{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T06:04:47Z","timestamp":1743573887288},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414357","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T15:53:45Z","timestamp":1620921225000},"page":"351-355","source":"Crossref","is-referenced-by-count":6,"title":["A Global-Local Attention Framework for Weakly Labelled Audio Tagging"],"prefix":"10.1109","author":[{"given":"Helin","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuexian","family":"Zou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenwu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053150"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2989575"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.08.026"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298668"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2930913"},{"key":"ref16","article-title":"Multi-level attention model for weakly supervised audio classification","author":"yu","year":"2018","journal-title":"Workshop on Detection and Classification of Acoustic Scenes and Events"},{"key":"ref17","first-page":"3376","article-title":"Attention-based deep multiple instance learning","author":"ilse","year":"2018","journal-title":"International Conference on Machine Learning (ICML) International Machine Learning Society (IMLS)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1219"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref4","article-title":"Large-scale weakly labeled semi-supervised sound event detection in domestic environments","author":"serizel","year":"2018","journal-title":"Workshop on Detection and Classification of Acoustic Scenes and Events"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2428998"},{"key":"ref6","first-page":"776","article-title":"Audio set: An ontology and human-labeled dataset for audio events","author":"gemmeke","year":"2017","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.33682\/006b-jx26"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1120"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2013.06.003"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2013.6701819"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682847"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-63450-0"},{"key":"ref20","first-page":"805","article-title":"Automatic tagging using deep convolutional neural networks","author":"choi","year":"2016","journal-title":"Proceedings of the 17th International Society for Music Information Retrieval Conference (ISMIR)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461975"},{"key":"ref24","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2731"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053427"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414357.pdf?arnumber=9414357","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T11:41:10Z","timestamp":1652182870000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414357\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414357","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}