{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T16:33:54Z","timestamp":1784392434747,"version":"3.55.0"},"reference-count":33,"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.2019.8682847","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T20:01:56Z","timestamp":1555531316000},"page":"31-35","source":"Crossref","is-referenced-by-count":109,"title":["A Comparison of Five Multiple Instance Learning Pooling Functions for Sound Event Detection with Weak Labeling"],"prefix":"10.1109","author":[{"given":"Yun","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juncheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Florian","family":"Metze","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Polyphonic sound event detection with weak labeling","author":"wang","year":"2018","journal-title":"PhD thesis"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2858559"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/463"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3206025.3206067"},{"key":"ref10","article-title":"DCASE 2017 challenge setup: Tasks, datasets and baseline system","author":"mesaros","year":"2017","journal-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events 2′17 Workshop (DCASE2′17)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2013.06.003"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952264"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964310"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-990"},{"key":"ref15","first-page":"570","article-title":"A framework for multiple-instance learning","author":"maron","year":"1998","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref16","first-page":"1417","article-title":"Multiple instance boosting for object detection","author":"zhang","year":"2006","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref17","article-title":"Simultaneous learning and alignment: Multi-instance and multi-pose learning","author":"babenko","year":"2008","journal-title":"Workshop on Faces in 'Real-Life' Images Detection Alignment and Recognition"},{"key":"ref18","article-title":"A closer look at weak label learning for audio events","author":"shah","year":"2018","journal-title":"ArXiv e-prints"},{"key":"ref19","article-title":"Deep learning for DCASE2017 challenge","author":"dang","year":"2017","journal-title":"Tech Rep DCASE2016 Challenge"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462200"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472176"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-015-0069-2"},{"key":"ref6","first-page":"6","article-title":"Sound event detection in multichannel audio using spatial and harmonic features","author":"adavanne","year":"2016","journal-title":"Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462168"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472917"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"1291","DOI":"10.1109\/TASLP.2017.2690575","article-title":"Convolutional recurrent neural networks for polyphonic sound event detection","volume":"25","author":"\u00e7ak?r","year":"2017","journal-title":"IEEE\/ACM Transactions on Audio Speech and Language Processing"},{"key":"ref7","first-page":"35","article-title":"Bidirectional LSTM-HMM hybrid system for polyphonic sound event detection","author":"hayashi","year":"2016","journal-title":"Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE)"},{"key":"ref2","article-title":"DCASE 2016 sound event detection system based on convolutional neural network","author":"gorin","year":"2016","journal-title":"Tech Rep DCASE2016 Challenge"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2014.80"},{"key":"ref20","article-title":"DCASE 2017 submission: Multiple instance learning for sound event detection","author":"salamon","year":"2017","journal-title":"Tech Rep DCASE2016 Challenge"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461392"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461975"},{"key":"ref24","article-title":"Automatic differentiation in PyTorch","author":"paszke","year":"2017","journal-title":"NIPS Workshop"},{"key":"ref23","article-title":"Multi-level attention model for weakly supervised audio classification","author":"yu","year":"2018","journal-title":"ArXiv e-prints"},{"key":"ref26","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3390\/app6060162"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Brighton, United Kingdom","start":{"date-parts":[[2019,5,12]]},"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\/08682847.pdf?arnumber=8682847","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:21:44Z","timestamp":1657855304000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8682847\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8682847","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}