{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T16:20:18Z","timestamp":1785860418255,"version":"3.56.0"},"publisher-location":"Cham","reference-count":87,"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_45","type":"book-chapter","created":{"date-parts":[[2020,11,26]],"date-time":"2020-11-26T19:03:23Z","timestamp":1606417403000},"page":"776-794","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1224,"title":["Contrastive Multiview Coding"],"prefix":"10.1007","author":[{"given":"Yonglong","family":"Tian","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dilip","family":"Krishnan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Phillip","family":"Isola","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,11,27]]},"reference":[{"key":"45_CR1","unstructured":"Information Diagram - Wikipedia. https:\/\/en.wikipedia.org\/wiki\/Information_diagram"},{"key":"45_CR2","doi-asserted-by":"crossref","unstructured":"Agustsson, E., Timofte, R.: Ntire 2017 challenge on single image super-resolution: dataset and study. In: CVPR (2017)","DOI":"10.1109\/CVPRW.2017.150"},{"key":"45_CR3","unstructured":"Arora, S., Khandeparkar, H., Khodak, M., Plevrakis, O., Saunshi, N.: A theoretical analysis of contrastive unsupervised representation learning. In: ICML (2019)"},{"key":"45_CR4","unstructured":"Bachman, P., Hjelm, R.D., Buchwalter, W.: Learning representations by maximizing mutual information across views. arXiv preprint arXiv:1906.00910 (2019)"},{"key":"45_CR5","unstructured":"Belghazi, M.I., et al.: Mine: mutual information neural estimation. arXiv preprint arXiv:1801.04062 (2018)"},{"key":"45_CR6","unstructured":"Bellet, A., Habrard, A., Sebban, M.: Similarity learning for provably accurate sparse linear classification. arXiv preprint arXiv:1206.6476 (2012)"},{"key":"45_CR7","doi-asserted-by":"publisher","first-page":"1798","DOI":"10.1109\/TPAMI.2013.50","volume":"35","author":"Y Bengio","year":"2013","unstructured":"Bengio, Y., Courville, A., Vincent, P.: Representation learning: a review and new perspectives. TPAMI 35, 1798\u20131828 (2013)","journal-title":"TPAMI"},{"key":"45_CR8","doi-asserted-by":"crossref","unstructured":"Blum, A., Mitchell, T.: Combining labeled and unlabeled data with co-training. In: COLT. ACM (1998)","DOI":"10.1145\/279943.279962"},{"key":"45_CR9","doi-asserted-by":"crossref","unstructured":"Buchler, U., Brattoli, B., Ommer, B.: Improving spatiotemporal self-supervision by deep reinforcement learning. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01267-0_47"},{"key":"45_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1007\/978-3-030-01264-9_9","volume-title":"Computer Vision \u2013 ECCV 2018","author":"M Caron","year":"2018","unstructured":"Caron, M., Bojanowski, P., Joulin, A., Douze, M.: Deep clustering for unsupervised learning of visual features. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision \u2013 ECCV 2018. LNCS, vol. 11218, pp. 139\u2013156. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01264-9_9"},{"key":"45_CR11","unstructured":"Coates, A., Ng, A., Lee, H.: An analysis of single-layer networks in unsupervised feature learning. In: AISTATS (2011)"},{"key":"45_CR12","unstructured":"Cortes, C., Mohri, M., Rostamizadeh, A.: Learning non-linear combinations of kernels. In: NIPS (2009)"},{"key":"45_CR13","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Shlens, J., Le, Q.V.: Randaugment: practical data augmentation with no separate search. arXiv preprint arXiv:1909.13719 (2019)","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"45_CR14","doi-asserted-by":"crossref","first-page":"548","DOI":"10.3389\/fpsyg.2012.00548","volume":"3","author":"HE Den Ouden","year":"2012","unstructured":"Den Ouden, H.E., Kok, P., De Lange, F.P.: How prediction errors shape perception, attention, and motivation. Front. Psychol. 