{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T18:01:28Z","timestamp":1790704888605,"version":"4.1.0"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82272072"],"award-info":[{"award-number":["82272072"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Scientific and Technological Innovation (STI) 2030?Major Projects","award":["2021ZD0201503"],"award-info":[{"award-number":["2021ZD0201503"]}]},{"name":"CAAI-Huawei MindSpore Open Fund"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611869","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:12Z","timestamp":1698391632000},"page":"6025-6033","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Auditory Attention Decoding with Task-Related Multi-View Contrastive Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8945-3150","authenticated-orcid":false,"given":"Xiaoyu","family":"Chen","sequence":"first","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences & University of Chinese Academy of Science, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0084-433X","authenticated-orcid":false,"given":"Changde","family":"Du","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9498-9523","authenticated-orcid":false,"given":"Qiongyi","family":"Zhou","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences & University of Chinese Academy of Science, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0684-1711","authenticated-orcid":false,"given":"Huiguang","family":"He","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences & University of Chinese Academy of Science, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"A tutorial on auditory attention identification methods. Frontiers in neuroscience","author":"Alickovic Emina","year":"2019","unstructured":"Emina Alickovic, Thomas Lunner, Fredrik Gustafsson, and Lennart Ljung. 2019. A tutorial on auditory attention identification methods. Frontiers in neuroscience (2019), 153."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2016.2571900"},{"key":"e_1_3_2_1_3_1","volume-title":"A mechanical model for human attention and immediate memory. Psychological review","author":"Broadbent Donald Eric","year":"1957","unstructured":"Donald Eric Broadbent. 1957. A mechanical model for human attention and immediate memory. Psychological review, Vol. 64, 3 (1957), 205."},{"key":"e_1_3_2_1_4_1","volume-title":"Perception and communication","author":"Broadbent Donald Eric","unstructured":"Donald Eric Broadbent. 2013. Perception and communication. Elsevier."},{"key":"e_1_3_2_1_5_1","volume-title":"Neuronal oscillations in cortical networks. science","author":"Buzsaki Gyorgy","year":"2004","unstructured":"Gyorgy Buzsaki and Andreas Draguhn. 2004. Neuronal oscillations in cortical networks. science, Vol. 304, 5679 (2004), 1926--1929."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2021.3125283"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1121\/1.1907229"},{"key":"e_1_3_2_1_8_1","volume-title":"Comparison of two-talker attention decoding from EEG with nonlinear neural networks and linear methods. Scientific reports","author":"Ciccarelli Gregory","year":"2019","unstructured":"Gregory Ciccarelli, Michael Nolan, Joseph Perricone, Paul T Calamia, Stephanie Haro, James O'Sullivan, Nima Mesgarani, Thomas F Quatieri, and Christopher J Smalt. 2019. Comparison of two-talker attention decoding from EEG with nonlinear neural networks and linear methods. Scientific reports, Vol. 9, 1 (2019), 1--10."},{"key":"e_1_3_2_1_9_1","volume-title":"The cocktail party phenomenon revisited: The importance of working memory capacity. Psychonomic bulletin & review","author":"Conway Andrew RA","year":"2001","unstructured":"Andrew RA Conway, Nelson Cowan, and Michael F Bunting. 2001. The cocktail party phenomenon revisited: The importance of working memory capacity. Psychonomic bulletin & review, Vol. 8 (2001), 331--335."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Bohan Dai Chuansheng Chen Yuhang Long Lifen Zheng Hui Zhao Xialu Bai Wenda Liu Yuxuan Zhang Li Liu Taomei Guo et al. 2018. Neural mechanisms for selectively tuning in to the target speaker in a naturalistic noisy situation. Nature communications Vol. 9 1 (2018) 2405.","DOI":"10.1038\/s41467-018-04819-z"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/aae0a6"},{"key":"e_1_3_2_1_12_1","volume-title":"Auditory attention detection dataset KULeuven. Zenodo","author":"Das Neetha","year":"2019","unstructured":"Neetha Das, Tom Francart, and Alexander Bertrand. 2019. Auditory attention detection dataset KULeuven. Zenodo (2019)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-71278-5_33"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/abf771"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2018.01.033"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1111\/ejn.13790"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1152\/jn.00297.2011"},{"key":"e_1_3_2_1_18_1","volume-title":"EEG and audio dataset for auditory attention decoding. Zenodo","author":"Fuglsang SA","year":"2018","unstructured":"SA Fuglsang, DDE Wong, and J Hjortkj\u00e6r. 2018. EEG and audio dataset for auditory attention decoding. Zenodo (2018)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2021.3075932"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2012.12.037"},{"key":"e_1_3_2_1_21_1","volume-title":"Training products of experts by minimizing contrastive divergence. Neural computation","author":"Hinton Geoffrey E","year":"2002","unstructured":"Geoffrey E Hinton. 