{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:09:55Z","timestamp":1778080195247,"version":"3.51.4"},"publisher-location":"Cham","reference-count":72,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031733895","type":"print"},{"value":"9783031733901","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-73390-1_11","type":"book-chapter","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T16:24:01Z","timestamp":1730305441000},"page":"180-197","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["SeiT++: Masked Token Modeling Improves Storage-Efficient Training"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-2641-7990","authenticated-orcid":false,"given":"Minhyun","family":"Lee","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4332-9733","authenticated-orcid":false,"given":"Song","family":"Park","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2134-6345","authenticated-orcid":false,"given":"Byeongho","family":"Heo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9130-8195","authenticated-orcid":false,"given":"Dongyoon","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6796-1058","authenticated-orcid":false,"given":"Hyunjung","family":"Shim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,31]]},"reference":[{"key":"11_CR1","unstructured":"Bahng, H., Chun, S., Yun, S., Choo, J., Oh, S.J.: Learning de-biased representations with biased representations. In: International Conference on Machine Learning, pp. 528\u2013539. PMLR (2020)"},{"key":"11_CR2","unstructured":"Bao, H., Dong, L., Piao, S., Wei, F.: Beit: Bert pre-training of image transformers. arXiv preprint arXiv:2106.08254 (2021)"},{"key":"11_CR3","unstructured":"Barbu, A., et al.: Objectnet: a large-scale bias-controlled dataset for pushing the limits of object recognition models. Adv. Neural Inform. Process. Syst. 32 (2019)"},{"key":"11_CR4","unstructured":"Chang, H., et\u00a0al.: Muse: Text-to-image generation via masked generative transformers. arXiv preprint arXiv:2301.00704 (2023)"},{"key":"11_CR5","doi-asserted-by":"crossref","unstructured":"Chang, H., Zhang, H., Jiang, L., Liu, C., Freeman, W.T.: Maskgit: masked generative image transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11315\u201311325 (2022)","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"11_CR6","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597\u20131607. PMLR (2020)"},{"key":"11_CR7","doi-asserted-by":"crossref","unstructured":"Chen, X., Xie, S., He, K.: An empirical study of training self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9640\u20139649 (2021)","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"11_CR8","unstructured":"Chun, S., Oh, S.J., Yun, S., Han, D., Choe, J., Yoo, Y.: An empirical evaluation on robustness and uncertainty of regularization methods. arXiv preprint arXiv:2003.03879 (2020)"},{"key":"11_CR9","unstructured":"Coleman, C., et al.: Selection via proxy: Efficient data selection for deep learning. arXiv preprint arXiv:1906.11829 (2019)"},{"key":"11_CR10","unstructured":"Contributors, M.: MMSegmentation: Openmmlab semantic segmentation toolbox and benchmark (2020). https:\/\/github.com\/open-mmlab\/mmsegmentation"},{"key":"11_CR11","unstructured":"Croce, F., Hein, M.: Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks. In: International Conference on Machine Learning, pp. 2206\u20132216. PMLR (2020)"},{"key":"11_CR12","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Mane, D., Vasudevan, V., Le, Q.V.: Autoaugment: learning augmentation strategies from data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 113\u2013123 (2019)","DOI":"10.1109\/CVPR.2019.00020"},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Shlens, J., Le, Q.V.: Randaugment: practical automated data augmentation with a reduced search space. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 702\u2013703 (2020)","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"11_CR14","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: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"11_CR15","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":"11_CR16","unstructured":"DeVries, T., Taylor, G.W.: Improved regularization of convolutional neural networks with cutout. arXiv preprint arXiv:1708.04552 (2017)"},{"key":"11_CR17","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"11_CR18","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12873\u201312883 (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"11_CR19","unstructured":"Fang, Y., Dong, L., Bao, H., Wang, X., Wei, F.: Corrupted image modeling for self-supervised visual pre-training. arXiv preprint arXiv:2202.03382 (2022)"},{"key":"11_CR20","unstructured":"Ford, N., Gilmer, J., Carlini, N., Cubuk, D.: Adversarial examples are a natural consequence of test error in noise. arXiv preprint arXiv:1901.10513 (2019)"},{"key":"11_CR21","unstructured":"Geirhos, R., Rubisch, P., Michaelis, C., Bethge, M., Wichmann, F.A., Brendel, W.: Imagenet-trained cnns are biased towards texture; increasing shape bias improves accuracy and robustness. arXiv preprint arXiv:1811.12231 (2018)"},{"key":"11_CR22","unstructured":"Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)"},{"key":"11_CR23","first-page":"21271","volume":"33","author":"JB Grill","year":"2020","unstructured":"Grill, J.B., et al.: Bootstrap your own latent-a new approach to self-supervised learning. Adv. Neural. Inf. Process. Syst. 33, 21271\u201321284 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR24","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"11_CR25","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., et al.: The many faces of robustness: A critical analysis of out-of-distribution generalization. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"11_CR26","unstructured":"Hendrycks, D., Dietterich, T.: Benchmarking neural network robustness to common corruptions and perturbations. arXiv preprint arXiv:1903.12261 (2019)"},{"key":"11_CR27","doi-asserted-by":"crossref","unstructured":"Huang, X., Belongie, S.: Arbitrary style transfer in real-time with adaptive instance normalization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1501\u20131510 (2017)","DOI":"10.1109\/ICCV.2017.167"},{"key":"11_CR28","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning, pp. 4904\u20134916. PMLR (2021)"},{"key":"11_CR29","unstructured":"Jiang, Z., Zhang, C., Talwar, K., Mozer, M.C.: Characterizing structural regularities of labeled data in overparameterized models. arXiv preprint arXiv:2002.03206 (2020)"},{"key":"11_CR30","unstructured":"Kim, H., et\u00a0al.: Nsml: Meet the mlaas platform with a real-world case study. arXiv preprint arXiv:1810.09957 (2018)"},{"key":"11_CR31","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3d object representations for fine-grained categorization. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 554\u2013561 (2013)","DOI":"10.1109\/ICCVW.2013.77"},{"issue":"7","key":"11_CR32","doi-asserted-by":"publisher","first-page":"1956","DOI":"10.1007\/s11263-020-01316-z","volume":"128","author":"A Kuznetsova","year":"2020","unstructured":"Kuznetsova, A., et al.: The open images dataset v4: unified image classification, object detection, and visual relationship detection at scale. Int. J. Comput. Vision 128(7), 1956\u20131981 (2020)","journal-title":"Int. J. Comput. Vision"},{"key":"11_CR33","unstructured":"Lee, S., Chun, S., Jung, S., Yun, S., Yoon, S.: Dataset condensation with contrastive signals. In: International Conference on Machine Learning, pp. 12352\u201312364. PMLR (2022)"},{"key":"11_CR34","doi-asserted-by":"crossref","unstructured":"Li, T., Chang, H., Mishra, S., Zhang, H., Katabi, D., Krishnan, D.: Mage: masked generative encoder to unify representation learning and image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2142\u20132152 (2023)","DOI":"10.1109\/CVPR52729.2023.00213"},{"key":"11_CR35","doi-asserted-by":"crossref","unstructured":"Lin, S., Ji, R., Yan, C., Zhang, B., Cao, L., Ye, Q., Huang, F., Doermann, D.: Towards optimal structured cnn pruning via generative adversarial learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2790\u20132799 (2019)","DOI":"10.1109\/CVPR.2019.00290"},{"key":"11_CR36","doi-asserted-by":"publisher","first-page":"5287","DOI":"10.1109\/TIP.2022.3193290","volume":"31","author":"J Liu","year":"2022","unstructured":"Liu, J., Guo, J., Xu, D.: Apsnet: toward adaptive point sampling for efficient 3d action recognition. IEEE Trans. Image Process. 31, 5287\u20135302 (2022)","journal-title":"IEEE Trans. Image Process."