3, 548 (2012)","journal-title":"Front. Psychol."},{"key":"45_CR15","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"45_CR16","doi-asserted-by":"crossref","unstructured":"Doersch, C., Gupta, A., Efros, A.A.: Unsupervised visual representation learning by context prediction. In: CVPR (2015)","DOI":"10.1109\/ICCV.2015.167"},{"key":"45_CR17","unstructured":"Donahue, J., Kr\u00e4henb\u00fchl, P., Darrell, T.: Adversarial feature learning. In: ICLR (2017)"},{"key":"45_CR18","unstructured":"Donahue, J., Simonyan, K.: Large scale adversarial representation learning. In: NIPS (2019)"},{"key":"45_CR19","doi-asserted-by":"crossref","unstructured":"Eigen, D., Fergus, R.: Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.304"},{"key":"45_CR20","doi-asserted-by":"crossref","unstructured":"Gan, C., Gong, B., Liu, K., Su, H., Guibas, L.J.: Geometry guided convolutional neural networks for self-supervised video representation learning. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00586"},{"key":"45_CR21","unstructured":"Gidaris, S., Singh, P., Komodakis, N.: Unsupervised representation learning by predicting image rotations. In: ICLR (2018)"},{"key":"45_CR22","doi-asserted-by":"publisher","first-page":"2025Grave","DOI":"10.1016\/0166-2236(92)90344-8","volume":"15","author":"MA Goodale","year":"1992","unstructured":"Goodale, M.A., Milner, A.D.: Separate visual pathways for perception and action. Trends Neurosci. 15, 2025Grave (1992)","journal-title":"Trends Neurosci."},{"key":"45_CR23","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: NIPS (2014)"},{"key":"45_CR24","unstructured":"Gutmann, M., Hyv\u00e4rinen, A.: Noise-contrastive estimation: a new estimation principle for unnormalized statistical models. In: AISTATS (2010)"},{"key":"45_CR25","unstructured":"Hadsell, R., Chopra, S., LeCun, Y.: Dimensionality reduction by learning an invariant mapping. In: CVPR (2006)"},{"key":"45_CR26","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. arXiv preprint arXiv:1911.05722 (2019)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"45_CR27","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"45_CR28","unstructured":"H\u00e9naff, O.J., Razavi, A., Doersch, C., Eslami, S., Oord, A.V.D.: Data-efficient image recognition with contrastive predictive coding. arXiv preprint arXiv:1905.09272 (2019)"},{"key":"45_CR29","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1126\/science.1127647","volume":"313","author":"GE Hinton","year":"2006","unstructured":"Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 313, 504\u2013507 (2006)","journal-title":"Science"},{"key":"45_CR30","unstructured":"Hjelm, R.D., Fedorov, A., Lavoie-Marchildon, S., Grewal, K., Trischler, A., Bengio, Y.: Learning deep representations by mutual information estimation and maximization. In: ICLR (2019)"},{"key":"45_CR31","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780199682737.001.0001","volume-title":"The Predictive Mind","author":"J Hohwy","year":"2013","unstructured":"Hohwy, J.: The Predictive Mind. Oxford University Press, Oxford (2013)"},{"key":"45_CR32","volume-title":"Independent Component Analysis","author":"A Hyv\u00e4rinen","year":"2004","unstructured":"Hyv\u00e4rinen, A., Karhunen, J., Oja, E.: Independent Component Analysis, vol. 46. Wiley, Hoboken (2004)"},{"key":"45_CR33","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"45_CR34","unstructured":"Isola, P., Zoran, D., Krishnan, D., Adelson, E.H.: Learning visual groups from co-occurrences in space and time. arXiv preprint arXiv:1511.06811 (2015)"},{"key":"45_CR35","doi-asserted-by":"crossref","unstructured":"Ji, X., Henriques, J.F., Vedaldi, A.: Invariant information clustering for unsupervised image classification and segmentation. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00996"},{"key":"45_CR36","doi-asserted-by":"publisher","DOI":"10.1007\/b98835","volume-title":"Principal Component Analysis","author":"I Jolliffe","year":"2011","unstructured":"Jolliffe, I.: Principal Component Analysis. Springer, Heidelberg (2011). https:\/\/doi.org\/10.1007\/b98835"},{"key":"45_CR37","doi-asserted-by":"crossref","unstructured":"Kawakami, K., Wang, L., Dyer, C., Blunsom, P., Oord, A.V.D.: Learning robust and multilingual speech representations. arXiv preprint arXiv:2001.11128 (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.106"},{"key":"45_CR38","doi-asserted-by":"publisher","first-page":"e36399","DOI":"10.1371\/journal.pone.0036399","volume":"7","author":"C Kidd","year":"2012","unstructured":"Kidd, C., Piantadosi, S.T., Aslin, R.N.: The goldilocks effect: human infants allocate attention to visual sequences that are neither too simple nor too complex. PloS One 7, e36399 (2012)","journal-title":"PloS One"},{"key":"45_CR39","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"45_CR40","doi-asserted-by":"crossref","unstructured":"Kolesnikov, A., Zhai, X., Beyer, L.: Revisiting self-supervised visual representation learning. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00202"},{"key":"45_CR41","unstructured":"Kr\u00e4henb\u00fchl, P., Doersch, C., Donahue, J., Darrell, T.: Data-dependent initializations of convolutional neural networks. arXiv preprint arXiv:1511.06856 (2015)"},{"key":"45_CR42","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NIPS (2012)"},{"key":"45_CR43","doi-asserted-by":"crossref","unstructured":"Lee, H.Y., Huang, J.B., Singh, M., Yang, M.H.: Unsupervised representation learning by sorting sequences. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.79"},{"key":"45_CR44","first-page":"1863","volume":"31","author":"Y Li","year":"2018","unstructured":"Li, Y., Yang, M., Zhang, Z.M.: A survey of multi-view representation learning. TKDE 31, 1863\u20131883 (2018)","journal-title":"TKDE"},{"key":"45_CR45","doi-asserted-by":"crossref","unstructured":"Luo, Z., Peng, B., Huang, D.A., Alahi, A., Fei-Fei, L.: Unsupervised learning of long-term motion dynamics for videos. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.751"},{"key":"45_CR46","unstructured":"McAllester, D., Statos, K.: Formal limitations on the measurement of mutual information. arXiv preprint arXiv:1811.04251 (2018)"},{"key":"45_CR47","doi-asserted-by":"crossref","unstructured":"Miech, A., Alayrac, J.B., Smaira, L., Laptev, I., Sivic, J., Zisserman, A.: End-to-end learning of visual representations from uncurated instructional videos. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"45_CR48","doi-asserted-by":"crossref","unstructured":"Misra, I., van der Maaten, L.: Self-supervised learning of pretext-invariant representations. arXiv preprint arXiv:1912.01991 (2019)","DOI":"10.1109\/CVPR42600.2020.00674"},{"key":"45_CR49","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"527","DOI":"10.1007\/978-3-319-46448-0_32","volume-title":"Computer Vision \u2013 ECCV 2016","author":"I Misra","year":"2016","unstructured":"Misra, I., Zitnick, C.L., Hebert, M.: Shuffle and learn: unsupervised learning using temporal order verification. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 527\u2013544. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_32"},{"key":"45_CR50","unstructured":"Mnih, A., Kavukcuoglu, K.: Learning word embeddings efficiently with noise-contrastive estimation. In: NIPS (2013)"},{"key":"45_CR51","doi-asserted-by":"crossref","unstructured":"Mobahi, H., Collobert, R., Weston, J.: Deep learning from temporal coherence in video. In: ICML (2009)","DOI":"10.1145\/1553374.1553469"},{"key":"45_CR52","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1007\/978-3-642-33715-4_54","volume-title":"Computer Vision \u2013 ECCV 2012","author":"N Silberman","year":"2012","unstructured":"Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from RGBD images. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7576, pp. 746\u2013760. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33715-4_54"},{"key":"45_CR53","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/978-3-319-46466-4_5","volume-title":"Computer Vision \u2013 ECCV 2016","author":"M Noroozi","year":"2016","unstructured":"Noroozi, M., Favaro, P.: Unsupervised learning of visual representations by solving jigsaw puzzles. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 69\u201384. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46466-4_5"},{"key":"45_CR54","doi-asserted-by":"crossref","unstructured":"Noroozi, M., Pirsiavash, H., Favaro, P.: Representation learning by learning to count. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.628"},{"key":"45_CR55","unstructured":"Oord, A.V.D., Kalchbrenner, N., Kavukcuoglu, K.: Pixel recurrent neural networks. arXiv preprint arXiv:1601.06759 (2016)"},{"key":"45_CR56","unstructured":"Oord, A.V.D., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"45_CR57","doi-asserted-by":"crossref","unstructured":"Owens, A., Isola, P., McDermott, J., Torralba, A., Adelson, E.H., Freeman, W.T.: Visually indicated sounds. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.264"},{"key":"45_CR58","unstructured":"Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: NIPS (2019)"},{"key":"45_CR59","doi-asserted-by":"crossref","unstructured":"Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., Efros, A.A.: Context encoders: feature learning by inpainting. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.278"},{"key":"45_CR60","doi-asserted-by":"crossref","unstructured":"Piergiovanni, A., Angelova, A., Ryoo, M.S.: Evolving losses for unlabeled video representation learning. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00021"},{"key":"45_CR61","unstructured":"Poole, B., Ozair, S., Oord, A.V.D., Alemi, A.A., Tucker, G.: On variational bounds of mutual information. In: ICML (2019)"},{"key":"45_CR62","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":"45_CR63","unstructured":"Sa, V.: Sensory modality segregation. In: NIPS (2004)"},{"key":"45_CR64","unstructured":"Salakhutdinov, R., Hinton, G.: Deep Boltzmann machines. In: AISTATS (2009)"},{"key":"45_CR65","doi-asserted-by":"crossref","unstructured":"Sayed, N., Brattoli, B., Ommer, B.: Cross and learn: cross-modal self-supervision. arXiv preprint arXiv:1811.03879 (2018)","DOI":"10.1007\/978-3-030-12939-2_17"},{"key":"45_CR66","doi-asserted-by":"publisher","first-page":"895","DOI":"10.1126\/science.163.3870.895","volume":"163","author":"GE Schneider","year":"1969","unstructured":"Schneider, G.E.: Two visual systems. Science 163, 895\u2013902 (1969)","journal-title":"Science"},{"key":"45_CR67","doi-asserted-by":"crossref","unstructured":"Sermanet, P., et al.: Time-contrastive networks: self-supervised learning from video. In: ICRA (2018)","DOI":"10.1109\/CVPRW.2017.69"},{"key":"45_CR68","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: NIPS (2014)"},{"key":"45_CR69","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1162\/1064546053278973","volume":"11","author":"L Smith","year":"2005","unstructured":"Smith, L., Gasser, M.: The development of embodied cognition: six lessons from babies. Artif. Life 11, 13\u201329 (2005)","journal-title":"Artif. Life"},{"key":"45_CR70","unstructured":"Smolensky, P.: Information processing in dynamical systems: foundations of harmony theory. Tech. rep., Colorado University at Boulder Department of Computer Science (1986)"},{"key":"45_CR71","unstructured":"Sohn, K.: Improved deep metric learning with multi-class n-pair loss objective. In: NIPS (2016)"},{"key":"45_CR72","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: Ucf101: a dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)"},{"key":"45_CR73","unstructured":"Sun, C., Baradel, F., Murphy, K., Schmid, C.: Contrastive bidirectional transformer for temporal representation learning. arXiv preprint arXiv:1906.05743 (2019)"},{"key":"45_CR74","unstructured":"Tian, Y., Krishnan, D., Isola, P.: Contrastive representation distillation. In: ICLR (2020)"},{"key":"45_CR75","unstructured":"Tian, Y., Sun, C., Poole, B., Krishnan, D., Schmid, C., Isola, P.: What makes for good views for contrastive learning. arXiv preprint arXiv:2005.10243 (2020)"},{"key":"45_CR76","doi-asserted-by":"crossref","unstructured":"Tschannen, M., et al.: Self-supervised learning of video-induced visual invariances. arXiv preprint arXiv:1912.02783 (2019)","DOI":"10.1109\/CVPR42600.2020.01382"},{"key":"45_CR77","unstructured":"Vondrick, C., Pirsiavash, H., Torralba, A.: Generating videos with scene dynamics. In: NIPS (2016)"},{"key":"45_CR78","doi-asserted-by":"crossref","unstructured":"Wang, X., Gupta, A.: Unsupervised learning of visual representations using videos. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.320"},{"key":"45_CR79","doi-asserted-by":"crossref","unstructured":"Wu, Z., Xiong, Y., Yu, S.X., Lin, D.: Unsupervised feature learning via non-parametric instance discrimination. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00393"},{"key":"45_CR80","unstructured":"Xu, C., Tao, D., Xu, C.: A survey on multi-view learning. arXiv preprint arXiv:1304.5634 (2013)"},{"key":"45_CR81","doi-asserted-by":"crossref","unstructured":"Ye, M., Zhang, X., Yuen, P.C., Chang, S.F.: Unsupervised embedding learning via invariant and spreading instance feature. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00637"},{"key":"45_CR82","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1007\/978-3-540-74936-3_22","volume-title":"Pattern Recognition","author":"C Zach","year":"2007","unstructured":"Zach, C., Pock, T., Bischof, H.: A duality based approach for realtime TV-L1 optical flow. In: Hamprecht, F.A., Schn\u00f6rr, C., J\u00e4hne, B. (eds.) DAGM 2007. LNCS, vol. 4713, pp. 214\u2013223. Springer, Heidelberg (2007). https:\/\/doi.org\/10.1007\/978-3-540-74936-3_22"},{"key":"45_CR83","doi-asserted-by":"crossref","unstructured":"Zhang, L., Qi, G.J., Wang, L., Luo, J.: AET vs. AED: unsupervised representation learning by auto-encoding transformations rather than data. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00265"},{"key":"45_CR84","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1007\/978-3-319-46487-9_40","volume-title":"Computer Vision \u2013 ECCV 2016","author":"R Zhang","year":"2016","unstructured":"Zhang, R., Isola, P., Efros, A.A.: Colorful image colorization. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 649\u2013666. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_40"},{"key":"45_CR85","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A.: Split-brain autoencoders: unsupervised learning by cross-channel prediction. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.76"},{"key":"45_CR86","doi-asserted-by":"crossref","unstructured":"Zhuang, C., Andonian, A., Yamins, D.: Unsupervised learning from video with deep neural embeddings. arXiv preprint arXiv:1905.11954 (2019)","DOI":"10.1109\/CVPR42600.2020.00958"},{"key":"45_CR87","doi-asserted-by":"crossref","unstructured":"Zhuang, C., Zhai, A.L., Yamins, D.: Local aggregation for unsupervised learning of visual embeddings. arXiv preprint arXiv:1903.12355 (2019)","DOI":"10.1109\/ICCV.2019.00610"}],"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_45","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T00:16:10Z","timestamp":1732580170000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58621-8_45"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030586201","9783030586218"],"references-count":87,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58621-8_45","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)"}}]}}