{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T15:13:57Z","timestamp":1784301237292,"version":"3.55.0"},"publisher-location":"Cham","reference-count":60,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585884","type":"print"},{"value":"9783030585891","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\/978-3-030-58589-1_42","type":"book-chapter","created":{"date-parts":[[2020,11,11]],"date-time":"2020-11-11T06:18:04Z","timestamp":1605075484000},"page":"700-717","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":286,"title":["MEAD: A Large-Scale Audio-Visual Dataset for Emotional Talking-Face Generation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2120-8383","authenticated-orcid":false,"given":"Kaisiyuan","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8764-6178","authenticated-orcid":false,"given":"Qianyi","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0817-2600","authenticated-orcid":false,"given":"Linsen","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5410-8282","authenticated-orcid":false,"given":"Zhuoqian","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1364-8151","authenticated-orcid":false,"given":"Wayne","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8761-5563","authenticated-orcid":false,"given":"Chen","family":"Qian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3807-991X","authenticated-orcid":false,"given":"Ran","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1889-2567","authenticated-orcid":false,"given":"Yu","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5345-1591","authenticated-orcid":false,"given":"Chen Change","family":"Loy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,11,12]]},"reference":[{"issue":"6","key":"42_CR1","doi-asserted-by":"publisher","first-page":"EL523","DOI":"10.1121\/1.5042758","volume":"143","author":"N Alghamdi","year":"2018","unstructured":"Alghamdi, N., Maddock, S., Marxer, R., Barker, J., Brown, G.J.: A corpus of audio-visual Lombard speech with frontal and profile views. J. Acoust. Soc. Am. 143(6), EL523 (2018)","journal-title":"J. Acoust. Soc. Am."},{"key":"42_CR2","doi-asserted-by":"crossref","unstructured":"Anina, I., Zhou, Z., Zhao, G., Pietik\u00e4inen, M.: Ouluvs2: a multi-view audiovisual database for non-rigid mouth motion analysis. In: 2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG), vol. 1, pp. 1\u20135. IEEE (2015)","DOI":"10.1109\/FG.2015.7163155"},{"key":"42_CR3","doi-asserted-by":"crossref","unstructured":"Burkhardt, F., Paeschke, A., Rolfes, M., Sendlmeier, W.F., Weiss, B.: A database of German emotional speech. In: Ninth European Conference on Speech Communication and Technology (2005)","DOI":"10.21437\/Interspeech.2005-446"},{"issue":"4","key":"42_CR4","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1109\/TAFFC.2014.2336244","volume":"5","author":"H Cao","year":"2014","unstructured":"Cao, H., Cooper, D.G., Keutmann, M.K., Gur, R.C., Nenkova, A., Verma, R.: Crema-d: crowd-sourced emotional multimodal actors dataset. IEEE Trans. Affect. Comput. 5(4), 377\u2013390 (2014)","journal-title":"IEEE Trans. Affect. Comput."},{"issue":"4","key":"42_CR5","doi-asserted-by":"publisher","first-page":"1283","DOI":"10.1145\/1095878.1095881","volume":"24","author":"Y Cao","year":"2005","unstructured":"Cao, Y., Tien, W.C., Faloutsos, P., Pighin, F.: Expressive speech-driven facial animation. ACM Trans. Graph. (TOG) 24(4), 1283\u20131302 (2005)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"42_CR6","doi-asserted-by":"crossref","unstructured":"Chen, L., Maddox, R.K., Duan, Z., Xu, C.: Hierarchical cross-modal talking face generation with dynamic pixel-wise loss. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7832\u20137841 (2019)","DOI":"10.1109\/CVPR.2019.00802"},{"key":"42_CR7","doi-asserted-by":"crossref","unstructured":"Chung, J.S., Nagrani, A., Zisserman, A.: Voxceleb2: deep speaker recognition. In: INTERSPEECH (2018)","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"42_CR8","unstructured":"Chung, J.S., Jamaludin, A., Zisserman, A.: You said that? In: British Machine Vision Conference (2017)"},{"key":"42_CR9","doi-asserted-by":"publisher","first-page":"2421","DOI":"10.1121\/1.2229005","volume":"120","author":"M Cooke","year":"2006","unstructured":"Cooke, M., Cunningham, S., Shao, X.: An audio-visual corpus for speech perception and automatic speech recognition. J. Acoust. Soc. Am. 120, 2421 (2006)","journal-title":"J. Acoust. Soc. Am."