{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T04:05:27Z","timestamp":1778299527399,"version":"3.51.4"},"publisher-location":"Cham","reference-count":82,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031198359","type":"print"},{"value":"9783031198366","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-19836-6_20","type":"book-chapter","created":{"date-parts":[[2022,10,21]],"date-time":"2022-10-21T09:04:58Z","timestamp":1666343098000},"page":"348-367","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":215,"title":["MultiMAE: Multi-modal Multi-task Masked Autoencoders"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5324-2474","authenticated-orcid":false,"given":"Roman","family":"Bachmann","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7973-444X","authenticated-orcid":false,"given":"David","family":"Mizrahi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5293-4807","authenticated-orcid":false,"given":"Andrei","family":"Atanov","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5559-1843","authenticated-orcid":false,"given":"Amir","family":"Zamir","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,10,22]]},"reference":[{"key":"20_CR1","unstructured":"Ahmed, S.A.A., Awais, M., Kittler, J.: Sit: Self-supervised vision transformer. ArXiv abs\/2104.03602 (2021)"},{"key":"20_CR2","first-page":"24206","volume":"34","author":"H Akbari","year":"2021","unstructured":"Akbari, H., et al.: Vatt: transformers for multimodal self-supervised learning from raw video, audio and text. Adv. Neural Inf. Process. Syst. 34, 24206\u201324221 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"20_CR3","first-page":"25","volume":"33","author":"JB Alayrac","year":"2020","unstructured":"Alayrac, J.B.: Self-supervised multimodal versatile networks. Adv. Neural Inf. Process. Syst. 33, 25\u201337 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"20_CR4","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":"20_CR5","unstructured":"Atito, S., Awais, M., Kittler, J.: Sit: self-supervised vision transformer. arXiv preprint arXiv:2104.03602 (2021)"},{"key":"20_CR6","unstructured":"Baevski, A., Hsu, W.N., Xu, Q., Babu, A., Gu, J., Auli, M.: Data2vec: a general framework for self-supervised learning in speech, vision and language. arXiv preprint arXiv:2202.03555 (2022)"},{"key":"20_CR7","unstructured":"Bao, H., Dong, L., Wei, F.: Beit: Bert pre-training of image transformers. ArXiv abs\/2106.08254 (2021)"},{"key":"20_CR8","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1613\/jair.731","volume":"12","author":"J Baxter","year":"2000","unstructured":"Baxter, J.: A model of inductive bias learning. J. Artif. Intell. Res. 12, 149\u2013198 (2000)","journal-title":"J. Artif. Intell. Res."},{"key":"20_CR9","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9630\u20139640 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"issue":"1","key":"20_CR10","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1023\/A:1007379606734","volume":"28","author":"R Caruana","year":"1997","unstructured":"Caruana, R.: Multitask learning. Mach. Learn. 28(1), 41\u201375 (1997). https:\/\/doi.org\/10.1023\/A:1007379606734. Jul","journal-title":"Mach. Learn."},{"key":"20_CR11","doi-asserted-by":"crossref","unstructured":"Castrejon, L., Aytar, Y., Vondrick, C., Pirsiavash, H., Torralba, A.: Learning aligned cross-modal representations from weakly aligned data. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2940\u20132949 (2016)","DOI":"10.1109\/CVPR.2016.321"},{"key":"20_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"695","DOI":"10.1007\/978-3-030-58545-7_40","volume-title":"Computer Vision \u2013 ECCV 2020","author":"L-C Chen","year":"2020","unstructured":"Chen, L.-C., et al.: Naive-student: leveraging semi-supervised learning in video sequences for urban scene segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 695\u2013714. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58545-7_40"},{"key":"20_CR13","unstructured":"Chen, M., et al.: Generative pretraining from pixels. In: Proceedings of the 37th International Conference on Machine Learning, pp. 1691\u20131703. PMLR (2020). iSSN: 2640\u20133498"},{"key":"20_CR14","doi-asserted-by":"crossref","unstructured":"Chen, X., Xie, S., He, K.: An empirical study of training self-supervised vision transformers. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9620\u20139629 (2021)","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"20_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1007\/978-3-030-58577-8_7","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y-C Chen","year":"2020","unstructured":"Chen, Y.-C., et al.: UNITER: UNiversal image-TExt representation learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 104\u2013120. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_7"},{"key":"20_CR16","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation. ArXiv abs\/2112.01527 (2021)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"20_CR17","unstructured":"De Sa, V.R.: Sensory modality segregation. In: NIPS, pp. 913\u2013920. Citeseer (2003)"},{"issue":"5","key":"20_CR18","doi-asserted-by":"publisher","first-page":"1097","DOI":"10.1162\/089976698300017368","volume":"10","author":"VR De Sa","year":"1998","unstructured":"De Sa, V.R., Ballard, D.H.: Category learning through multimodality sensing. Neural Comput. 10(5), 1097\u20131117 (1998)","journal-title":"Neural Comput."},{"key":"20_CR19","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":"20_CR20","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"20_CR21","doi-asserted-by":"crossref","unstructured":"Doersch, C., Zisserman, A.: Multi-task self-supervised visual learning. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2051\u20132060 (2017)","DOI":"10.1109\/ICCV.2017.226"},{"key":"20_CR22","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. ArXiv abs\/2010.11929 (2021)"},{"key":"20_CR23","doi-asserted-by":"crossref","unstructured":"Eftekhar, A., Sax, A., Bachmann, R., Malik, J., Zamir, A.R.: Omnidata: a scalable pipeline for making multi-task mid-level vision datasets from 3D scans. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 10766\u201310776 (2021)","DOI":"10.1109\/ICCV48922.2021.01061"},{"key":"20_CR24","doi-asserted-by":"crossref","unstructured":"Eigen, D., Fergus, R.: Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2650\u20132658 (2015)","DOI":"10.1109\/ICCV.2015.304"},{"key":"20_CR25","unstructured":"El-Nouby, A., Izacard, G., Touvron, H., Laptev, I., Jegou, H., Grave, E.: Are large-scale datasets necessary for self-supervised pre-training? arXiv preprint arXiv:2112.10740 (2021)"},{"key":"20_CR26","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Zoph, B., Cubuk, E.D., Le, Q.V., Lin, T.Y.: Multi-task self-training for learning general representations. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 8836\u20138845 (2021)","DOI":"10.1109\/ICCV48922.2021.00873"},{"key":"20_CR27","doi-asserted-by":"crossref","unstructured":"Girdhar, R., Singh, M., Ravi, N., van der Maaten, L., Joulin, A., Misra, I.: Omnivore: a single model for many visual modalities. arXiv preprint arXiv:2201.08377 (2022)","DOI":"10.1109\/CVPR52688.2022.01563"},{"key":"20_CR28","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u2019ar, P., Girshick, R.B.: Masked autoencoders are scalable vision learners. ArXiv abs\/2111.06377 (2021)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"20_CR29","doi-asserted-by":"crossref","unstructured":"Hu, R., Singh, A.: Unit: multimodal multitask learning with a unified transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1439\u20131449 (2021)","DOI":"10.1109\/ICCV48922.2021.00147"},{"key":"20_CR30","unstructured":"Jaegle, A., et al.: Perceiver io: a general architecture for structured inputs & outputs. arXiv preprint arXiv:2107.14795 (2021)"},{"key":"20_CR31","unstructured":"Kaiser, L., et al.: One model to learn them all. arXiv preprint arXiv:1706.05137 (2017)"},{"key":"20_CR32","doi-asserted-by":"crossref","unstructured":"Kamath, A., Singh, M., LeCun, Y., Synnaeve, G., Misra, I., Carion, N.: Mdetr-modulated detection for end-to-end multi-modal understanding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1780\u20131790 (2021)","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"20_CR33","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3128\u20133137 (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"20_CR34","unstructured":"Kim, W., Son, B., Kim, I.: Vilt: vision-and-language transformer without convolution or region supervision. In: International Conference on Machine Learning, pp. 5583\u20135594. PMLR (2021)"},{"key":"20_CR35","doi-asserted-by":"crossref","unstructured":"Kokkinos, I.: Ubernet: training a universal convolutional neural network for low-, mid-, and high-level vision using diverse datasets and limited memory. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6129\u20136138 (2017)","DOI":"10.1109\/CVPR.2017.579"},{"key":"20_CR36","unstructured":"Lee, D.H., et al.: Pseudo-label: the simple and efficient semi-supervised learning method for deep neural networks. In: Workshop on Challenges in Representation Learning. ICML (2013)"},{"key":"20_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"20_CR38","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"20_CR39","unstructured":"Loshchilov, I., Hutter, F.: Sgdr: stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983 (2016)"},{"key":"20_CR40","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2019)"},{"key":"20_CR41","first-page":"1","volume":"32","author":"J Lu","year":"2019","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: Vilbert: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Adv. Neural Inf. Process. Syst. 32, 1\u201311 (2019)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"20_CR42","doi-asserted-by":"crossref","unstructured":"Lu, J., Goswami, V., Rohrbach, M., Parikh, D., Lee, S.: 