},{"key":"11_CR37","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":"11_CR38","unstructured":"Lopes, R.G., Yin, D., Poole, B., Gilmer, J., Cubuk, E.D.: Improving robustness without sacrificing accuracy with patch gaussian augmentation. arXiv preprint arXiv:1906.02611 (2019)"},{"key":"11_CR39","doi-asserted-by":"crossref","unstructured":"Ma, Y., et al.: Annealing-based label-transfer learning for open world object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11454\u201311463 (2023)","DOI":"10.1109\/CVPR52729.2023.01102"},{"key":"11_CR40","unstructured":"Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv:1706.06083 (2017)"},{"key":"11_CR41","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1007\/978-3-030-01216-8_12","volume-title":"Computer Vision \u2013 ECCV 2018","author":"D Mahajan","year":"2018","unstructured":"Mahajan, D., et al.: Exploring the limits of weakly supervised pretraining. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11206, pp. 185\u2013201. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01216-8_12"},{"issue":"10","key":"11_CR42","doi-asserted-by":"publisher","first-page":"5868","DOI":"10.1109\/TCSVT.2023.3260246","volume":"33","author":"Z Mei","year":"2023","unstructured":"Mei, Z., Ye, P., Ye, H., Li, B., Guo, J., Chen, T., Ouyang, W.: Automatic loss function search for adversarial unsupervised domain adaptation. IEEE Trans. Circuits Syst. Video Technol. 33(10), 5868\u20135881 (2023)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"11_CR43","doi-asserted-by":"crossref","unstructured":"Nilsback, M.E., Zisserman, A.: Automated flower classification over a large number of classes. In: 2008 Sixth Indian Conference on Computer Vision, Graphics & Image Processing, pp. 722\u2013729. IEEE (2008)","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"11_CR44","doi-asserted-by":"crossref","unstructured":"Park, S., Chun, S., Heo, B., Kim, W., Yun, S.: Seit: Storage-efficient vision training with tokens using 1% of pixel storage. arXiv preprint arXiv:2303.11114 (2023)","DOI":"10.1109\/ICCV51070.2023.01582"},{"key":"11_CR45","first-page":"20596","volume":"34","author":"M Paul","year":"2021","unstructured":"Paul, M., Ganguli, S., Dziugaite, G.K.: Deep learning on a data diet: finding important examples early in training. Adv. Neural. Inf. Process. Syst. 34, 20596\u201320607 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR46","doi-asserted-by":"crossref","unstructured":"Riba, E., Mishkin, D., Ponsa, D., Rublee, E., Bradski, G.: Kornia: an open source differentiable computer vision library for pytorch. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 3674\u20133683 (2020)","DOI":"10.1109\/WACV45572.2020.9093363"},{"key":"11_CR47","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"11_CR48","doi-asserted-by":"publisher","unstructured":"Rosasco, A., Carta, A., Cossu, A., Lomonaco, V., Bacciu, D.: Distilled replay: overcoming forgetting through synthetic samples. In: International Workshop on Continual Semi-Supervised Learning. pp. 104\u2013117. Springer (2021). https:\/\/doi.org\/10.1007\/978-3-031-17587-9_8","DOI":"10.1007\/978-3-031-17587-9_8"},{"key":"11_CR49","doi-asserted-by":"crossref","unstructured":"Sangermano, M., Carta, A., Cossu, A., Bacciu, D.: Sample condensation in online continual learning. In: 2022 International Joint Conference on Neural Networks (IJCNN), pp. 01\u201308. IEEE (2022)","DOI":"10.1109\/IJCNN55064.2022.9892299"},{"key":"11_CR50","first-page":"25278","volume":"35","author":"C Schuhmann","year":"2022","unstructured":"Schuhmann, C., et al.: Laion-5b: an open large-scale dataset for training next generation image-text models. Adv. Neural. Inf. Process. Syst. 35, 25278\u201325294 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR51","unstructured":"Scimeca, L., Oh, S.J., Chun, S., Poli, M., Yun, S.: Which shortcut cues will dnns choose? a study from the parameter-space perspective. arXiv preprint arXiv:2110.03095 (2021)"},{"key":"11_CR52","doi-asserted-by":"crossref","unstructured":"Shao, S., Yin, Z., Zhou, M., Zhang, X., Shen, Z.: Generalized large-scale data condensation via various backbone and statistical matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16709\u201316718 (2024)","DOI":"10.1109\/CVPR52733.2024.01581"},{"key":"11_CR53","doi-asserted-by":"crossref","unstructured":"Singh, M., et al.: Revisiting weakly supervised pre-training of visual perception models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 804\u2013814 (2022)","DOI":"10.1109\/CVPR52688.2022.00088"},{"key":"11_CR54","unstructured":"Steiner, A., Kolesnikov, A., Zhai, X., Wightman, R., Uszkoreit, J., Beyer, L.: How to train your vit? data, augmentation, and regularization in vision transformers. arXiv preprint arXiv:2106.10270 (2021)"},{"key":"11_CR55","first-page":"18583","volume":"33","author":"R