{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T17:46:30Z","timestamp":1776879990076,"version":"3.51.2"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447697","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"1061-1065","source":"Crossref","is-referenced-by-count":5,"title":["Max-AST: Combining Convolution, Local and Global Self-Attentions for Audio Event Classification"],"prefix":"10.1109","author":[{"given":"Tony","family":"Alex","sequence":"first","affiliation":[{"name":"University of Surrey,Surrey Institute for People-Centred AI,Guildford,UK,GU2 7XH"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sara","family":"Ahmed","sequence":"additional","affiliation":[{"name":"University of Surrey,Surrey Institute for People-Centred AI,Guildford,UK,GU2 7XH"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Armin","family":"Mustafa","sequence":"additional","affiliation":[{"name":"University of Surrey,Surrey Institute for People-Centred AI,Guildford,UK,GU2 7XH"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad","family":"Awais","sequence":"additional","affiliation":[{"name":"University of Surrey,Surrey Institute for People-Centred AI,Guildford,UK,GU2 7XH"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Philip JB","family":"Jackson","sequence":"additional","affiliation":[{"name":"University of Surrey,Surrey Institute for People-Centred AI,Guildford,UK,GU2 7XH"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref3","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746312"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096513"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00356"},{"key":"ref10","article-title":"Stand-alone self-attention in vision models","volume-title":"Advances in neural information processing systems","volume":"32","author":"Ramachandran"},{"key":"ref11","first-page":"459","article-title":"MaxViT: Multiaxis vision transformer","volume-title":"European Conference on Computer Vision","author":"Tu"},{"key":"ref12","first-page":"1597","article-title":"Simclr: A simple framework for contrastive learning of visual representations","volume-title":"Proceedings of the 37th International Conference on Machine Learning","author":"Chen"},{"key":"ref13","article-title":"Sit: Self-supervised vision transformer","author":"Atito","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096787"},{"key":"ref15","author":"Atito","year":"2022","journal-title":"Asit: Audio spectrogram vision transformer for general audio representation"},{"key":"ref16","article-title":"Masked autoencoders that listen","author":"Huang","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref18","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume-title":"International conference on machine learning","author":"Tan"},{"key":"ref19","first-page":"18367","article-title":"Improved transformer for high-resolution gans","volume-title":"Advances in neural information processing systems","volume":"34","author":"Zhao"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"ref22","first-page":"3965","article-title":"Coatnet: Marrying convolution and attention for all data sizes","volume-title":"Advances in neural information processing systems","volume":"34","author":"Dai"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref24","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","author":"Warden","year":"2018"},{"key":"ref25","author":"Tokozume","year":"2018","journal-title":"Learning from between-class examples for deep sound recognition"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref27","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-227"},{"key":"ref29","author":"Sovrasov","year":"2018","journal-title":"ptflops: a flops counting tool for neural networks in pytorch framework"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447697.pdf?arnumber=10447697","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:48:40Z","timestamp":1722574120000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447697\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447697","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}