12-in-1: multi-task vision and language representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10437\u201310446 (2020)","DOI":"10.1109\/CVPR42600.2020.01045"},{"key":"20_CR43","doi-asserted-by":"crossref","unstructured":"Mensink, T., Uijlings, J.R.R., Kuznetsova, A., Gygli, M., Ferrari, V.: Factors of influence for transfer learning across diverse appearance domains and task types. IEEE Trans. Pattern Anal. Mach. Intell. (2021)","DOI":"10.1109\/TPAMI.2021.3129870"},{"key":"20_CR44","first-page":"14200","volume":"34","author":"A Nagrani","year":"2021","unstructured":"Nagrani, A., Yang, S., Arnab, A., Jansen, A., Schmid, C., Sun, C.: Attention bottlenecks for multimodal fusion. Adv. Neural Inf. Process. Syst. 34, 14200\u201314213 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"20_CR45","unstructured":"Ngiam, J., Khosla, A., Kim, M., Nam, J., Lee, H., Ng, A.: Multimodal deep learning. In: ICML (2011)"},{"key":"20_CR46","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":"20_CR47","unstructured":"Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: NeurIPS (2019)"},{"key":"20_CR48","doi-asserted-by":"crossref","unstructured":"Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., Efros, A.A.: Context encoders: feature learning by inpainting. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2536\u20132544 (2016)","DOI":"10.1109\/CVPR.2016.278"},{"key":"20_CR49","doi-asserted-by":"crossref","unstructured":"Pham, H., Dai, Z., Xie, Q., Le, Q.V.: Meta pseudo labels. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11557\u201311568 (2021)","DOI":"10.1109\/CVPR46437.2021.01139"},{"key":"20_CR50","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Bochkovskiy, A., Koltun, V.: Vision transformers for dense prediction. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 12159\u201312168 (2021)","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"20_CR51","doi-asserted-by":"publisher","first-page":"1623","DOI":"10.1109\/TPAMI.2020.3019967","volume":"44","author":"R Ranftl","year":"2022","unstructured":"Ranftl, R., Lasinger, K., Hafner, D., Schindler, K., Koltun, V.: Towards robust monocular depth estimation: mixing datasets for zero-shot cross-dataset transfer. IEEE Trans. Pattern Anal. Mach. Intell. 44, 1623\u20131637 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"20_CR52","doi-asserted-by":"crossref","unstructured":"Roberts, M., Paczan, N.: Hypersim: a photorealistic synthetic dataset for holistic indoor scene understanding. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 10892\u201310902 (2021)","DOI":"10.1109\/ICCV48922.2021.01073"},{"key":"20_CR53","doi-asserted-by":"crossref","unstructured":"Rosenberg, C., Hebert, M., Schneiderman, H.: Semi-supervised self-training of object detection models. In: IEEE Workshops on Applications of Computer Vision (WACV\/MOTION 2005) (2005)","DOI":"10.1109\/ACVMOT.2005.107"},{"key":"20_CR54","unstructured":"Sax, A., Emi, B., Zamir, A.R., Guibas, L.J., Savarese, S., Malik, J.: Mid-level visual representations improve generalization and sample efficiency for learning visuomotor policies. (2018)"},{"issue":"3","key":"20_CR55","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1109\/TIT.1965.1053799","volume":"11","author":"H Scudder","year":"1965","unstructured":"Scudder, H.: Probability of error of some adaptive pattern-recognition machines. IEEE Trans. Inf. Theory 11(3), 363\u2013371 (1965)","journal-title":"IEEE Trans. Inf. Theory"},{"key":"20_CR56","unstructured":"Shi, Y., Siddharth, N., Paige, B., Torr, P.H.S.: Variational mixture-of-experts autoencoders for multi-modal deep generative models. ArXiv abs\/1911.03393 (2019)"},{"key":"20_CR57","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"},{"issue":"1\u20132","key":"20_CR58","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(1\u20132), 13\u201329 (2005)","journal-title":"Artif. Life"},{"key":"20_CR59","unstructured":"Su, W., et al.: Vl-bert: pre-training of generic visual-linguistic representations. arXiv preprint arXiv:1908.08530 (2019)"},{"key":"20_CR60","unstructured":"Sutter, T.M., Daunhawer, I., Vogt, J.E.: Multimodal generative learning utilizing jensen-shannon-divergence. ArXiv abs\/2006.08242 (2019)"},{"key":"20_CR61","unstructured":"Sutter, T.M., Daunhawer, I., Vogt, J.E.: Generalized multimodal ELBO. CoRR abs\/2105.02470 (2021). https:\/\/arxiv.org\/abs\/2105.02470"},{"key":"20_CR62","doi-asserted-by":"crossref","unstructured":"Tan, H., Bansal, M.: Lxmert: learning cross-modality encoder representations from transformers. arXiv preprint arXiv:1908.07490 (2019)","DOI":"10.18653\/v1\/D19-1514"},{"key":"20_CR63","doi-asserted-by":"crossref","unstructured":"Tian, Y., Wang, Y., Krishnan, D., Tenenbaum, J.B., Isola, P.: Rethinking few-shot image classification: a good embedding is all you need? ArXiv abs\/2003.11539 (2020)","DOI":"10.1007\/978-3-030-58568-6_16"},{"key":"20_CR64","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u2019egou, H.: Training data-efficient image transformers & distillation through attention. In: ICML (2021)"},{"key":"20_CR65","first-page":"7852","volume":"33","author":"N Tripuraneni","year":"2020","unstructured":"Tripuraneni, N., Jordan, M., Jin, C.: On the theory of transfer learning: the importance of task diversity. Adv. Neural Inf. Process. Syst. 33, 7852\u20137862 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"20_CR66","unstructured":"Tripuraneni, N., Jordan, M.I., Jin, C.: On the theory of transfer learning: the importance of task diversity. ArXiv abs\/2006.11650 (2020)"},{"key":"20_CR67","doi-asserted-by":"crossref","unstructured":"Vandenhende, S., Georgoulis, S., Van Gansbeke, W., Proesmans, M., Dai, D., Van Gool, L.: Multi-task learning for dense prediction tasks: a survey. IEEE Trans. Pattern Anal. Mach. Intell. (2021)","DOI":"10.1109\/TPAMI.2021.3054719"},{"key":"20_CR68","unstructured":"Vaswani, A., et al.: Attention is all you need. ArXiv abs\/1706.03762 (2017)"},{"key":"20_CR69","unstructured":"Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., Manzagol, P.A.: Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. J. Mach. Learn. Res. 11(110), 3371\u20133408 (2010). http:\/\/jmlr.org\/papers\/v11\/vincent10a.html"},{"key":"20_CR70","doi-asserted-by":"crossref","unstructured":"Wei, C., Fan, H., Xie, S., Wu, C.Y., Yuille, A., Feichtenhofer, C.: Masked feature prediction for self-supervised visual pre-training. arXiv preprint arXiv:2112.09133 (2021)","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"20_CR71","unstructured":"Wu, M., Goodman, N.D.: Multimodal generative models for scalable weakly-supervised learning. In: NeurIPS (2018)"},{"key":"20_CR72","unstructured":"Xiao, T., Radosavovic, I., Darrell, T., Malik, J.: Masked visual pre-training for motor control. arXiv preprint arXiv:2203.06173 (2022)"},{"key":"20_CR73","doi-asserted-by":"crossref","unstructured":"Xie, Q., Luong, M.T., Hovy, E., Le, Q.V.: Self-training with noisy student improves imagenet classification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10687\u201310698 (2020)","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"20_CR74","doi-asserted-by":"crossref","unstructured":"Xie, Z., et al.: Simmim: a simple framework for masked image modeling. ArXiv abs\/2111.09886 (2021)","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"20_CR75","doi-asserted-by":"crossref","unstructured":"Xu, H., et al.: E2e-vlp: end-to-end vision-language pre-training enhanced by visual learning. arXiv preprint arXiv:2106.01804 (2021)","DOI":"10.18653\/v1\/2021.acl-long.42"},{"key":"20_CR76","unstructured":"Yalniz, I.Z., J\u00e9gou, H., Chen, K., Paluri, M., Mahajan, D.: Billion-scale semi-supervised learning for image classification. arXiv preprint arXiv:1905.00546 (2019)"},{"key":"20_CR77","doi-asserted-by":"crossref","unstructured":"Yarowsky, D.: Unsupervised word sense disambiguation rivaling supervised methods. In: ACL (1995)","DOI":"10.3115\/981658.981684"},{"key":"20_CR78","doi-asserted-by":"crossref","unstructured":"Yin, W., et al.: Learning to recover 3D scene shape from a single image. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 204\u2013213 (2021)","DOI":"10.1109\/CVPR46437.2021.00027"},{"key":"20_CR79","doi-asserted-by":"crossref","unstructured":"Zamir, A.R., Sax, A., Shen, W.B., Guibas, L.J., Malik, J., Savarese, S.: Taskonomy: disentangling task transfer learning. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE (2018)","DOI":"10.24963\/ijcai.2019\/871"},{"key":"20_CR80","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ade20k dataset. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5122\u20135130 (2017)","DOI":"10.1109\/CVPR.2017.544"},{"key":"20_CR81","unstructured":"Zhou, J., et al.: ibot: image bert pre-training with online tokenizer. arXiv preprint arXiv:2111.07832 (2021)"},{"key":"20_CR82","first-page":"3833","volume":"33","author":"B Zoph","year":"2020","unstructured":"Zoph, B., et al.: Rethinking pre-training and self-training. Adv. Neural Inf. Process. Syst. 33, 3833\u20133845 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19836-6_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,24]],"date-time":"2022-10-24T23:09:04Z","timestamp":1666652944000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19836-6_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198359","9783031198366"],"references-count":82,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19836-6_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"22 October 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","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":"1645","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":"28% - 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":"3.21","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":"3.91","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)"}}]}}