{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T02:17:08Z","timestamp":1777083428119,"version":"3.51.4"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096532","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":5,"title":["Play It Back: Iterative Attention For Audio Recognition"],"prefix":"10.1109","author":[{"given":"Alexandros","family":"Stergiou","sequence":"first","affiliation":[{"name":"Vrije University of Brussels,Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dima","family":"Damen","sequence":"additional","affiliation":[{"name":"University of Bristol,United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3014737"},{"key":"ref35","article-title":"Polyvit: Co-training vision transformers on images, videos and audio","author":"likhosherstov","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413376"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00806"},{"key":"ref15","article-title":"Convolution augmented transformer for semi-supervised sound event detection","author":"miyazaki","year":"2020","journal-title":"DCAS"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref36","article-title":"mixup: Beyond empirical risk minimization","author":"zhang","year":"0"},{"key":"ref31","article-title":"Masked autoencoders that listen","author":"xu","year":"2022","journal-title":"NeurIPS"},{"key":"ref30","article-title":"Masked spectrogram prediction for self-supervised audio pre-training","author":"chong","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682847"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053274"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"ref2","article-title":"Auditory sensory (\"echoic\") memory dysfunction in schizophrenia","author":"strous","year":"1995","journal-title":"The American Journal of Psychiatry"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1108\/eb024707"},{"key":"ref17","article-title":"Efficient training of audio transformers with patchout","author":"koutini","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746312"},{"key":"ref19","article-title":"Learning the spectrogram temporal resolution for audio classification","author":"liu","year":"2022"},{"key":"ref18","article-title":"Attention bottlenecks for multimodal fusion","author":"nagrani","year":"2021","journal-title":"NeurIPS"},{"key":"ref24","article-title":"Maeast: Masked autoencoding audio spectrogram transformer","author":"baade","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.476"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref25","article-title":"Perceiver: General perception with iterative attention","author":"jaegle","year":"2021","journal-title":"ICML"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.185"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_4"},{"key":"ref21","article-title":"Visual concept recognition and localization via iterative introspection","author":"rosenfeld","year":"2016","journal-title":"ACCV"},{"key":"ref28","article-title":"Training data-efficient image transformers & distillation through attention","author":"touvron","year":"2021","journal-title":"ICML"},{"key":"ref27","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","author":"tan","year":"2019","journal-title":"ICML"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01531-2"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3120633"},{"key":"ref4","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"ICLRE"},{"key":"ref3","author":"radvansky","year":"2005","journal-title":"Human Memory"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref5","article-title":"Object-centric learning with slot attention","author":"locatello","year":"2020","journal-title":"NeuIPS"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096532.pdf?arnumber=10096532","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T18:57:30Z","timestamp":1700506650000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096532\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096532","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}