{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T16:43:35Z","timestamp":1761324215815},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8682376","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T20:01:56Z","timestamp":1555531316000},"page":"755-759","source":"Crossref","is-referenced-by-count":13,"title":["A Region Based Attention Method for Weakly Supervised Sound Event Detection and Classification"],"prefix":"10.1109","author":[{"given":"Jie","family":"Yan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wu","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li-Rong","family":"Dai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ian","family":"McLoughlin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Very deep convolutional networks for large-scale image recognition","year":"2014","author":"simonyan","key":"ref10"},{"article-title":"Rethinking the inception architecture for computer vision","year":"2015","author":"szegedy","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"article-title":"Language modeling with gated convolutional networks","year":"2016","author":"dauphin","key":"ref13"},{"key":"ref14","first-page":"807","article-title":"Rectified linear units improve restricted boltzmann machines","author":"nair","year":"2010","journal-title":"ICML"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"article-title":"Squeeze-and-excitation networks","year":"2017","author":"hu","key":"ref16"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"kingma","key":"ref17"},{"key":"ref18","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":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.5626\/JCSE.2012.6.1.40"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2871183"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref5","article-title":"DCASE 2017 challenge setup: Tasks, datasets and baseline system","author":"mesaros","year":"2017","journal-title":"D-CASE 2017-Workshop on Detection and Classification of Acoustic Scenes and Events"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"3083","DOI":"10.21437\/Interspeech.2017-486","article-title":"Attention and localization based on a deep convolutional recurrent model for weakly supervised audio tagging","author":"xu","year":"2017","journal-title":"InterSpeech"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462006"},{"key":"ref2","first-page":"1360","article-title":"Exploring audio semantic concepts for event-based video retrieval","author":"wang","year":"2014","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2007.4425280"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461975"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2019,5,12]]},"location":"Brighton, United Kingdom","end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08682376.pdf?arnumber=8682376","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:14:20Z","timestamp":1657854860000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8682376\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8682376","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}