{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T15:58:48Z","timestamp":1790438328481,"version":"4.1.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9413376","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"855-859","source":"Crossref","is-referenced-by-count":41,"title":["Slow-Fast Auditory Streams for Audio Recognition"],"prefix":"10.1109","author":[{"given":"Evangelos","family":"Kazakos","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arsha","family":"Nagrani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew","family":"Zisserman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dima","family":"Damen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref30","article-title":"SpecAugment","year":"0"},{"key":"ref10","article-title":"Devicerobust acoustic scene classification based on two-stage categorization and data augmentation","author":"hu","year":"2020","journal-title":"Tech Rep DCASE2020 Challenge"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2019.8902732"},{"key":"ref12","article-title":"Integrating the data augmentation scheme with various classifiers for acoustic scene modeling","author":"chen","year":"2019","journal-title":"Tech Rep DCASE2016 Challenge"},{"key":"ref13","article-title":"Acoustic scene classification with fully convolutional neural networks and I- vectors","author":"dorfer","year":"2018","journal-title":"Tech Rep DCASE2016 Challenge"},{"key":"ref14","article-title":"Acoustic scene classification using multi-scale features","author":"liping","year":"2018","journal-title":"Tech Rep DCASE2016 Challenge"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2017.8081710"},{"key":"ref16","article-title":"Comparison of time-frequency representations for environmental sound classification using convolutional neural networks","author":"huzaifah","year":"2017","journal-title":"CoRR"},{"key":"ref17","article-title":"Audiovisual slow- fast networks for video recognition","author":"xiao","year":"2020"},{"key":"ref18","article-title":"Deep audio priors emerge from harmonic convolutional networks","author":"zhang","year":"2020","journal-title":"ICLRE"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3390\/s19071733"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3389\/fncom.2019.00095"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1003412"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2657381"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref8","article-title":"Soundnet: Learning sound representations from unlabeled video","author":"aytar","year":"2016","journal-title":"NIPS"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref2","article-title":"Rescaling egocentric vision","author":"damen","year":"2020","journal-title":"CoRR"},{"key":"ref9","article-title":"Designing acoustic scene classification models with CNN variants","author":"suh","year":"2020","journal-title":"Tech Rep DCASE2020 Challenge"},{"key":"ref1","article-title":"VG- Gsound: A Large-Scale Audio-Visual Dataset","author":"chen","year":"2020","journal-title":"ICASSP"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3019"},{"key":"ref22","article-title":"Acoustic scene classification with multiple decision schemes","author":"wang","year":"2020","journal-title":"Tech Rep DCASE2020 Challenge"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2018-7"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053194"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053274"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003730"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09413376.pdf?arnumber=9413376","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:41:03Z","timestamp":1652197263000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413376\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413376","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}