{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T00:12:41Z","timestamp":1789603961903,"version":"build-2803163510"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2018,4,1]],"date-time":"2018-04-01T00:00:00Z","timestamp":1522540800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2018,4,1]],"date-time":"2018-04-01T00:00:00Z","timestamp":1522540800000},"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":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8461392","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T18:24:48Z","timestamp":1537554288000},"page":"316-320","source":"Crossref","is-referenced-by-count":51,"title":["Audio Set Classification with Attention Model: A Probabilistic Perspective"],"prefix":"10.1109","author":[{"given":"Qiuqiang","family":"Kong","sequence":"first","affiliation":[{"name":"Center for Vision, Speech and Signal Processing, University of Surrey, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Xu","sequence":"additional","affiliation":[{"name":"Center for Vision, Speech and Signal Processing, University of Surrey, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenwu","family":"Wang","sequence":"additional","affiliation":[{"name":"Center for Vision, Speech and Signal Processing, University of Surrey, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mark D.","family":"Plumbley","sequence":"additional","affiliation":[{"name":"Center for Vision, Speech and Signal Processing, University of Surrey, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","author":"xu","year":"2003","journal-title":"Statistical Learning in Multiple Instance Problem"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2013.06.003"},{"key":"ref12","author":"choi","year":"2016","journal-title":"Automatic tagging using deep convolutional neural networks"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964310"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952234"},{"key":"ref15","first-page":"16","article-title":"A course in probability theory","author":"chung","year":"2001","journal-title":"Academic Press"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref17","first-page":"807","article-title":"Rectified linear units improve restricted boltzmann machines","author":"nair","year":"2010","journal-title":"Proceedings of the 27th International Conference on Machine Learning"},{"key":"ref18","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","author":"srivastava","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2690563"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966291"},{"key":"ref6","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":"ref5","first-page":"776","article-title":"Audio Set: An ontology and human-labeled dataset for audio events","author":"gemmeke","year":"2017","journal-title":"ICASSP"},{"key":"ref8","first-page":"570","article-title":"A framework for multiple-instance learning","author":"maron","year":"1998","journal-title":"Advances in neural information processing systems"},{"key":"ref7","author":"xu","year":"2017","journal-title":"Large-scale weakly supervised audio classification using gated convolutional neural network"},{"key":"ref2","article-title":"DCASE 2017 challenge setup: Tasks, datasets and baseline system","author":"mesaros","year":"0","journal-title":"Proc DCAS Workshop"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2016.7760424"},{"key":"ref9","first-page":"570","volume":"25","author":"foulds","year":"2010","journal-title":"A Review of Multi-instance Learning Assumptions"}],"event":{"name":"ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Calgary, AB, Canada","start":{"date-parts":[[2018,4,15]]},"end":{"date-parts":[[2018,4,20]]}},"container-title":["2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8450881\/8461260\/08461392.pdf?arnumber=8461392","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,4]],"date-time":"2025-08-04T18:37:41Z","timestamp":1754332661000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8461392\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8461392","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}