{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T11:16:17Z","timestamp":1782386177702,"version":"3.54.5"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61501374"],"award-info":[{"award-number":["61501374"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62071383"],"award-info":[{"award-number":["62071383"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC-Zhejiang Joint Fund for the Integration of Industrialization and Information","doi-asserted-by":"publisher","award":["U1609204"],"award-info":[{"award-number":["U1609204"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cogn. Dev. Syst."],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1109\/tcds.2022.3160168","type":"journal-article","created":{"date-parts":[[2022,3,17]],"date-time":"2022-03-17T20:32:35Z","timestamp":1647549155000},"page":"555-565","source":"Crossref","is-referenced-by-count":13,"title":["Multimodal Urban Sound Tagging With Spatiotemporal Context"],"prefix":"10.1109","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9803-8212","authenticated-orcid":false,"given":"Jisheng","family":"Bai","sequence":"first","affiliation":[{"name":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianfeng","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6476-2501","authenticated-orcid":false,"given":"Mou","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3224204"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1093\/bmb\/ldg033"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.33682\/j5zw-2t88"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2012.07.007"},{"key":"ref5","first-page":"1","article-title":"Inception-v3 based method of LifeCLEF 2019 bird recognition","volume-title":"Proc. CLEF","volume":"2380","author":"Bai"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7177954"},{"key":"ref7","article-title":"Learning frame level attention for environmental sound classification","author":"Zhang","year":"2020","journal-title":"arXiv:2007.07241"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.33682\/8axe-9243"},{"key":"ref9","article-title":"Convolutional neural networks with transfer learning for urban sound tagging","author":"Kim","year":"2019"},{"key":"ref10","article-title":"Cross-task learning for audio tagging, sound event detection and spatial localization: DCASE 2019 baseline systems","author":"Kong","year":"2019","journal-title":"arXiv:1904.03476"},{"key":"ref11","article-title":"Incorporating auxiliary data for urban sound tagging","author":"Iqbal","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023099"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-03335-4_31"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2016.7760424"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2017438"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref18","article-title":"Surrey-CVSSP system for DCASE2017 challenge task4","author":"Xu","year":"2017"},{"key":"ref19","article-title":"Weakly-supervised classification of domestic acoustic events for indoor monitoring applications","volume-title":"Proc. IEEE Conf. Biomed. Health Informat.","author":"Vuegen"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8655(03)00147-8"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1186\/1687-4722-2013-1"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2011.6082331"},{"key":"ref24","article-title":"Large-scale weakly labeled semi-supervised sound event detection in domestic environments","author":"Serizel","year":"2018","journal-title":"arXiv:1807.10501"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2657381"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2690575"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.33682\/0avf-bm61"},{"key":"ref28","first-page":"689","article-title":"Multimodal deep learning","volume-title":"Proc. ICML","author":"Ngiam"},{"issue":"1","key":"ref29","first-page":"2949","article-title":"Multimodal learning with deep Boltzmann machines","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2016.2624705"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2738401"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2018.2819826"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2017.2721552"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2013.6553805"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.01.095"},{"key":"ref36","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Advances in Neural Information Processing Systems","author":"Simonyan","year":"2014"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2017.2685338"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s00034-019-01072-7"},{"key":"ref39","article-title":"Comparison of time\u2013frequency representations for environmental sound classification using convolutional neural networks","author":"Huzaifah","year":"2017","journal-title":"arXiv:1706.07156"},{"key":"ref40","first-page":"1","article-title":"Harmonic\/percussive separation using median filtering","volume-title":"Proc. 13th Int. Conf. Digit. Audio Effects (DAFx)","author":"Fitzgerald"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2013.2287052"},{"key":"ref42","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"Ioffe","year":"2015","journal-title":"arXiv:1502.03167"},{"key":"ref43","article-title":"Empirical evaluation of rectified activations in convolutional network","author":"Xu","year":"2015","journal-title":"arXiv:1505.00853"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2858559"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023236"},{"key":"ref46","article-title":"SONYC-UST-V2: An urban sound tagging dataset with spatiotemporal context","author":"Cartwright","year":"2020","journal-title":"arXiv:2009.05188"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1710.09412"},{"key":"ref48","article-title":"Urban sound classification using convolutional neural networks for DCASE 2020 challenge","author":"Diez","year":"2020"},{"key":"ref49","article-title":"SONYC-UST-V2: An urban sound tagging dataset with spatiotemporal context","author":"Cartwright","year":"2020"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682475"},{"key":"ref51","first-page":"933","article-title":"Language modeling with gated convolutional networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dauphin"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"}],"container-title":["IEEE Transactions on Cognitive and Developmental Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7274989\/10146524\/09737309.pdf?arnumber=9737309","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,18]],"date-time":"2024-01-18T00:44:37Z","timestamp":1705538677000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9737309\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6]]},"references-count":54,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcds.2022.3160168","relation":{},"ISSN":["2379-8920","2379-8939"],"issn-type":[{"value":"2379-8920","type":"print"},{"value":"2379-8939","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6]]}}}