{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T16:58:41Z","timestamp":1762102721405,"version":"3.28.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746091","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:50:34Z","timestamp":1651074634000},"page":"1036-1040","source":"Crossref","is-referenced-by-count":6,"title":["Attentive Max Feature Map and Joint Training for Acoustic Scene Classification"],"prefix":"10.1109","author":[{"given":"Hye-jin","family":"Shim","sequence":"first","affiliation":[{"name":"University of Seoul,School of Computer Science"}]},{"given":"Jee-weon","family":"Jung","sequence":"additional","affiliation":[{"name":"Naver Corporation"}]},{"given":"Ju-ho","family":"Kim","sequence":"additional","affiliation":[{"name":"University of Seoul,School of Computer Science"}]},{"given":"Ha-Jin","family":"Yu","sequence":"additional","affiliation":[{"name":"University of Seoul,School of Computer Science"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Clova submission for the DCASE 2021 challenge: Acoustic scene classification using light architectures and device augmentation","author":"heo","year":"0","journal-title":"Tech Rep DCASE2016 Challenge"},{"key":"ref32","first-page":"794","article-title":"Gradnorm: Gradient normalization for adaptive loss balancing in deep multitask networks","author":"chen","year":"2018","journal-title":"Proc ICML"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00195"},{"key":"ref30","article-title":"Sound event classification using ontology-based neural networks","author":"jim\u00e9nez","year":"2018","journal-title":"Proceedings of the Annual Conference on Neural Information Processing Systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683288"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952265"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1989"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3021711"},{"key":"ref16","article-title":"Audio tagging and deep architectures for acoustic scene classification: Uos submission for the dcase 2020 challenge","author":"shim","year":"0","journal-title":"Tech Rep DCASE2020 Challenge"},{"key":"ref17","article-title":"Acoustic scene classification using audio tagging","author":"jung","year":"2020","journal-title":"Proc INTERSPEECH"},{"key":"ref18","article-title":"Dcase 2018 challenge surrey cross-task convolutional neural network baseline","author":"kong","year":"0","journal-title":"DCASE 2018 workshop"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414406"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01267"},{"key":"ref4","article-title":"Designing acoustic scene classification models with cnn variants","author":"suh","year":"0","journal-title":"Tech Rep DCASE2020 Challenge"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00391"},{"key":"ref3","article-title":"Acoustic scene classification in dcase 2020 challenge: generalization across devices and low complexity solutions","author":"heittola","year":"0","journal-title":"DCASE 2020 Workshop"},{"key":"ref6","article-title":"Acoustic scene classification using deep residual networks with focal loss and mild domain adaptation","author":"gao","year":"0","journal-title":"Tech Rep DCASE2020 Challenge"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1023\/A:1007379606734","article-title":"Multitask learning","volume":"28","author":"caruana","year":"1997","journal-title":"Machine Learning"},{"key":"ref5","article-title":"Device-robust acoustic scene classification based on two-stage categorization and data augmentation","author":"hu","year":"0","journal-title":"Tech Rep DCASE2020 Challenge"},{"key":"ref8","article-title":"Cp-jku submissions to dcase’20: Low-complexity cross-device acoustic scene classification with rf-regularized cnns","author":"koutini","year":"0","journal-title":"Tech Rep DCASE2020 Challenge"},{"key":"ref7","article-title":"Acoustic scene classification with residual networks and attention mechanism","author":"liu","year":"0","journal-title":"Tech Rep DCASE2020 Challenge"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.33682\/m5kp-fa97"},{"key":"ref9","article-title":"mixup: Beyond empirical risk minimization","author":"zhang","year":"2018","journal-title":"Proc ICLR"},{"key":"ref1","article-title":"A multi-device dataset for urban acoustic scene classification","author":"mesaros","year":"0","journal-title":"DCASE 2018 workshop"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683434"},{"key":"ref22","first-page":"3","article-title":"Cbam: Convolutional block attention module","author":"woo","year":"2018","journal-title":"Proc ECCV"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3040"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3390\/app11188361"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2018.2833032"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414835"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10040371"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2022,5,23]]},"location":"Singapore, Singapore","end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746091.pdf?arnumber=9746091","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T16:15:01Z","timestamp":1661184901000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746091\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746091","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}