{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T10:43:55Z","timestamp":1770461035405,"version":"3.49.0"},"publisher-location":"Cham","reference-count":57,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030695439","type":"print"},{"value":"9783030695446","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-69544-6_25","type":"book-chapter","created":{"date-parts":[[2021,2,25]],"date-time":"2021-02-25T11:05:00Z","timestamp":1614251100000},"page":"409-426","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Visually Guided Sound Source Separation Using Cascaded Opponent Filter Network"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6707-6665","authenticated-orcid":false,"given":"Lingyu","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8767-0864","authenticated-orcid":false,"given":"Esa","family":"Rahtu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,2,26]]},"reference":[{"key":"25_CR1","doi-asserted-by":"publisher","first-page":"472","DOI":"10.1023\/A:1007425814087","volume":"29","author":"Z Ghahramani","year":"1996","unstructured":"Ghahramani, Z., Jordan, M.I.: Factorial hidden Markov models. Mach. Learn. 29, 472\u2013478 (1996). https:\/\/doi.org\/10.1023\/A:1007425814087","journal-title":"Mach. Learn."},{"key":"25_CR2","unstructured":"Roweis, S.T.: One microphone source separation. In: Advances in Neural Information Processing Systems, pp. 793\u2013799 (2001)"},{"key":"25_CR3","doi-asserted-by":"publisher","DOI":"10.1002\/9780470747278","volume-title":"Nonnegative Matrix and Tensor Factorizations: Applications to Exploratory Multi-way Data Analysis and Blind Source Separation","author":"A Cichocki","year":"2009","unstructured":"Cichocki, A., Zdunek, R., Phan, A.H., Amari, S.I.: Nonnegative Matrix and Tensor Factorizations: Applications to Exploratory Multi-way Data Analysis and Blind Source Separation. Wiley, Hoboken (2009)"},{"key":"25_CR4","doi-asserted-by":"publisher","first-page":"1066","DOI":"10.1109\/TASL.2006.885253","volume":"15","author":"T Virtanen","year":"2007","unstructured":"Virtanen, T.: Monaural sound source separation by nonnegative matrix factorization with temporal continuity and sparseness criteria. IEEE Trans. Audio Speech Lang. Process. 15, 1066\u20131074 (2007)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"25_CR5","doi-asserted-by":"crossref","unstructured":"Ephrat, A., et al.: Looking to listen at the cocktail party: a speaker-independent audio-visual model for speech separation. arXiv preprint arXiv:1804.03619 (2018)","DOI":"10.1145\/3197517.3201357"},{"key":"25_CR6","doi-asserted-by":"crossref","unstructured":"Gao, R., Feris, R., Grauman, K.: Learning to separate object sounds by watching unlabeled video. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 35\u201353 (2018)","DOI":"10.1007\/978-3-030-01219-9_3"},{"key":"25_CR7","doi-asserted-by":"crossref","unstructured":"Owens, A., Efros, A.A.: Audio-visual scene analysis with self-supervised multisensory features. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 631\u2013648 (2018)","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"25_CR8","doi-asserted-by":"crossref","unstructured":"Zhao, H., Gan, C., Rouditchenko, A., Vondrick, C., McDermott, J., Torralba, A.: The sound of pixels. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 570\u2013586 (2018)","DOI":"10.1007\/978-3-030-01246-5_35"},{"key":"25_CR9","doi-asserted-by":"crossref","unstructured":"Zhao, H., Gan, C., Ma, W.C., Torralba, A.: The sound of motions. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1735\u20131744 (2019)","DOI":"10.1109\/ICCV.2019.00182"},{"key":"25_CR10","doi-asserted-by":"crossref","unstructured":"Xu, X., Dai, B., Lin, D.: Recursive visual sound separation using minus-plus net. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 882\u2013891 (2019)","DOI":"10.1109\/ICCV.2019.00097"},{"key":"25_CR11","doi-asserted-by":"crossref","unstructured":"Gao, R., Grauman, K.: 2.5 D 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":"25_CR12","doi-asserted-by":"crossref","unstructured":"Gao, R., Grauman, K.: Co-separating sounds of visual objects. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3879\u20133888 (2019)","DOI":"10.1109\/ICCV.2019.00398"},{"key":"25_CR13","doi-asserted-by":"crossref","unstructured":"Pertil\u00e4, P., Mieskolainen, M., H\u00e4m\u00e4l\u00e4inen, M.S.: Closed-form self-localization of asynchronous microphone arrays. In: Joint Workshop on Hands-Free Speech Communication and Microphone Arrays, vol. 2011, pp. 139\u2013144. IEEE (2011)","DOI":"10.1109\/HSCMA.2011.5942380"},{"key":"25_CR14","doi-asserted-by":"crossref","unstructured":"Tian, Y., Shi, J., Li, B., Duan, Z., Xu, C.: Audio-visual event localization in unconstrained videos. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 247\u2013263 (2018)","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"25_CR15","doi-asserted-by":"crossref","unstructured":"Hu, D., Nie, F., Li, X.: Deep multimodal clustering for unsupervised audiovisual learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9248\u20139257 (2019)","DOI":"10.1109\/CVPR.2019.00947"},{"key":"25_CR16","doi-asserted-by":"crossref","unstructured":"Bilen, H., Fernando, B., Gavves, E., Vedaldi, A., Gould, S.: Dynamic image networks for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3034\u20133042 (2016)","DOI":"10.1109\/CVPR.2016.331"},{"key":"25_CR17","doi-asserted-by":"crossref","unstructured":"Aytar, Y., Vondrick, C., Torralba, A.: Soundnet: learning sound representations from unlabeled video. In: Advances in Neural Information Processing Systems, pp. 892\u2013900 (2016)","DOI":"10.1109\/CVPR.2016.18"},{"key":"25_CR18","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":"25_CR19","doi-asserted-by":"crossref","unstructured":"Arandjelovic, R., Zisserman, A.: Look, listen and learn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 609\u2013617 (2017)","DOI":"10.1109\/ICCV.2017.73"},{"key":"25_CR20","doi-asserted-by":"crossref","unstructured":"Arandjelovic, R., Zisserman, A.: Objects that sound. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 435\u2013451 (2018)","DOI":"10.1007\/978-3-030-01246-5_27"},{"key":"25_CR21","doi-asserted-by":"crossref","unstructured":"Nagrani, A., Albanie, S., Zisserman, A.: Seeing voices and hearing faces: cross-modal biometric matching. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8427\u20138436 (2018)","DOI":"10.1109\/CVPR.2018.00879"},{"key":"25_CR22","unstructured":"Alwassel, H., Mahajan, D., Torresani, L., Ghanem, B., Tran, D.: Self-supervised learning by cross-modal audio-video clustering. arXiv preprint arXiv:1911.12667 (2019)"},{"key":"25_CR23","doi-asserted-by":"crossref","unstructured":"Zhou, H., Liu, Y., Liu, Z., Luo, P., Wang, X.: Talking face generation by adversarially disentangled audio-visual representation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 9299\u20139306 (2019)","DOI":"10.1609\/aaai.v33i01.33019299"},{"key":"25_CR24","doi-asserted-by":"crossref","unstructured":"Cudeiro, D., Bolkart, T., Laidlaw, C., Ranjan, A., Black, M.J.: Capture, learning, and synthesis of 3D speaking styles. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 10101\u201310111 (2019)","DOI":"10.1109\/CVPR.2019.01034"},{"key":"25_CR25","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":"25_CR26","doi-asserted-by":"crossref","unstructured":"Hu, D., Wang, D., Li, X., Nie, F., Wang, Q.: Listen to the image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7972\u20137981 (2019)","DOI":"10.1109\/CVPR.2019.00816"},{"key":"25_CR27","doi-asserted-by":"crossref","unstructured":"Gan, C., Huang, D., Chen, P., Tenenbaum, J.B., Torralba, A.: Foley music: learning to generate music from videos. arXiv preprint arXiv:2007.10984 (2020)","DOI":"10.1007\/978-3-030-58621-8_44"},{"key":"25_CR28","unstructured":"Chen, C., Jain, U., Schissler, C., Gari, S.V.A., Al-Halah, Z., Ithapu, V.K., Robinson, P., Grauman, K.: Audio-visual embodied navigation. arXiv preprint arXiv:1912.11474 (2019)"},{"key":"25_CR29","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. In: 