{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T18:19:43Z","timestamp":1775067583982,"version":"3.50.1"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"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":[[2021,1,10]]},"DOI":"10.1109\/icpr48806.2021.9413035","type":"proceedings-article","created":{"date-parts":[[2021,5,5]],"date-time":"2021-05-05T22:15:54Z","timestamp":1620252954000},"page":"4933-4940","source":"Crossref","is-referenced-by-count":66,"title":["ESResNet: Environmental Sound Classification Based on Visual Domain Models"],"prefix":"10.1109","author":[{"given":"Andrey","family":"Guzhov","sequence":"first","affiliation":[]},{"given":"Federico","family":"Raue","sequence":"additional","affiliation":[]},{"given":"Jorn","family":"Hees","sequence":"additional","affiliation":[]},{"given":"Andreas","family":"Dengel","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"Accurate, large minibatch sgd: Training imagenet in 1 hour","author":"goyal","year":"2017","journal-title":"arXiv preprint arXiv 1706 02677"},{"key":"ref38","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv preprint arXiv 1412 6980"},{"key":"ref33","article-title":"Spectrum and spectral density estimation by the discrete fourier transform (dft), including a comprehensive list of window functions and some new flat-top windows","author":"heinzel","year":"2002","journal-title":"Max-Planck-Institut für Gravitationsphysik Tech Rep"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1978.10837"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1090\/S0025-5718-1965-0178586-1","article-title":"An algorithm for the machine calculation of complex fourier series","volume":"19","author":"cooley","year":"1965","journal-title":"Mathematics of Computation"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref37","author":"mcfee","year":"2020","journal-title":"librosa\/librosa 0 7 2"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502245"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref34","article-title":"Siamese neural networks for one-shot image recognition","volume":"2","author":"koch","year":"2015","journal-title":"ICML Deep Learning Workshop"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2015.7324337"},{"key":"ref40","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1121\/1.1901999"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2657381"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1977.1162950"},{"key":"ref14","article-title":"Mel frequency cepstral coefficients for music modeling","author":"logan","year":"2000","journal-title":"Int Symp Music Information Retrieval (ISMIR)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2017.08.250"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.66.026702"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1993.319457"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2017.8081521"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-69900-4_40"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref27","article-title":"Learning discriminative and robust time-frequency representations for environmental sound classification","author":"wang","year":"2019","journal-title":"arXiv preprint arXiv 1912 06808"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref6","author":"tokozume","year":"2017","journal-title":"Learning from between-class examples for deep sound recognition"},{"key":"ref29","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952651"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2019.06.040"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00767-6_49"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cities.2005.05.003"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-831"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2911996.2912043"},{"key":"ref20","article-title":"An efficient implementation of the patterson- holdsworth auditory filter bank","volume":"35","author":"slaney","year":"1993","journal-title":"Apple Computer Perception Group Tech Rep"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2939495"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-03335-4_31"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3390\/s19071733"},{"key":"ref41","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","volume":"12","author":"pedregosa","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1121\/1.1919362"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/1178723.1178727"},{"key":"ref25","first-page":"113","article-title":"Music type classification by spectral contrast feature","volume":"1","author":"jiang","year":"0","journal-title":"Proceedings IEEE International Conference on Multimedia and Expo"}],"event":{"name":"2020 25th International Conference on Pattern Recognition (ICPR)","location":"Milan, Italy","start":{"date-parts":[[2021,1,10]]},"end":{"date-parts":[[2021,1,15]]}},"container-title":["2020 25th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9411940\/9411911\/09413035.pdf?arnumber=9413035","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T11:40:50Z","timestamp":1652182850000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413035\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,10]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icpr48806.2021.9413035","relation":{},"subject":[],"published":{"date-parts":[[2021,1,10]]}}}