{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T17:06:40Z","timestamp":1784394400407,"version":"3.55.0"},"reference-count":81,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Major Project for New Generation of AI","award":["2018AAA0100400"],"award-info":[{"award-number":["2018AAA0100400"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61836014"],"award-info":[{"award-number":["61836014"]}],"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":["U21B2042"],"award-info":[{"award-number":["U21B2042"]}],"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":["62072457"],"award-info":[{"award-number":["62072457"]}],"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":["62006231"],"award-info":[{"award-number":["62006231"]}],"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":["61976174"],"award-info":[{"award-number":["61976174"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2021M703489"],"award-info":[{"award-number":["2021M703489"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1109\/tnnls.2023.3288022","type":"journal-article","created":{"date-parts":[[2023,7,12]],"date-time":"2023-07-12T17:23:40Z","timestamp":1689182620000},"page":"15528-15542","source":"Crossref","is-referenced-by-count":6,"title":["Visually Guided Sound Source Separation With Audio-Visual Predictive Coding"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7914-3252","authenticated-orcid":false,"given":"Zengjie","family":"Song","sequence":"first","affiliation":[{"name":"School of Mathematics and Statistics, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2648-3875","authenticated-orcid":false,"given":"Zhaoxiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Center for Research on Intelligent Perception and Computing, National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1037\/h0074549"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-7687.2006.00512.x"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nrn2331"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.actpsy.2010.03.010"},{"key":"ref5","first-page":"892","article-title":"SoundNet: Learning sound representations from unlabeled video","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Aytar"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref7","first-page":"7763","article-title":"Cooperative learning of audio and video models from self-supervised synchronization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Korbar"},{"key":"ref8","first-page":"435","article-title":"Objects that sound","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Arandjelovi\u00e1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11018-5_62"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00694"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12329"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00374"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747669"},{"key":"ref15","first-page":"813","article-title":"Audio-vision: Using audio-visual synchrony to locate sounds","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hershey"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00458"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00947"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01659"},{"key":"ref20","first-page":"3222","article-title":"Self-supervised predictive learning: A negative-free method for sound source localization in visual scenes","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Song"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_3"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_35"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00398"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00097"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00182"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01049"},{"key":"ref28","first-page":"1","article-title":"Visually guided sound source separation using cascaded opponent filter network","volume-title":"Proc. Asian Conf. Comput. Vis.","author":"Zhu"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00124"},{"key":"ref30","first-page":"1","article-title":"Learning audio-visual dynamics using scene graphs for audio source separation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chatterjee"},{"key":"ref31","first-page":"36858","article-title":"Towards versatile embodied navigation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Wang"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref33","article-title":"Curriculum audiovisual learning","author":"Hu","year":"2020","journal-title":"arXiv:2001.09414"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1038\/4580"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2005.1622"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.bandc.2015.11.003"},{"key":"ref38","first-page":"5266","article-title":"Deep predictive coding network for object recognition","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wen"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2862866"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1162\/0899766054322964"},{"key":"ref41","first-page":"556","article-title":"Algorithms for non-negative matrix factorization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lee"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2003.1285860"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2006-655"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.885253"},{"key":"ref45","first-page":"1","article-title":"Source-filter based clustering for monaural blind source separation","volume-title":"Proc. Int. Conf. Digital Audio Effects","author":"Spiertz"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1002\/9780470747278"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853860"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-53547-0_25"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461722"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3066303"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462527"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2853566"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682061"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_48"},{"key":"ref61","first-page":"9758","article-title":"Self-supervised learning by cross-modal audio-video clustering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alwassel"},{"key":"ref62","first-page":"25","article-title":"Self-supervised multimodal versatile networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Alayrac"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_13"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-021-1293-0"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104425"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref69","first-page":"1","article-title":"Rectifier nonlinearities improve neural network acoustic models","volume-title":"Proc. Int. Conf. Mach. Learn. Workshop","author":"Maas"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472159"},{"key":"ref71","first-page":"10268","article-title":"Understanding self-supervised learning dynamics without contrastive pairs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tian"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2856090"},{"key":"ref73","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Loshchilov"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2003.1292216"},{"key":"ref75","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682467"},{"key":"ref78","article-title":"Learning controllable disentangled representations with decorrelation regularization","author":"Song","year":"2019","journal-title":"arXiv:1912.11675"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3000480"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01410"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01657"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10737991\/10180219.pdf?arnumber=10180219","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T19:24:52Z","timestamp":1732735492000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10180219\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11]]},"references-count":81,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2023.3288022","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11]]}}}