2020 IEEE International Conference on Robotics and Automation (ICRA), pp. 9701\u20139707. IEEE (2020)","DOI":"10.1109\/ICRA40945.2020.9197008"},{"key":"25_CR30","doi-asserted-by":"crossref","unstructured":"Nagrani, A., Chung, J.S., Albanie, S., Zisserman, A.: Disentangled speech embeddings using cross-modal self-supervision. arXiv preprint arXiv:2002.08742 (2020)","DOI":"10.1109\/ICASSP40776.2020.9054057"},{"key":"25_CR31","doi-asserted-by":"crossref","unstructured":"Laptev, I., Marszalek, M., Schmid, C., Rozenfeld, B.: Learning realistic human actions from movies. In: 2008 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20138. IEEE (2008)","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"25_CR32","doi-asserted-by":"crossref","unstructured":"Wang, H., Ullah, M.M., Klaser, A., Laptev, I., Schmid, C.: Evaluation of local spatio-temporal features for action recognition (2009)","DOI":"10.5244\/C.23.124"},{"key":"25_CR33","doi-asserted-by":"crossref","unstructured":"Klaser, A., Marsza\u0142ek, M., Schmid, C.: A spatio-temporal descriptor based on 3D-gradients (2008)","DOI":"10.5244\/C.22.99"},{"key":"25_CR34","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3d convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4489\u20134497 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"25_CR35","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Advances in Neural Information Processing Systems, pp. 568\u2013576 (2014)"},{"key":"25_CR36","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"25_CR37","doi-asserted-by":"crossref","unstructured":"Zhan, X., Pan, X., Liu, Z., Lin, D., Loy, C.C.: Self-supervised learning via conditional motion propagation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1881\u20131889 (2019)","DOI":"10.1109\/CVPR.2019.00198"},{"key":"25_CR38","doi-asserted-by":"crossref","unstructured":"Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2625\u20132634 (2015)","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"25_CR39","doi-asserted-by":"crossref","unstructured":"Wang, X., Gupta, A.: Videos as space-time region graphs. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 399\u2013417 (2018)","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"25_CR40","doi-asserted-by":"crossref","unstructured":"Long, X., Gan, C., De Melo, G., Wu, J., Liu, X., Wen, S.: Attention clusters: purely attention based local feature integration for video classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7834\u20137843 (2018)","DOI":"10.1109\/CVPR.2018.00817"},{"key":"25_CR41","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1007\/978-3-319-22482-4_50","volume-title":"Latent Variable Analysis and Signal Separation","author":"AJR Simpson","year":"2015","unstructured":"Simpson, A.J.R., Roma, G., Plumbley, M.D.: Deep karaoke: extracting vocals from musical mixtures using a convolutional deep neural network. In: Vincent, E., Yeredor, A., Koldovsk\u00fd, Z., Tichavsk\u00fd, P. (eds.) LVA\/ICA 2015. LNCS, vol. 9237, pp. 429\u2013436. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-22482-4_50"},{"key":"25_CR42","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1007\/978-3-319-53547-0_25","volume-title":"Latent Variable Analysis and Signal Separation","author":"P Chandna","year":"2017","unstructured":"Chandna, P., Miron, M., Janer, J., G\u00f3mez, E.: Monoaural audio source separation using deep convolutional neural networks. In: Tichavsk\u00fd, P., Babaie-Zadeh, M., Michel, O.J.J., Thirion-Moreau, N. (eds.) LVA\/ICA 2017. LNCS, vol. 10169, pp. 258\u2013266. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-53547-0_25"},{"key":"25_CR43","doi-asserted-by":"crossref","unstructured":"Hershey, J.R., Chen, Z., Le Roux, J., Watanabe, S.: Deep clustering: discriminative embeddings for segmentation and separation. In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 31\u201335. IEEE (2016)","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"25_CR44","doi-asserted-by":"crossref","unstructured":"Grais, E.M., Plumbley, M.D.: Combining fully convolutional and recurrent neural networks for single channel audio source separation. In: Audio Engineering Society Convention 144, Audio Engineering Society (2018)","DOI":"10.1109\/GlobalSIP.2017.8309164"},{"key":"25_CR45","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":"25_CR46","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 \u2013 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":"25_CR47","unstructured":"Hershey, J.R., Movellan, J.R.: Audio vision: using audio-visual synchrony to locate sounds. In: Advances in Neural Information Processing Systems, pp. 813\u2013819 (2000)"},{"key":"25_CR48","doi-asserted-by":"crossref","unstructured":"Barzelay, Z., Schechner, Y.Y.: Harmony in motion. In: 2007 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20138. IEEE (2007)","DOI":"10.1109\/CVPR.2007.383344"},{"key":"25_CR49","doi-asserted-by":"crossref","unstructured":"Kidron, E., Schechner, Y.Y., Elad, M.: Pixels that sound. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005), vol. 1, pp. 88\u201395. IEEE (2005)","DOI":"10.1109\/CVPR.2005.274"},{"key":"25_CR50","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4358\u20134366 (2018)","DOI":"10.1109\/CVPR.2018.00458"},{"key":"25_CR51","doi-asserted-by":"publisher","first-page":"1120","DOI":"10.1007\/s11263-018-1083-5","volume":"126","author":"A Owens","year":"2018","unstructured":"Owens, A., Wu, J., McDermott, J.H., Freeman, W.T., Torralba, A.: Learning sight from sound: ambient sound provides supervision for visual learning. Int. J. Comput. Vis. 126, 1120\u20131137 (2018). https:\/\/doi.org\/10.1007\/s11263-018-1083-5","journal-title":"Int. J. Comput. Vis."},{"key":"25_CR52","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":"25_CR53","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"25_CR54","doi-asserted-by":"crossref","unstructured":"Sun, D., Yang, X., Liu, M.Y., Kautz, J.: Pwc-net: CNNs for optical flow using pyramid, warping, and cost volume. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8934\u20138943 (2018)","DOI":"10.1109\/CVPR.2018.00931"},{"key":"25_CR55","doi-asserted-by":"crossref","unstructured":"Hui, T.W., Tang, X., Change Loy, C.: Liteflownet: a lightweight convolutional neural network for optical flow estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8981\u20138989 (2018)","DOI":"10.1109\/CVPR.2018.00936"},{"key":"25_CR56","doi-asserted-by":"crossref","unstructured":"Hu, J., Zhang, Y., Okatani, T.: Visualization of convolutional neural networks for monocular depth estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3869\u20133878 (2019)","DOI":"10.1109\/ICCV.2019.00397"},{"key":"25_CR57","doi-asserted-by":"crossref","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. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7952261"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2020"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-69544-6_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,24]],"date-time":"2024-08-24T21:12:50Z","timestamp":1724533970000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-69544-6_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030695439","9783030695446"],"references-count":57,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-69544-6_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"26 February 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kyoto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","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":"30 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 December 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2020.kyoto\/","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":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"768","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":"254","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":"33% - 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":"3","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.","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)"}}]}}