Taori","year":"2020","unstructured":"Taori, R., Dave, A., Shankar, V., Carlini, N., Recht, B., Schmidt, L.: Measuring robustness to natural distribution shifts in image classification. Adv. Neural. Inf. Process. Syst. 33, 18583\u201318599 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR56","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning, pp. 10347\u201310357. PMLR (2021)"},{"key":"11_CR57","unstructured":"Van\u00a0Horn, G., et al.: The inaturalist challenge 2018 dataset. arXiv preprint arXiv:1707.06642 (2018)"},{"key":"11_CR58","unstructured":"Van\u00a0Horn, G., et al.: The inaturalist challenge 2019 dataset. arXiv preprint arXiv:1707.06642 (2019)"},{"key":"11_CR59","unstructured":"Wang, H., Ge, S., Lipton, Z., Xing, E.P.: Learning robust global representations by penalizing local predictive power. In: Advances in Neural Information Processing Systems, pp. 10506\u201310518 (2019)"},{"key":"11_CR60","unstructured":"Wang, T., Zhu, J.Y., Torralba, A., Efros, A.A.: Dataset distillation. arXiv preprint arXiv:1811.10959 (2018)"},{"key":"11_CR61","doi-asserted-by":"crossref","unstructured":"Wei, J., Zou, K.: Eda: Easy data augmentation techniques for boosting performance on text classification tasks. arXiv preprint arXiv:1901.11196 (2019)","DOI":"10.18653\/v1\/D19-1670"},{"key":"11_CR62","unstructured":"Wightman, R., Touvron, H., J\u00e9gou, H.: Resnet strikes back: An improved training procedure in timm. arXiv preprint arXiv:2110.00476 (2021)"},{"key":"11_CR63","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"432","DOI":"10.1007\/978-3-030-01228-1_26","volume-title":"Computer Vision \u2013 ECCV 2018","author":"T Xiao","year":"2018","unstructured":"Xiao, T., Liu, Y., Zhou, B., Jiang, Y., Sun, J.: Unified Perceptual Parsing for Scene Understanding. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 432\u2013448. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01228-1_26"},{"key":"11_CR64","doi-asserted-by":"crossref","unstructured":"Xie, Z., et al.: Simmim: a simple framework for masked image modeling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9653\u20139663 (2022)","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"11_CR65","unstructured":"Yin, Z., Xing, E., Shen, Z.: Squeeze, recover and relabel: dataset condensation at imagenet scale from a new perspective. In: Thirty-seventh Conference on Neural Information Processing Systems (2023)"},{"key":"11_CR66","unstructured":"Yu, J., et al.: Vector-quantized image modeling with improved vqgan. arXiv preprint arXiv:2110.04627 (2021)"},{"key":"11_CR67","doi-asserted-by":"crossref","unstructured":"Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., Yoo, Y.: Cutmix: regularization strategy to train strong classifiers with localizable features. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6023\u20136032 (2019)","DOI":"10.1109\/ICCV.2019.00612"},{"key":"11_CR68","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412 (2017)"},{"key":"11_CR69","unstructured":"Zhao, B., Bilen, H.: Dataset condensation with differentiable siamese augmentation. In: International Conference on Machine Learning, pp. 12674\u201312685. PMLR (2021)"},{"key":"11_CR70","unstructured":"Zhao, B., Mopuri, K.R., Bilen, H.: Dataset condensation with gradient matching. arXiv preprint arXiv:2006.05929 (2020)"},{"key":"11_CR71","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Zheng, L., Kang, G., Li, S., Yang, Y.: Random erasing data augmentation. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI) (2020)","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"11_CR72","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1007\/s11263-018-1140-0","volume":"127","author":"B Zhou","year":"2019","unstructured":"Zhou, B., et al.: Semantic understanding of scenes through the ade20k dataset. Int. J. Comput. Vision 127, 302\u2013321 (2019)","journal-title":"Int. J. Comput. Vision"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73390-1_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T16:31:54Z","timestamp":1730305914000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73390-1_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,31]]},"ISBN":["9783031733895","9783031733901"],"references-count":72,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73390-1_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,31]]},"assertion":[{"value":"31 October 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}