},{"key":"42_CR10","volume-title":"Oxford Advanced Learner\u2019s Dictionary of Current English","author":"AP Cowie","year":"1992","unstructured":"Cowie, A.P., Gimson, A.: Oxford Advanced Learner\u2019s Dictionary of Current English. Oxford University Press, Oxford (1992)"},{"issue":"1","key":"42_CR11","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1109\/79.911197","volume":"18","author":"R Cowie","year":"2001","unstructured":"Cowie, R., et al.: Emotion recognition in human-computer interaction. IEEE Signal Process. Mag. 18(1), 32\u201380 (2001)","journal-title":"IEEE Signal Process. Mag."},{"key":"42_CR12","doi-asserted-by":"crossref","unstructured":"Ding, H., Sricharan, K., Chellappa, R.: Exprgan: facial expression editing with controllable expression intensity. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.12277"},{"issue":"4","key":"42_CR13","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1145\/2897824.2925984","volume":"35","author":"P Edwards","year":"2016","unstructured":"Edwards, P., Landreth, C., Fiume, E., Singh, K.: Jali: an animator-centric viseme model for expressive lip synchronization. ACM Trans. Graph. (TOG) 35(4), 127 (2016)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"42_CR14","doi-asserted-by":"crossref","unstructured":"Ezzat, T., Geiger, G., Poggio, T.: Trainable videorealistic speech animation, vol. 21. ACM (2002)","DOI":"10.1145\/566654.566594"},{"key":"42_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3306346.3323028","volume":"38","author":"O Fried","year":"2019","unstructured":"Fried, O., et al.: Text-based editing of talking-head video. ACM Trans. Graph. (TOG) 38, 1\u201314 (2019)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"42_CR16","unstructured":"Garofolo, J.S.: Timit acoustic phonetic continuous speech corpus. Linguistic Data Consortium (1993)"},{"issue":"5","key":"42_CR17","doi-asserted-by":"publisher","first-page":"603","DOI":"10.1109\/TMM.2015.2407694","volume":"17","author":"N Harte","year":"2015","unstructured":"Harte, N., Gillen, E.: Tcd-timit: an audio-visual corpus of continuous speech. IEEE Trans. Multimedia 17(5), 603\u2013615 (2015)","journal-title":"IEEE Trans. Multimedia"},{"key":"42_CR18","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"},{"issue":"4","key":"42_CR19","doi-asserted-by":"publisher","first-page":"3029","DOI":"10.1121\/1.4820893","volume":"134","author":"EW Healy","year":"2013","unstructured":"Healy, E.W., Yoho, S.E., Wang, Y., Wang, D.: An algorithm to improve speech recognition in noise for hearing-impaired listeners. J. Acoust. Soc. Am. 134(4), 3029\u20133038 (2013)","journal-title":"J. Acoust. Soc. Am."},{"key":"42_CR20","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: Gans trained by a two time-scale update rule converge to a local nash equilibrium. In: Advances in Neural Information Processing Systems, pp. 6626\u20136637 (2017)"},{"issue":"8","key":"42_CR21","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"42_CR22","doi-asserted-by":"crossref","unstructured":"Huang, X., Liu, M.Y., Belongie, S., Kautz, J.: Multimodal unsupervised image-to-image translation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 172\u2013189 (2018)","DOI":"10.1007\/978-3-030-01219-9_11"},{"key":"42_CR23","unstructured":"Jackson, P., Haq, S.: Surrey audio-visual expressed emotion (savee) database. http:\/\/kahlan.eps.surrey.ac.uk"},{"key":"42_CR24","doi-asserted-by":"crossref","unstructured":"Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46475-6_43"},{"issue":"4","key":"42_CR25","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":"42_CR26","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"42_CR27","unstructured":"Klautau, A.: Arpabet and the timit alphabet (2001)"},{"key":"42_CR28","unstructured":"Kossaifi, J., et al.: Sewa db: A rich database for audio-visual emotion and sentiment research in the wild. arXiv preprint arXiv:1901.02839 (2019)"},{"issue":"8","key":"42_CR29","doi-asserted-by":"publisher","first-page":"1377","DOI":"10.1080\/02699930903485076","volume":"24","author":"O Langner","year":"2010","unstructured":"Langner, O., Dotsch, R., Bijlstra, G., Wigboldus, D.H., Hawk, S.T., Van Knippenberg, A.: Presentation and validation of the radboud faces database. Cogn. Emot. 24(8), 1377\u20131388 (2010)","journal-title":"Cogn. Emot."