{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T14:51:48Z","timestamp":1784904708793,"version":"3.55.0"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585648","type":"print"},{"value":"9783030585655","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-58565-5_18","type":"book-chapter","created":{"date-parts":[[2020,11,11]],"date-time":"2020-11-11T12:03:19Z","timestamp":1605096199000},"page":"292-308","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":127,"title":["Multiple Sound Sources Localization from Coarse to Fine"],"prefix":"10.1007","author":[{"given":"Rui","family":"Qian","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Di","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heinrich","family":"Dinkel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengyue","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ning","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiyao","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,11,12]]},"reference":[{"key":"18_CR1","doi-asserted-by":"publisher","unstructured":"Arandjelovic, R., Zisserman, A.: Look, listen and learn. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 609\u2013617, October 2017. https:\/\/doi.org\/10.1109\/ICCV.2017.73","DOI":"10.1109\/ICCV.2017.73"},{"key":"18_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1007\/978-3-030-01246-5_27","volume-title":"Computer Vision \u2013 ECCV 2018","author":"R Arandjelovi\u0107","year":"2018","unstructured":"Arandjelovi\u0107, R., Zisserman, A.: Objects that sound. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 451\u2013466. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01246-5_27"},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Aytar, Y., Vondrick, C., Torralba, A.: SoundNet: learning sound representations from unlabeled video. In: Lee, D.D., Sugiyama, M., Luxburg, U.V., Guyon, I., Garnett, R. (eds.) Advances in Neural Information Processing Systems 29, pp. 892\u2013900. Curran Associates, Inc. (2016). http:\/\/papers.nips.cc\/paper\/6146-soundnet-learning-sound-representations-from-unlabeled-video.pdf","DOI":"10.1109\/CVPR.2016.18"},{"key":"18_CR4","doi-asserted-by":"publisher","unstructured":"Chattopadhay, A., Sarkar, A., Howlader, P., Balasubramanian, V.N.: Grad-CAM++: generalized gradient-based visual explanations for deep convolutional networks. In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 839\u2013847, March 2018. https:\/\/doi.org\/10.1109\/WACV.2018.00097","DOI":"10.1109\/WACV.2018.00097"},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Gan, C., Huang, D., Zhao, H., Tenenbaum, J.B., Torralba, A.: Music gesture for visual sound separation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10478\u201310487 (2020)","DOI":"10.1109\/CVPR42600.2020.01049"},{"key":"18_CR6","doi-asserted-by":"crossref","unstructured":"Gan, C., Zhang, Y., Wu, J., Gong, B., Tenenbaum, J.B.: Look, listen, and act: towards audio-visual embodied navigation. arXiv preprint arXiv:1912.11684 (2019)","DOI":"10.1109\/ICRA40945.2020.9197008"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Gan, C., Zhao, H., Chen, P., Cox, D., Torralba, A.: Self-supervised moving vehicle tracking with stereo sound. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 7053\u20137062 (2019)","DOI":"10.1109\/ICCV.2019.00715"},{"key":"18_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1007\/978-3-030-01219-9_3","volume-title":"Computer Vision \u2013 ECCV 2018","author":"R Gao","year":"2018","unstructured":"Gao, R., Feris, R., Grauman, K.: Learning to separate object sounds by watching unlabeled video. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 36\u201354. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01219-9_3"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Gao, R., Grauman, K.: 2.5D visual sound. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 324\u2013333 (2019)","DOI":"10.1109\/CVPR.2019.00041"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Gao, R., Grauman, K.: Co-separating sounds of visual objects. In: The IEEE International Conference on Computer Vision (ICCV), October 2019","DOI":"10.1109\/ICCV.2019.00398"},{"key":"18_CR11","doi-asserted-by":"publisher","unstructured":"Gemmeke, J.F., et al.: Audio set: an ontology and human-labeled dataset for audio events. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 776\u2013780, March 2017. https:\/\/doi.org\/10.1109\/ICASSP.2017.7952261","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"18_CR12","doi-asserted-by":"publisher","unstructured":"Hadsell, R., Chopra, S., LeCun, Y.: Dimensionality reduction by learning an invariant mapping. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2006), vol. 2, pp. 1735\u20131742, June 2006. https:\/\/doi.org\/10.1109\/CVPR.2006.100","DOI":"10.1109\/CVPR.2006.100"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016","DOI":"10.1109\/CVPR.2016.90"},{"key":"18_CR14","doi-asserted-by":"publisher","unstructured":"Hershey, S., et al.: CNN architectures for large-scale audio classification. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 131\u2013135, March 2017. https:\/\/doi.org\/10.1109\/ICASSP.2017.7952132","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Hu, D., Nie, F., Li, X.: Deep multimodal clustering for unsupervised audiovisual learning. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2019","DOI":"10.1109\/CVPR.2019.00947"},{"key":"18_CR16","unstructured":"Hu, D., Wang, Z., Xiong, H., Wang, D., Nie, F., Dou, D.: Curriculum audiovisual learning. arXiv preprint arXiv:2001.09414 (2020)"},{"key":"18_CR17","unstructured":"Korbar, B., Tran, D., Torresani, L.: Co-training of audio and video representations from self-supervised temporal synchronization. arXiv:1807.00230 (2018)"},{"key":"18_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"639","DOI":"10.1007\/978-3-030-01231-1_39","volume-title":"Computer Vision \u2013 ECCV 2018","author":"A Owens","year":"2018","unstructured":"Owens, A., Efros, A.A.: Audio-visual scene analysis with self-supervised multisensory features. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 639\u2013658. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01231-1_39"},{"key":"18_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"801","DOI":"10.1007\/978-3-319-46448-0_48","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Owens","year":"2016","unstructured":"Owens, A., Wu, J., McDermott, J.H., Freeman, W.T., Torralba, A.: Ambient sound provides supervision for visual learning. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 801\u2013816. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_48"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: GloVe: global vectors for word representation. In: Empirical Methods in Natural Language Processing (EMNLP), pp. 1532\u20131543 (2014). http:\/\/www.aclweb.org\/anthology\/D14-1162","DOI":"10.3115\/v1\/D14-1162"},{"key":"18_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2014 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Rouditchenko, A., Zhao, H., Gan, C., McDermott, J., Torralba, A.: Self-supervised audio-visual co-segmentation. In: ICASSP 2019\u20132019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2357\u20132361. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8682467"},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. In: The IEEE International Conference on Computer Vision (ICCV), October 2017","DOI":"10.1109\/ICCV.2017.74"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Senocak, A., Oh, T.H., Kim, J., Yang, M.H., So Kweon, I.: Learning to localize sound source in visual scenes. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018","DOI":"10.1109\/CVPR.2018.00458"},{"issue":"11","key":"18_CR25","doi-asserted-by":"publisher","first-page":"2298","DOI":"10.1109\/TPAMI.2016.2646371","volume":"39","author":"B Shi","year":"2017","unstructured":"Shi, B., Bai, X., Yao, C.: An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. IEEE Trans. Pattern Anal. Mach. Intell. 39(11), 2298\u20132304 (2017). https:\/\/doi.org\/10.1109\/TPAMI.2016.2646371","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"18_CR26","unstructured":"Spiertz, M., Gnann, V.: Source-filter based clustering for monaural blind source separation. In: Proceedings of the 12th International Conference on Digital Audio Effects (2009)"},{"key":"18_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1007\/978-3-030-01216-8_16","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Y Tian","year":"2018","unstructured":"Tian, Y., Shi, J., Li, B., Duan, Z., Xu, C.: Audio-visual event localization in unconstrained videos. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11206, pp. 252\u2013268. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01216-8_16"},{"key":"18_CR28","doi-asserted-by":"crossref","unstructured":"Zhao, H., Gan, C., Ma, W.C., Torralba, A.: The sound of motions. In: The IEEE International Conference on Computer Vision (ICCV), October 2019","DOI":"10.1109\/ICCV.2019.00182"},{"key":"18_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"587","DOI":"10.1007\/978-3-030-01246-5_35","volume-title":"Computer Vision \u2013 ECCV 2018","author":"H Zhao","year":"2018","unstructured":"Zhao, H., Gan, C., Rouditchenko, A., Vondrick, C., McDermott, J., Torralba, A.: The sound of pixels. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 587\u2013604. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01246-5_35"},{"key":"18_CR30","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016","DOI":"10.1109\/CVPR.2016.319"},{"key":"18_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1007\/978-3-030-58610-2_4","volume-title":"Computer Vision \u2013 ECCV 2020","author":"H Zhou","year":"2020","unstructured":"Zhou, H., Xu, X., Lin, D., Wang, X., Liu, Z.: Sep-stereo: visually guided stereophonic audio generation by associating source separation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12357, pp. 52\u201369. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58610-2_4"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58565-5_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,11]],"date-time":"2024-11-11T00:06:06Z","timestamp":1731283566000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58565-5_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585648","9783030585655"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58565-5_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"12 November 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1360","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"27% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"7","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}