{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T00:17:04Z","timestamp":1730247424356,"version":"3.28.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,8]],"date-time":"2023-10-08T00:00:00Z","timestamp":1696723200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,8]],"date-time":"2023-10-08T00:00:00Z","timestamp":1696723200000},"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":[[2023,10,8]]},"DOI":"10.1109\/icip49359.2023.10222551","type":"proceedings-article","created":{"date-parts":[[2023,9,11]],"date-time":"2023-09-11T13:58:31Z","timestamp":1694440711000},"page":"2600-2604","source":"Crossref","is-referenced-by-count":0,"title":["Group Masked Model Learning for General Audio Representation"],"prefix":"10.1109","author":[{"given":"Sara","family":"Atito","sequence":"first","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammed","family":"Awais","sequence":"additional","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tony","family":"Alex","sequence":"additional","affiliation":[{"name":"University of Surrey,Surrey Institute for People-Centred AI,Guildford,UK,GU2 7XH"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Josef","family":"Kittler","sequence":"additional","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP)"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10961"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21315"},{"article-title":"GMML is all you need","year":"2022","author":"atito","key":"ref15"},{"article-title":"Xu. Masked autoencoders that listen","year":"2022","author":"hu","key":"ref14"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"article-title":"SGDR: Stochastic gradient descent with warm restarts","year":"2016","author":"loshchilov","key":"ref30"},{"article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"devlin","key":"ref11"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10126"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"article-title":"SiT: Self-supervised vision transformer","year":"2021","author":"atito","key":"ref2"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2020","author":"dosovitskiy","key":"ref1"},{"journal-title":"Theory and Applications of Digital Speech Processing","year":"2010","author":"rabiner","key":"ref17"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"article-title":"MC-SSL: Towards multi-concept self-supervised learning","year":"2021","author":"atito","key":"ref19"},{"article-title":"BEIT: Bert pre-training of image transformers","year":"2021","author":"bao","key":"ref18"},{"article-title":"Beit v2: Masked image modeling with vector-quantized visual tokenizers","year":"2022","author":"peng","key":"ref24"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.75"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"article-title":"Gaussian error linear units (GeLUs)","year":"2016","author":"hendrycks","key":"ref22"},{"article-title":"Masked spectrogram prediction for self-supervised audio pre-training","year":"2022","author":"chong","key":"ref21"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027"},{"article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","year":"2018","author":"warden","key":"ref27"},{"article-title":"Fixing weight decay regularization in Adam","year":"2017","author":"loshchilov","key":"ref29"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534474"},{"key":"ref7","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"International Conference on Machine Learning"},{"key":"ref9","first-page":"21271","article-title":"Grill. Bootstrap your own latent-a new approach to self-supervised learning","volume":"33","author":"jean-bastien","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1007\/978-3-031-16760-7_9","article-title":"SB-SSL: Slice-based self-supervised transformers for knee abnormality classification from MRI","author":"atito","year":"2022","journal-title":"Workshop on Medical Image Learning with Limited and Noisy Data"},{"key":"ref3","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"krizhevsky","year":"2012","journal-title":"NeurIPS"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413528"},{"key":"ref5","article-title":"Pre-training audio representations with self-supervision","author":"xu","year":"2017","journal-title":"IEEE\/ACM Transactions on Audio Speech and Language Processing"}],"event":{"name":"2023 IEEE International Conference on Image Processing (ICIP)","start":{"date-parts":[[2023,10,8]]},"location":"Kuala Lumpur, Malaysia","end":{"date-parts":[[2023,10,11]]}},"container-title":["2023 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10221937\/10221892\/10222551.pdf?arnumber=10222551","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T11:09:11Z","timestamp":1701256151000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10222551\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,8]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icip49359.2023.10222551","relation":{},"subject":[],"published":{"date-parts":[[2023,10,8]]}}}