{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T19:05:24Z","timestamp":1776107124702,"version":"3.50.1"},"publisher-location":"Cham","reference-count":68,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030586201","type":"print"},{"value":"9783030586218","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\/978-3-030-58621-8_44","type":"book-chapter","created":{"date-parts":[[2020,11,26]],"date-time":"2020-11-26T19:03:23Z","timestamp":1606417403000},"page":"758-775","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":85,"title":["Foley Music: Learning to Generate Music from Videos"],"prefix":"10.1007","author":[{"given":"Chuang","family":"Gan","sequence":"first","affiliation":[]},{"given":"Deng","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Peihao","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Joshua B.","family":"Tenenbaum","sequence":"additional","affiliation":[]},{"given":"Antonio","family":"Torralba","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,27]]},"reference":[{"key":"44_CR1","doi-asserted-by":"crossref","unstructured":"Albanie, S., Nagrani, A., Vedaldi, A., Zisserman, A.: Emotion recognition in speech using cross-modal transfer in the wild. In: ACM Multimedia (2018)","DOI":"10.1145\/3240508.3240578"},{"key":"44_CR2","doi-asserted-by":"crossref","unstructured":"Arandjelovic, R., Zisserman, A.: Look, listen and learn. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 609\u2013617. IEEE (2017)","DOI":"10.1109\/ICCV.2017.73"},{"key":"44_CR3","doi-asserted-by":"crossref","unstructured":"Arandjelovi\u0107, R., Zisserman, A.: Objects that sound. arXiv preprint arXiv:1712.06651 (2017)","DOI":"10.1007\/978-3-030-01246-5_27"},{"key":"44_CR4","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":"44_CR5","unstructured":"Briot, J.P., Hadjeres, G., Pachet, F.D.: Deep learning techniques for music generation-a survey. arXiv preprint arXiv:1709.01620 (2017)"},{"key":"44_CR6","doi-asserted-by":"crossref","unstructured":"Cao, Z., Hidalgo, G., Simon, T., Wei, S.E., Sheikh, Y.: OpenPose: realtime multi-person 2D pose estimation using part affinity fields. In: arXiv preprint arXiv:1812.08008 (2018)","DOI":"10.1109\/CVPR.2017.143"},{"key":"44_CR7","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4724\u20134733. IEEE (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"44_CR8","doi-asserted-by":"crossref","unstructured":"Chen, K., Zhang, C., Fang, C., Wang, Z., Bui, T., Nevatia, R.: Visually indicated sound generation by perceptually optimized classification. In: ECCV, vol. 11134, pp. 560\u2013574 (2018)","DOI":"10.1007\/978-3-030-11024-6_43"},{"key":"44_CR9","doi-asserted-by":"crossref","unstructured":"Chen, K., Zhang, C., Fang, C., Wang, Z., Bui, T., Nevatia, R.: Visually indicated sound generation by perceptually optimized classification. In: The European Conference on Computer Vision, pp. 560\u2013574 (2018)","DOI":"10.1007\/978-3-030-11024-6_43"},{"key":"44_CR10","doi-asserted-by":"crossref","unstructured":"Chen, L., Srivastava, S., Duan, Z., Xu, C.: Deep cross-modal audio-visual generation. In: ACM Multimedia 2017, pp. 349\u2013357 (2017)","DOI":"10.1145\/3126686.3126723"},{"key":"44_CR11","unstructured":"Chu, H., Urtasun, R., Fidler, S.: Song from pi: a musically plausible network for pop music generation. In: ICLR (2017)"},{"key":"44_CR12","doi-asserted-by":"crossref","unstructured":"Chung, J.S., Senior, A.W., Vinyals, O., Zisserman, A.: Lip reading sentences in the wild. In: CVPR, pp. 3444\u20133453 (2017)","DOI":"10.1109\/CVPR.2017.367"},{"key":"44_CR13","unstructured":"Engel, J.H., Agrawal, K.K., Chen, S., Gulrajani, I., Donahue, C., Roberts, A.: GANSynth: adversarial neural audio synthesis. In: ICLR (2019)"},{"issue":"4","key":"44_CR14","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1145\/3197517.3201357","volume":"37","author":"A Ephrat","year":"2018","unstructured":"Ephrat, A., et al.: Looking to listen at the cocktail party: a speaker-independent audio-visual model for speech separation. ACM Trans. Graph. (TOG) 37(4), 112 (2018)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"44_CR15","doi-asserted-by":"crossref","unstructured":"Gan, C., Huang, D., Zhao, H., Tenenbaum, J.B., Torralba, A.: Music gesture for visual sound separation. In: CVPR, pp. 10478\u201310487 (2020)","DOI":"10.1109\/CVPR42600.2020.01049"},{"key":"44_CR16","unstructured":"Gan, C., et al.: ThreeDWorld: a platform for interactive multi-modal physical simulation. arXiv preprint arXiv:2007.04954 (2020)"},{"key":"44_CR17","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: ICRA (2020)","DOI":"10.1109\/ICRA40945.2020.9197008"},{"key":"44_CR18","doi-asserted-by":"crossref","unstructured":"Gan, C., Zhao, H., Chen, P., Cox, D., Torralba, A.: Self-supervised moving vehicle tracking with stereo sound. In: ICCV, pp. 7053\u20137062 (2019)","DOI":"10.1109\/ICCV.2019.00715"},{"key":"44_CR19","doi-asserted-by":"crossref","unstructured":"Gao, R., Feris, R., Grauman, K.: Learning to separate object sounds by watching unlabeled video. In: ECCV, pp. 35\u201353 (2018)","DOI":"10.1007\/978-3-030-01219-9_3"},{"key":"44_CR20","unstructured":"Gao, R., Grauman, K.: 2.5 d visual sound. arXiv preprint arXiv:1812.04204 (2018)"},{"key":"44_CR21","doi-asserted-by":"crossref","unstructured":"Gao, R., Oh, T.H., Grauman, K., Torresani, L.: Listen to look: action recognition by previewing audio. In: CVPR, pp. 10457\u201310467 (2020)","DOI":"10.1109\/CVPR42600.2020.01047"},{"key":"44_CR22","doi-asserted-by":"crossref","unstructured":"Ginosar, S., Bar, A., Kohavi, G., Chan, C., Owens, A., Malik, J.: Learning individual styles of conversational gesture. In: CVPR, pp. 3497\u20133506 (2019)","DOI":"10.1109\/CVPR.2019.00361"},{"key":"44_CR23","doi-asserted-by":"publisher","DOI":"10.4324\/9780203863411","volume-title":"Musical Gestures: Sound, Movement, and Meaning","author":"RI God\u00f8y","year":"2010","unstructured":"God\u00f8y, R.I., Leman, M.: Musical Gestures: Sound, Movement, and Meaning. Routledge, Abingdon (2010)"},{"key":"44_CR24","unstructured":"Hadjeres, G., Pachet, F., Nielsen, F.: DeepBach: a steerable model for bach chorales generation. In: ICML, pp. 1362\u20131371 (2017)"},{"key":"44_CR25","unstructured":"Hawthorne, C., et al.: Enabling factorized piano music modeling and generation with the maestro dataset. In: ICLR (2019)"},{"key":"44_CR26","unstructured":"Hershey, J.R., Movellan, J.R.: Audio vision: using audio-visual synchrony to locate sounds. In: Solla, S.A., Leen, T.K., M\u00fcller, K. (eds.) Advances in Neural Information Processing Systems, vol. 12, pp. 813\u2013819 (2000)"},{"key":"44_CR27","doi-asserted-by":"crossref","unstructured":"Hu, D., et al.: Cross-task transfer for multimodal aerial scene recognition. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58586-0_5"},{"key":"44_CR28","unstructured":"Huang, C.Z.A., et al.: Music transformer: generating music with long-term structure (2018)"},{"issue":"2","key":"44_CR29","doi-asserted-by":"publisher","first-page":"378","DOI":"10.1109\/TMM.2012.2228476","volume":"15","author":"H Izadinia","year":"2013","unstructured":"Izadinia, H., Saleemi, I., Shah, M.: Multimodal analysis for identification and segmentation of moving-sounding objects. IEEE Trans. Multimed. 15(2), 378\u2013390 (2013)","journal-title":"IEEE Trans. Multimed."},{"key":"44_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11263-019-01150-y","volume":"127","author":"A Jamaludin","year":"2019","unstructured":"Jamaludin, A., Chung, J.S., Zisserman, A.: You said that?: Synthesising talking faces from audio. Int. J. Comput. Vis. 127, 1\u201313 (2019)","journal-title":"Int. J. Comput. Vis."