},{"key":"42_CR30","doi-asserted-by":"crossref","unstructured":"Lee, H.Y., Tseng, H.Y., Huang, J.B., Singh, M., Yang, M.H.: Diverse image-to-image translation via disentangled representations. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 35\u201351 (2018)","DOI":"10.1007\/978-3-030-01246-5_3"},{"issue":"4","key":"42_CR31","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1002\/vis.4340020404","volume":"2","author":"J Lewis","year":"1991","unstructured":"Lewis, J.: Automated lip-sync: background and techniques. J. Vis. Comput. Animation 2(4), 118\u2013122 (1991)","journal-title":"J. Vis. Comput. Animation"},{"key":"42_CR32","doi-asserted-by":"publisher","first-page":"e0196391","DOI":"10.1371\/journal.pone.0196391","volume":"13","author":"ST Livingstone","year":"2018","unstructured":"Livingstone, S.T., Russo, F.A.: The ryerson audio-visual database of emotional speech and song (ravdess): a dynamic, multimodal set of facial and vocal expressions in north American English. PLoS One 13, e0196391 (2018)","journal-title":"PLoS One"},{"key":"42_CR33","doi-asserted-by":"crossref","unstructured":"Lucey, P., Cohn, J.F., Kanade, T., Saragih, J., Ambadar, Z., Matthews, I.: The extended cohn-kanade dataset (ck+): a complete dataset for action unit and emotion-specified expression. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition-Workshops, pp. 94\u2013101. IEEE (2010)","DOI":"10.1109\/CVPRW.2010.5543262"},{"key":"42_CR34","doi-asserted-by":"crossref","unstructured":"Mao, X., Li, Q., Xie, H., Lau, R.Y., Wang, Z., Paul Smolley, S.: Least squares generative adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2794\u20132802 (2017)","DOI":"10.1109\/ICCV.2017.304"},{"key":"42_CR35","doi-asserted-by":"crossref","unstructured":"Mariooryad, S., Busso, C.: Analysis and compensation of the reaction lag of evaluators in continuous emotional annotations. In: 2013 Humaine Association Conference on Affective Computing and Intelligent Interaction, pp. 85\u201390. IEEE (2013)","DOI":"10.1109\/ACII.2013.21"},{"key":"42_CR36","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1016\/j.specom.2014.11.001","volume":"66","author":"W Mattheyses","year":"2015","unstructured":"Mattheyses, W., Verhelst, W.: Audiovisual speech synthesis: an overview of the state-of-the-art. Speech Commun. 66, 182\u2013217 (2015)","journal-title":"Speech Commun."},{"key":"42_CR37","doi-asserted-by":"crossref","unstructured":"Meng, D., Peng, X., Wang, K., Qiao, Y.: frame attention networks for facial expression recognition in videos. In: 2019 IEEE International Conference on Image Processing (ICIP), pp. 3866\u20133870. IEEE (2019). https:\/\/github.com\/Open-Debin\/Emotion-FAN","DOI":"10.1109\/ICIP.2019.8803603"},{"issue":"1","key":"42_CR38","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/TAFFC.2017.2740923","volume":"10","author":"A Mollahosseini","year":"2017","unstructured":"Mollahosseini, A., Hasani, B., Mahoor, M.H.: Affectnet: a database for facial expression, valence, and arousal computing in the wild. IEEE Trans. Affect. Comput. 10(1), 18\u201331 (2017)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"42_CR39","doi-asserted-by":"crossref","unstructured":"Nagrani, A., Chung, J.S., Zisserman, A.: Voxceleb: a large-scale speaker identification dataset. In: INTERSPEECH (2017)","DOI":"10.21437\/Interspeech.2017-950"},{"key":"42_CR40","doi-asserted-by":"crossref","unstructured":"Narayanan, A., Wang, D.: Ideal ratio mask estimation using deep neural networks for robust speech recognition. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 7092\u20137096. IEEE (2013)","DOI":"10.1109\/ICASSP.2013.6639038"},{"key":"42_CR41","doi-asserted-by":"crossref","unstructured":"Petridis, S., Shen, J., Cetin, D., Pantic, M.: Visual-only recognition of normal, whispered and silent speech. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6219\u20136223. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8461596"},{"key":"42_CR42","doi-asserted-by":"crossref","unstructured":"Pumarola, A., Agudo, A., Martinez, A.M., Sanfeliu, A., Moreno-Noguer, F.: Ganimation: anatomically-aware facial animation from a single image. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 818\u2013833 (2018)","DOI":"10.1007\/978-3-030-01249-6_50"},{"key":"42_CR43","doi-asserted-by":"crossref","unstructured":"Qian, S., et al.: Make a face: towards arbitrary high fidelity face manipulation. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.01013"},{"key":"42_CR44","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"},{"issue":"6","key":"42_CR45","doi-asserted-by":"publisher","first-page":"1161","DOI":"10.1037\/h0077714","volume":"39","author":"JA Russell","year":"1980","unstructured":"Russell, J.A.: A circumplex model of affect. J. Pers. Soc. Psychol. 39(6), 1161 (1980)","journal-title":"J. Pers. Soc. Psychol."},{"key":"42_CR46","unstructured":"Sadoughi, N., Busso, C.: Speech-driven expressive talking lips with conditional sequential generative adversarial networks. IEEE Trans. Affect. Comput. (2019)"},{"key":"42_CR47","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"42_CR48","unstructured":"Song, L., Wu, W., Qian, C., Qian, C., Loy, C.C.: Everybody\u2019s talkin\u2019: let me talk as you want. arXiv preprint arXiv:2001.05201 (2020)"},{"key":"42_CR49","doi-asserted-by":"crossref","unstructured":"Song, Y., Zhu, J., Wang, X., Qi, H.: Talking face generation by conditional recurrent adversarial network. arXiv preprint arXiv:1804.04786 (2018)","DOI":"10.24963\/ijcai.2019\/129"},{"issue":"11","key":"42_CR50","doi-asserted-by":"publisher","first-page":"1486","DOI":"10.1016\/j.specom.2006.09.003","volume":"48","author":"S Srinivasan","year":"2006","unstructured":"Srinivasan, S., Roman, N., Wang, D.: Binary and ratio time-frequency masks for robust speech recognition. Speech Commun. 48(11), 1486\u20131501 (2006)","journal-title":"Speech Commun."},{"issue":"4","key":"42_CR51","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)"},{"key":"42_CR52","doi-asserted-by":"crossref","unstructured":"Vougioukas, K., Petridis, S., Pantic, M.: Realistic speech-driven facial animation with gans. Int. J. Comput. Vis., 1\u201316 (2019)","DOI":"10.1007\/s11263-019-01251-8"},{"key":"42_CR53","unstructured":"Wang, T.C., et al.: Video-to-video synthesis. In: NeurIPS (2018)"},{"issue":"4B","key":"42_CR54","doi-asserted-by":"publisher","first-page":"1238","DOI":"10.1121\/1.1913238","volume":"52","author":"CE Williams","year":"1972","unstructured":"Williams, C.E., Stevens, K.N.: Emotions and speech: some acoustical correlates. J. Acoust. Soc. Am. 52(4B), 1238\u20131250 (1972)","journal-title":"J. Acoust. Soc. Am."},{"key":"42_CR55","doi-asserted-by":"crossref","unstructured":"Wu, W., Cao, K., Li, C., Qian, C., Loy, C.C.: Transgaga: geometry-aware unsupervised image-to-image translation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00820"},{"key":"42_CR56","doi-asserted-by":"crossref","unstructured":"Wu, W., Qian, C., Yang, S., Wang, Q., Cai, Y., Zhou, Q.: Look at boundary: a boundary-aware face alignment algorithm. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2129\u20132138 (2018)","DOI":"10.1109\/CVPR.2018.00227"},{"key":"42_CR57","doi-asserted-by":"crossref","unstructured":"Zakharov, E., Shysheya, A., Burkov, E., Lempitsky, V.: Few-shot adversarial learning of realistic neural talking head models. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 9459\u20139468 (2019)","DOI":"10.1109\/ICCV.2019.00955"},{"key":"42_CR58","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: The Association for the Advancement of Artificial Intelligence Conference (2019)","DOI":"10.1609\/aaai.v33i01.33019299"},{"issue":"4","key":"42_CR59","first-page":"161","volume":"37","author":"Y Zhou","year":"2018","unstructured":"Zhou, Y., Xu, Z., Landreth, C., Kalogerakis, E., Maji, S., Singh, K.: Visemenet: audio-driven animator-centric speech animation. ACM Trans. Graph. (TOG) 37(4), 161 (2018)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"42_CR60","doi-asserted-by":"crossref","unstructured":"Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2223\u20132232 (2017)","DOI":"10.1109\/ICCV.2017.244"}],"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\/978-3-030-58589-1_42","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,11]],"date-time":"2024-11-11T00:25:15Z","timestamp":1731284715000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58589-1_42"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585884","9783030585891"],"references-count":60,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58589-1_42","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)"}}]}}