"any":[130],"models.":[132]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}