{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,17]],"date-time":"2026-05-17T06:09:06Z","timestamp":1778998146093,"version":"3.51.4"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"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":["62302006"],"award-info":[{"award-number":["62302006"]}],"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":["62276135"],"award-info":[{"award-number":["62276135"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003995","name":"Natural Science Foundation of Anhui Province","doi-asserted-by":"publisher","award":["2308085QF221"],"award-info":[{"award-number":["2308085QF221"]}],"id":[{"id":"10.13039\/501100003995","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1109\/tpami.2024.3363508","type":"journal-article","created":{"date-parts":[[2024,2,7]],"date-time":"2024-02-07T18:43:48Z","timestamp":1707331428000},"page":"4896-4907","source":"Crossref","is-referenced-by-count":10,"title":["Robust Audio-Visual Contrastive Learning for Proposal-Based Self-Supervised Sound Source Localization in Videos"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4633-2794","authenticated-orcid":false,"given":"Hanyu","family":"Xuan","sequence":"first","affiliation":[{"name":"School of Big Data and Statistics, Anhui University, Heifei, Anhui, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6597-8048","authenticated-orcid":false,"given":"Zhiliang","family":"Wu","sequence":"additional","affiliation":[{"name":"CCAI, Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4800-832X","authenticated-orcid":false,"given":"Jian","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6238-1596","authenticated-orcid":false,"given":"Bo","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Anhui University, Heifei, Anhui, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7618-119X","authenticated-orcid":false,"given":"Lei","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5354-1084","authenticated-orcid":false,"given":"Xavier","family":"Alameda-Pineda","sequence":"additional","affiliation":[{"name":"INRIA, University Grenoble Alpes, Grenoble, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9976-0442","authenticated-orcid":false,"given":"Yan","family":"Yan","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Illinois Institute of Technology, Chicago, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2004.01.008"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1162\/1064546053278973"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968183"},{"key":"ref4","first-page":"8","article-title":"Drone positioning system based on sound signals detection for tracking and photography","volume-title":"Proc. IEEE Annu. Inf. Technol. Electron. Mob. Commun. Conf.","author":"Mismar"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref6","first-page":"292","article-title":"Multiple sound sources localization from coarse to fine","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Rui"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5361"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3090866"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_35"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_27"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00458"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00947"},{"key":"ref13","first-page":"10 077","article-title":"Discriminative sounding objects localization via self-supervised audio-visual matching","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hu"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01659"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00110"},{"key":"ref16","first-page":"875","article-title":"Formal limitations on the measurement of mutual information","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"McAllester"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01274"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01229"},{"key":"ref19","article-title":"Active contrastive learning of audio-visual video representations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ma"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref22","first-page":"5628","article-title":"A theoretical analysis of contrastive unsupervised representation learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Saunshi"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2023.3238524"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00407"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2876304"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01061"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00481"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.155"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/506"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.274"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2228476"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00542"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3137988"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2952095"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_13"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00065"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747867"},{"key":"ref40","first-page":"3222","article-title":"Self-supervised predictive learning: A negative-free method for sound source localization in visual scenes","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Song"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548317"},{"key":"ref42","first-page":"37 524","article-title":"A closer look at weakly-supervised audio-visual source localization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mo"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00231"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00517"},{"key":"ref45","first-page":"7774","article-title":"Cooperative learning of audio and video models from self-supervised synchronization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Korbar"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3390\/technologies9010002"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2535231"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.366"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.326"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00993"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00139"},{"key":"ref54","first-page":"9735","article-title":"Weakly supervised object detection with segmentation collaboration","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Xiaoyan"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00966"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.457"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00230"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2389824"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_26"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794166"},{"key":"ref64","first-page":"297","article-title":"Noise-contrastive estimation: A new estimation principle for unnormalized statistical models","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Gutmann"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref66","first-page":"18 661","article-title":"Supervised contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Khosla"},{"key":"ref67","first-page":"892","article-title":"SoundNet: Learning sound representations from unlabeled video","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Aytar"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref70","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10550108\/10423816.pdf?arnumber=10423816","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T09:47:02Z","timestamp":1725961622000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10423816\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7]]},"references-count":70,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3363508","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7]]}}}