2002. Training products of experts by minimizing contrastive divergence. Neural computation, Vol. 14, 8 (2002), 1771--1800."},{"key":"e_1_3_2_1_22_1","volume-title":"Long short-term memory. Neural computation","author":"Hochreiter Sepp","year":"1997","unstructured":"Sepp Hochreiter and J\u00fcrgen Schmidhuber. 1997. Long short-term memory. Neural computation, Vol. 9, 8 (1997), 1735--1780."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC44109.2020.9176208"},{"key":"e_1_3_2_1_24_1","volume-title":"Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114","author":"Kingma Diederik P","year":"2013","unstructured":"Diederik P Kingma and Max Welling. 2013. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014114"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.3389\/fphys.2021.700655"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cub.2009.09.005"},{"key":"e_1_3_2_1_28_1","volume-title":"Nature","volume":"485","author":"Mesgarani Nima","year":"2012","unstructured":"Nima Mesgarani and Edward F Chang. 2012. Selective cortical representation of attended speaker in multi-talker speech perception. Nature, Vol. 485, 7397 (2012), 233--236."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2560\/12\/4\/046007"},{"key":"e_1_3_2_1_30_1","volume-title":"Nima Mesgarani, Siddharth Rajaram, John J Foxe, Barbara G Shinn-Cunningham, Malcolm Slaney, Shihab A Shamma, and Edmund C Lalor.","author":"O'Sullivan James A","year":"2015","unstructured":"James A O'Sullivan, Alan J Power, Nima Mesgarani, Siddharth Rajaram, John J Foxe, Barbara G Shinn-Cunningham, Malcolm Slaney, Shihab A Shamma, and Edmund C Lalor. 2015. Attentional selection in a cocktail party environment can be decoded from single-trial EEG. Cerebral cortex, Vol. 25, 7 (2015), 1697--1706."},{"key":"e_1_3_2_1_31_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_32_1","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Shi Yuge","year":"2019","unstructured":"Yuge Shi, Brooks Paige, Philip Torr, et al. 2019. Variational mixture-of-experts autoencoders for multi-modal deep generative models. Advances in Neural Information Processing Systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_33_1","volume-title":"Philip HS Torr, and N Siddharth","author":"Shi Yuge","year":"2020","unstructured":"Yuge Shi, Brooks Paige, Philip HS Torr, and N Siddharth. 2020. Relating by contrasting: A data-efficient framework for multimodal generative models. arXiv preprint arXiv:2007.01179 (2020)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2022.3140246"},{"key":"e_1_3_2_1_35_1","first-page":"6100","article-title":"Multimodal generative learning utilizing jensen-shannon-divergence","volume":"33","author":"Sutter Thomas","year":"2020","unstructured":"Thomas Sutter, Imant Daunhawer, and Julia Vogt. 2020. Multimodal generative learning utilizing jensen-shannon-divergence. Advances in Neural Information Processing Systems, Vol. 33 (2020), 6100--6110.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_36_1","volume-title":"Generalized multimodal ELBO. arXiv preprint arXiv:2105.02470","author":"Sutter Thomas M","year":"2021","unstructured":"Thomas M Sutter, Imant Daunhawer, and Julia E Vogt. 2021. Generalized multimodal ELBO. arXiv preprint arXiv:2105.02470 (2021)."},{"key":"e_1_3_2_1_37_1","article-title":"Visualizing data using t-SNE","volume":"9","author":"der Maaten Laurens Van","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of machine learning research, Vol. 9, 11 (2008).","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.56481"},{"key":"e_1_3_2_1_39_1","volume-title":"A comparison of regularization methods in forward and backward models for auditory attention decoding. Frontiers in neuroscience","author":"Wong Daniel DE","year":"2018","unstructured":"Daniel DE Wong, S\u00f8ren A Fuglsang, Jens Hjortkj\u00e6r, Enea Ceolini, Malcolm Slaney, and Alain De Cheveigne. 2018. A comparison of regularization methods in forward and backward models for auditory attention decoding. Frontiers in neuroscience, Vol. 12 (2018), 531."},{"key":"e_1_3_2_1_40_1","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Wu Mike","year":"2018","unstructured":"Mike Wu and Noah Goodman. 2018. Multimodal generative models for scalable weakly-supervised learning. Advances in Neural Information Processing Systems, Vol. 31 (2018)."},{"key":"e_1_3_2_1_41_1","volume-title":"Multimodal generative models for compositional representation learning. arXiv preprint arXiv:1912.05075","author":"Wu Mike","year":"2019","unstructured":"Mike Wu and Noah Goodman. 2019. Multimodal generative models for compositional representation learning. arXiv preprint arXiv:1912.05075 (2019)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.heares.2022.108552"},{"key":"e_1_3_2_1_43_1","volume-title":"Psychoacoustics: Facts and models.","author":"Zwicker Eberhard","year":"2013","unstructured":"Eberhard Zwicker and Hugo Fastl. 2013. Psychoacoustics: Facts and models. Vol. 22. Springer Science & Business Media."}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611869","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611869","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T23:59:49Z","timestamp":1755820789000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611869"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":43,"alternative-id":["10.1145\/3581783.3611869","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611869","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}