},{"issue":"4","key":"44_CR31","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1145\/3072959.3073658","volume":"36","author":"T Karras","year":"2017","unstructured":"Karras, T., Aila, T., Laine, S., Herva, A., Lehtinen, J.: Audio-driven facial animation by joint end-to-end learning of pose and emotion. ACM Trans. Graph. (TOG) 36(4), 94 (2017)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"44_CR32","doi-asserted-by":"crossref","unstructured":"Koepke, A.S., Wiles, O., Moses, Y., Zisserman, A.: Sight to sound: an end-to-end approach for visual piano transcription. In: ICASSP, pp. 1838\u20131842 (2020)","DOI":"10.1109\/ICASSP40776.2020.9053115"},{"key":"44_CR33","unstructured":"Korbar, B., Tran, D., Torresani, L.: Co-training of audio and video representations from self-supervised temporal synchronization. arXiv preprint arXiv:1807.00230 (2018)"},{"issue":"2","key":"44_CR34","doi-asserted-by":"publisher","first-page":"522","DOI":"10.1109\/TMM.2018.2856090","volume":"21","author":"B Li","year":"2018","unstructured":"Li, B., Liu, X., Dinesh, K., Duan, Z., Sharma, G.: Creating a multitrack classical music performance dataset for multimodal music analysis: challenges, insights, and applications. IEEE Trans. Multimed. 21(2), 522\u2013535 (2018)","journal-title":"IEEE Trans. Multimed."},{"key":"44_CR35","doi-asserted-by":"crossref","unstructured":"Long, X., et al.: Multimodal keyless attention fusion for video classification. In: AAAI (2018)","DOI":"10.1609\/aaai.v32i1.12319"},{"key":"44_CR36","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: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00817"},{"issue":"5588","key":"44_CR37","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1038\/264746a0","volume":"264","author":"H McGurk","year":"1976","unstructured":"McGurk, H., MacDonald, J.: Hearing lips and seeing voices. Nature 264(5588), 746\u2013748 (1976)","journal-title":"Nature"},{"key":"44_CR38","unstructured":"Morgado, P., Nvasconcelos, N., Langlois, T., Wang, O.: Self-supervised generation of spatial audio for 360 video. In: NIPS (2018)"},{"key":"44_CR39","doi-asserted-by":"crossref","unstructured":"Nagrani, A., Albanie, S., Zisserman, A.: Seeing voices and hearing faces: cross-modal biometric matching. arXiv preprint arXiv:1804.00326 (2018)","DOI":"10.1109\/CVPR.2018.00879"},{"key":"44_CR40","unstructured":"Oord, A.V.D., et al.: WaveNet: a generative model for raw audio. In: ICLR (2017)"},{"key":"44_CR41","first-page":"1","volume":"32","author":"S Oore","year":"2018","unstructured":"Oore, S., Simon, I., Dieleman, S., Eck, D., Simonyan, K.: This time with feeling: learning expressive musical performance. Neural Comput. Appl. 32, 1\u201313 (2018)","journal-title":"Neural Comput. Appl."},{"key":"44_CR42","doi-asserted-by":"crossref","unstructured":"Owens, A., Efros, A.A.: Audio-visual scene analysis with self-supervised multisensory features. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"44_CR43","doi-asserted-by":"crossref","unstructured":"Owens, A., Isola, P., McDermott, J., Torralba, A., Adelson, E.H., Freeman, W.T.: Visually indicated sounds. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2405\u20132413 (2016)","DOI":"10.1109\/CVPR.2016.264"},{"key":"44_CR44","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":"44_CR45","doi-asserted-by":"publisher","first-page":"8292","DOI":"10.1109\/TIP.2020.3009820","volume":"29","author":"C Peihao","year":"2020","unstructured":"Peihao, C., Yang, Z., Mingkui, T., Hongdong, X., Deng, H., Chuang, G.: Generating visually aligned sound from videos. IEEE Trans. Image Process. 29, 8292\u20138302 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"44_CR46","unstructured":"Roberts, A., Engel, J., Raffel, C., Hawthorne, C., Eck, D.: A hierarchical latent vector model for learning long-term structure in music. arXiv preprint arXiv:1803.05428 (2018)"},{"key":"44_CR47","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":"44_CR48","doi-asserted-by":"crossref","unstructured":"Senocak, A., Oh, T.H., Kim, J., Yang, M.H., Kweon, I.S.: Learning to localize sound source in visual scenes. arXiv preprint arXiv:1803.03849 (2018)","DOI":"10.1109\/CVPR.2018.00458"},{"key":"44_CR49","doi-asserted-by":"crossref","unstructured":"Shaw, P., Uszkoreit, J., Vaswani, A.: Self-attention with relative position representations. arXiv preprint arXiv:1803.02155 (2018)","DOI":"10.18653\/v1\/N18-2074"},{"key":"44_CR50","doi-asserted-by":"crossref","unstructured":"Shlizerman, E., Dery, L., Schoen, H., Kemelmacher-Shlizerman, I.: Audio to body dynamics. In: CVPR, pp. 7574\u20137583 (2018)","DOI":"10.1109\/CVPR.2018.00790"},{"key":"44_CR51","doi-asserted-by":"crossref","unstructured":"Simon, T., Joo, H., Matthews, I., Sheikh, Y.: Hand keypoint detection in single images using multiview bootstrapping. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.494"},{"key":"44_CR52","unstructured":"Su, K., Liu, X., Shlizerman, E.: Audeo: audio generation for a silent performance video. arXiv preprint arXiv:2006.14348 (2020)"},{"key":"44_CR53","unstructured":"Submission, A.: At your fingertips: automatic piano fingering detection. In: ICLR (2020)"},{"issue":"4","key":"44_CR54","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1145\/3072959.3073640","volume":"36","author":"S Suwajanakorn","year":"2017","unstructured":"Suwajanakorn, S., Seitz, S.M., Kemelmacher-Shlizerman, I.: Synthesizing Obama: learning lip sync from audio. ACM Trans. Graph. (TOG) 36(4), 95 (2017)","journal-title":"ACM Trans. Graph. (TOG)"},{"issue":"4","key":"44_CR55","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1145\/3072959.3073699","volume":"36","author":"S Taylor","year":"2017","unstructured":"Taylor, S., et al.: A deep learning approach for generalized speech animation. ACM Trans. Graph. (TOG) 36(4), 93 (2017)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"44_CR56","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":"44_CR57","doi-asserted-by":"crossref","unstructured":"Tian, Y., Krishnan, D., Isola, P.: Contrastive multiview coding. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"44_CR58","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS, pp. 5998\u20136008 (2017)"},{"key":"44_CR59","unstructured":"Waite, E., et\u00a0al.: Generating long-term structure in songs and stories. Webblog Post. Magenta, vol. 15 (2016)"},{"key":"44_CR60","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":"44_CR61","doi-asserted-by":"crossref","unstructured":"Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition. In: AAAI (2018)","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"44_CR62","unstructured":"Yang, L.C., Chou, S.Y., Yang, Y.H.: MidiNet: a convolutional generative adversarial network for symbolic-domain music generation. arXiv preprint arXiv:1703.10847 (2017)"},{"key":"44_CR63","doi-asserted-by":"crossref","unstructured":"Zhao, H., Gan, C., Ma, W.C., Torralba, A.: The sound of motions. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00182"},{"key":"44_CR64","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":"44_CR65","doi-asserted-by":"crossref","unstructured":"Zhao, K., Li, S., Cai, J., Wang, H., Wang, J.: An emotional symbolic music generation system based on LSTM networks. In: 2019 IEEE 3rd Information Technology, Networking, Electronic and Automation Control Conference (ITNEC), pp. 2039\u20132043 (2019)","DOI":"10.1109\/ITNEC.2019.8729266"},{"key":"44_CR66","doi-asserted-by":"crossref","unstructured":"Zhou, H., Liu, Z., Xu, X., Luo, P., Wang, X.: Vision-infused deep audio inpainting. In: ICCV, pp. 283\u2013292 (2019)","DOI":"10.1109\/ICCV.2019.00037"},{"key":"44_CR67","doi-asserted-by":"crossref","unstructured":"Zhou, H., Xu, X., Lin, D., Wang, X., Liu, Z.: Sep-stereo: visually guided stereophonic audio generation by associating source separation. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58610-2_4"},{"key":"44_CR68","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Wang, Z., Fang, C., Bui, T., Berg, T.L.: Visual to sound: generating natural sound for videos in the wild. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00374"}],"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\/978-3-030-58621-8_44","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T00:15:46Z","timestamp":1732580146000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58621-8_44"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030586201","9783030586218"],"references-count":68,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58621-8_44","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":"27 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. From the ECCV Workshops 249 full papers, 18 short papers, and 21 further contributions were published out of a total of 467 submissions.","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)"}}]}}