{"id":"https://openalex.org/W3200870442","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533332","title":"Power Pooling: An Adaptive Pooling Function for Weakly Labelled Sound Event Detection","display_name":"Power Pooling: An Adaptive Pooling Function for Weakly Labelled Sound Event Detection","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3200870442","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533332","mag":"3200870442"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9533332","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533332","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","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/A5103199045","display_name":"Yuzhuo Liu","orcid":"https://orcid.org/0000-0002-8679-8759"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuzhuo Liu","raw_affiliation_strings":["Key Laboratory of Speech Acoustics and Content Understanding Institute of Acoustics, Chinese Academy of Sciences, China","University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Speech Acoustics and Content Understanding Institute of Acoustics, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048946763","display_name":"Hangting Chen","orcid":"https://orcid.org/0000-0002-4085-4364"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hangting Chen","raw_affiliation_strings":["Key Laboratory of Speech Acoustics and Content Understanding Institute of Acoustics, Chinese Academy of Sciences, China","University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Speech Acoustics and Content Understanding Institute of Acoustics, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100618681","display_name":"Yun Wang","orcid":"https://orcid.org/0000-0003-3117-8955"},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yun Wang","raw_affiliation_strings":["Facebook AI, Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I4210114444","https://openalex.org/I4210099336"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036446253","display_name":"Pengyuan Zhang","orcid":"https://orcid.org/0000-0001-6838-5160"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengyuan Zhang","raw_affiliation_strings":["Key Laboratory of Speech Acoustics and Content Understanding Institute of Acoustics, Chinese Academy of Sciences, China","University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Speech Acoustics and Content Understanding Institute of Acoustics, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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":0.996999979019165,"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":0.9787999987602234,"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":0.9299976229667664},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.9247419834136963},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7230607271194458},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6284579634666443},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5203944444656372},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5154184103012085},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46359556913375854},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4466373026371002},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37427911162376404},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.1764315962791443},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0774402916431427}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.9299976229667664},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.9247419834136963},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7230607271194458},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6284579634666443},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5203944444656372},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5154184103012085},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46359556913375854},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4466373026371002},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37427911162376404},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.1764315962791443},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0774402916431427},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9533332","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533332","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5835218336","display_name":"\u9c81\u68d2\u97f3\u9891\u573a\u666f\u8bc6\u522b\u6280\u672f\u7814\u7a76","funder_award_id":"62071461","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"},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"id":"https://openalex.org/F4320326972","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57"},{"id":"https://openalex.org/F4320336292","display_name":"Institute of Acoustics, Chinese Academy of Sciences","ror":"https://ror.org/00v8rqv75"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1650531274","https://openalex.org/W1844944916","https://openalex.org/W2010792435","https://openalex.org/W2341412280","https://openalex.org/W2408239454","https://openalex.org/W2526050071","https://openalex.org/W2553581788","https://openalex.org/W2592691248","https://openalex.org/W2593116425","https://openalex.org/W2654517624","https://openalex.org/W2775505379","https://openalex.org/W2799258971","https://openalex.org/W2922706775","https://openalex.org/W2953070460","https://openalex.org/W2963022469","https://openalex.org/W2963517948","https://openalex.org/W2963610932","https://openalex.org/W2963952323","https://openalex.org/W2991023920","https://openalex.org/W3017351200","https://openalex.org/W3034883497","https://openalex.org/W4294620492","https://openalex.org/W6733814495","https://openalex.org/W6747331233","https://openalex.org/W6750169387","https://openalex.org/W6960144812"],"related_works":["https://openalex.org/W3107204728","https://openalex.org/W4287591324","https://openalex.org/W4226420367","https://openalex.org/W2980176872","https://openalex.org/W2962876041","https://openalex.org/W3090555870","https://openalex.org/W3108503355","https://openalex.org/W2249953602","https://openalex.org/W3134502938","https://openalex.org/W4385572368"],"abstract_inverted_index":{"Access":[0],"to":[1,19,25,59,122,131,202],"large":[2],"corpora":[3],"with":[4,36,102],"strongly":[5],"labelled":[6],"sound":[7,34,63,103,124],"events":[8,35,104],"is":[9,68],"expensive":[10],"and":[11,30,56,90,154,170,182],"difficult":[12],"in":[13,61,143,205],"engineering":[14],"applications.":[15],"Many":[16],"researches":[17],"turn":[18],"address":[20],"the":[21,28,31,42,62,69,88,91,158,176,186,196],"problem":[22],"of":[23,33,71,93,105],"how":[24],"detect":[26],"both":[27,87,151,168],"types":[29],"timestamps":[32],"weak":[37],"labels":[38],"that":[39],"only":[40],"specify":[41],"types.":[43],"This":[44],"task":[45,67],"can":[46,85,119,136,199],"be":[47,200],"treated":[48],"as":[49],"a":[50,57,72,114,128,144],"multiple":[51],"instance":[52],"learning":[53],"(MIL)":[54],"problem,":[55],"key":[58],"it":[60,84,174],"event":[64],"detection":[65],"(SED)":[66],"design":[70],"pooling":[73,78,98,116,135,148,161,166],"function.":[74],"The":[75],"linear":[76,96,164],"softmax":[77,97,165],"function":[79,117,162],"achieves":[80],"state-of-the-art":[81],"performance":[82],"since":[83],"vary":[86],"signs":[89],"magnitudes":[92],"gradients.":[94],"However,":[95],"cannot":[99],"flexibly":[100],"deal":[101],"different":[106],"time":[107],"scales.":[108],"In":[109],"this":[110,190],"paper,":[111],"we":[112],"propose":[113],"power":[115,134,160],"which":[118],"automatically":[120],"adapt":[121],"various":[123],"events.":[125],"By":[126],"adding":[127],"trainable":[129],"parameter":[130],"each":[132],"event,":[133],"provide":[137],"more":[138],"accurate":[139],"gradients":[140],"for":[141],"frames":[142],"clip":[145],"than":[146],"other":[147,206],"functions.":[149],"On":[150],"weakly":[152],"supervised":[153],"semi-supervised":[155],"SED":[156,194],"datasets,":[157],"proposed":[159,197],"outperforms":[163],"on":[167,185,193],"coarse-grained":[169],"fine-grained":[171],"metrics.":[172],"Specifically,":[173],"improves":[175],"event-based":[177],"F1":[178],"score":[179],"by":[180],"11.4%":[181],"10.2%":[183],"relatively":[184],"two":[187],"datasets.":[188],"While":[189],"paper":[191],"focuses":[192],"applications,":[195],"method":[198],"applied":[201],"MIL":[203],"tasks":[204],"domains.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}