{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:58:04Z","timestamp":1776884284977,"version":"3.51.2"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,9,17]],"date-time":"2023-09-17T00:00:00Z","timestamp":1694908800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,17]],"date-time":"2023-09-17T00:00:00Z","timestamp":1694908800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,9,17]]},"DOI":"10.1109\/mlsp55844.2023.10285893","type":"proceedings-article","created":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T17:55:41Z","timestamp":1698083741000},"page":"1-6","source":"Crossref","is-referenced-by-count":6,"title":["Underwater Acoustic Signal Classification using Hierarchical Audio Transformer with Noisy Input"],"prefix":"10.1109","author":[{"given":"Quoc Thinh","family":"Vo","sequence":"first","affiliation":[{"name":"Drexel University,Department of Electrical and Computer Engineering,Philadelphia,PA,USA"}]},{"given":"David K.","family":"Han","sequence":"additional","affiliation":[{"name":"Drexel University,Department of Electrical and Computer Engineering,Philadelphia,PA,USA"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Efficient training of audio transformers with patchout","author":"koutini","year":"2021","journal-title":"arXiv preprint arXiv 2110 07058"},{"key":"ref12","article-title":"Contrastive audio-visual masked autoencoder","author":"gong","year":"2022","journal-title":"In The Eleventh International Conference on Learning Representations"},{"key":"ref15","first-page":"3302","article-title":"Htsat: A hierarchical token-semantic audio transformer for sound classification and detection","author":"chen","year":"2022","journal-title":"ICASSP 2022-2022 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2021.04.024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01073"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2962005"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2016.06.008"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1286"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21315"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2020.3044397"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3390\/s20185429"},{"key":"ref24","article-title":"mixup: Beyond empirical risk minimization","author":"zhang","year":"2017","journal-title":"arXiv preprint arXiv 1710 09412"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1118\/1.3213517"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3390\/s18124318"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0266425"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICET51757.2021.9451099"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2018.2886368"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref9","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICALIP.2010.5685063"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2012.65"},{"key":"ref6","first-page":"27","article-title":"Libsvm: a library for support vector machines","volume":"2","author":"chih-chung","year":"2011","journal-title":"ACM Transactions on Intelligent Systems and Technology"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/72.991427"}],"event":{"name":"2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing (MLSP)","location":"Rome, Italy","start":{"date-parts":[[2023,9,17]]},"end":{"date-parts":[[2023,9,20]]}},"container-title":["2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing (MLSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10285838\/10285858\/10285893.pdf?arnumber=10285893","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T19:03:30Z","timestamp":1699902210000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10285893\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,17]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/mlsp55844.2023.10285893","relation":{},"subject":[],"published":{"date-parts":[[2023,9,17]]}}}