{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T15:32:04Z","timestamp":1774539124764,"version":"3.50.1"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"WAVES Research Group, Flemish Government"},{"name":"Onderzoeksprogramma Artificiële Intelligentie (AI) Vlaanderen"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/lsp.2023.3319233","type":"journal-article","created":{"date-parts":[[2023,9,26]],"date-time":"2023-09-26T18:00:42Z","timestamp":1695751242000},"page":"1382-1386","source":"Crossref","is-referenced-by-count":11,"title":["Audio Event-Relational Graph Representation Learning for Acoustic Scene Classification"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8469-5740","authenticated-orcid":false,"given":"Yuanbo","family":"Hou","sequence":"first","affiliation":[{"name":"WAVES Research Group, Ghent University, Ghent, Belgium"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2339-5685","authenticated-orcid":false,"given":"Siyang","family":"Song","sequence":"additional","affiliation":[{"name":"School of Computing and Mathematical Science, University of Leicester, Leicester, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3185-3578","authenticated-orcid":false,"given":"Chuang","family":"Yu","sequence":"additional","affiliation":[{"name":"UCL Interaction Centre, University College London, London, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8393-5703","authenticated-orcid":false,"given":"Wenwu","family":"Wang","sequence":"additional","affiliation":[{"name":"Centre for Vision, Speech, and Signal Processing, University of Surrey, Guildford, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7756-7238","authenticated-orcid":false,"given":"Dick","family":"Botteldooren","sequence":"additional","affiliation":[{"name":"WAVES Research Group, Ghent University, Ghent, Belgium"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2326181"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3233\/JIFS-224285"},{"key":"ref12","first-page":"45","article-title":"Audio-visual scene classification: Analysis of DCASE 2021 challenge submissions","author":"wang","year":"0","journal-title":"Proc Detection Classication Acoustic Scenes Events"},{"key":"ref34","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref15","first-page":"39","article-title":"Attention-based convolutional neural networks for acoustic scene classification","author":"ren","year":"0","journal-title":"Proc Detection Classification Acoust Scenes Events Workshop"},{"key":"ref37","first-page":"9","article-title":"A multi-device dataset for urban acoustic scene classification","author":"mesaros","year":"0","journal-title":"Proc Detection Classification Acoustic Scenes Events Workshop"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3390\/app13127122"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746402"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref30","first-page":"1","article-title":"Gated graph sequence neural networks","author":"li","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP55362.2022.9949447"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1214\/19-AOS1875"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2778423"},{"key":"ref32","first-page":"7705","article-title":"Understanding batch normalization","author":"bjorck","year":"0","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref2","first-page":"1","article-title":"Automatic recognition of urban sound sources","author":"defr\u00e9ville","year":"0","journal-title":"Proc Audio Eng Soc Conv 120"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-63450-0"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW.2019.00074"},{"key":"ref39","first-page":"1","article-title":"Decoupled weight decay regularization","author":"ilya","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICOSC.2019.8665547"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053702"},{"key":"ref19","first-page":"78","article-title":"Polyphonic audio tagging with sequentially labelled data using crnn with learnable gated linear units","author":"hou","year":"0","journal-title":"Proc Detection Classification Acoustic Scenes Events Workshop"},{"key":"ref18","article-title":"Instance-level loss based multiple-instance learning framework for acoustic scene classification","author":"choi","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892893"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2020EDP7036"},{"key":"ref26","article-title":"Learning graph representation of person-specific cognitive processes from audio-visual behaviours for automatic personality recognition","author":"song","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.landurbplan.2015.08.013"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3040"},{"key":"ref42","first-page":"34","article-title":"Acoustic scene classification using a convolutional neural network ensemble and nearest neighbor filters","author":"nguyen","year":"0","journal-title":"Proc Detection Classification Acoust Scenes Events Workshop"},{"key":"ref41","first-page":"776","article-title":"AudioSet: An ontology and human-labeled dataset for audio events","author":"gemmeke","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2169"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2023.3260282"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3234512"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/173"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3264856.3264857"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2019.03.016"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3390\/su15043528"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2023.109489"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2428998"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2015.7336899"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1806"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/97\/10036333\/10264066.pdf?arnumber=10264066","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,30]],"date-time":"2023-10-30T19:47:19Z","timestamp":1698695239000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10264066\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/lsp.2023.3319233","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}