{"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":1778080195286,"version":"3.51.4"},"publisher-location":"Cham","reference-count":51,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726606","type":"print"},{"value":"9783031726613","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:00:00Z","timestamp":1732665600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:00:00Z","timestamp":1732665600000},"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\/978-3-031-72661-3_25","type":"book-chapter","created":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T07:52:07Z","timestamp":1732607527000},"page":"432-449","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["ColorMAE: Exploring Data-Independent Masking Strategies in\u00a0Masked AutoEncoders"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9286-9587","authenticated-orcid":false,"given":"Carlos","family":"Hinojosa","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5227-647X","authenticated-orcid":false,"given":"Shuming","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5534-587X","authenticated-orcid":false,"given":"Bernard","family":"Ghanem","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,27]]},"reference":[{"issue":"6","key":"25_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3414685.3417881","volume":"39","author":"AG Ahmed","year":"2020","unstructured":"Ahmed, A.G., Wonka, P.: Screen-space blue-noise diffusion of Monte Carlo sampling error via hierarchical ordering of pixels. ACM Trans. Graph. (TOG) 39(6), 1\u201315 (2020)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"25_CR2","unstructured":"Bachman, P., Hjelm, R.D., Buchwalter, W.: Learning representations by maximizing mutual information across views. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"25_CR3","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. In: International Conference on Machine Learning, pp. 1298\u20131312. PMLR (2022)"},{"key":"25_CR4","unstructured":"Bao, H., Dong, L., Piao, S., Wei, F.: BEiT: BERT pre-training of image transformers. arXiv preprint arXiv:2106.08254 (2021)"},{"key":"25_CR5","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR6","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"25_CR7","unstructured":"Castleman, K.R.: Digital Image Processing. Prentice Hall Press (1996)"},{"key":"25_CR8","doi-asserted-by":"crossref","unstructured":"Chen, K., Liu, Z., Hong, L., Xu, H., Li, Z., Yeung, D.Y.: Mixed autoencoder for self-supervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22742\u201322751 (2023)","DOI":"10.1109\/CVPR52729.2023.02178"},{"key":"25_CR9","unstructured":"Chen, P., Liu, S., Zhao, H., Jia, J.: GridMask data augmentation. arXiv preprint arXiv:2001.04086 (2020)"},{"key":"25_CR10","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)"},{"issue":"1","key":"25_CR11","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1007\/s11263-023-01852-4","volume":"132","author":"X Chen","year":"2024","unstructured":"Chen, X., et al.: Context autoencoder for self-supervised representation learning. Int. J. Comput. Vis. 132(1), 208\u2013223 (2024)","journal-title":"Int. J. Comput. Vis."},{"key":"25_CR12","doi-asserted-by":"crossref","unstructured":"Chen, X., He, K.: Exploring simple Siamese representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15750\u201315758 (2021)","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"25_CR13","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, October 2021, pp. 9640\u20139649 (2021)","DOI":"10.1109\/ICCV48922.2021.00950"},{"issue":"12","key":"25_CR14","doi-asserted-by":"publisher","first-page":"2312","DOI":"10.1364\/JOSAA.33.002312","volume":"33","author":"CV Correa","year":"2016","unstructured":"Correa, C.V., Arguello, H., Arce, G.R.: Spatiotemporal blue noise coded aperture design for multi-shot compressive spectral imaging. JOSA A 33(12), 2312\u20132322 (2016)","journal-title":"JOSA A"},{"key":"25_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":"25_CR16","doi-asserted-by":"publisher","unstructured":"Dong, X., et al.: Bootstrapped Masked Autoencoders for Vision BERT Pretraining. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022, ECCV 2022. LNCS, vol. 13690, pp. 247\u2013264. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20056-4_15","DOI":"10.1007\/978-3-031-20056-4_15"},{"key":"25_CR17","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. In: 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, 3\u20137 May 2021. OpenReview.net (2021). https:\/\/openreview.net\/forum?id=YicbFdNTTy"},{"key":"25_CR18","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":"25_CR19","unstructured":"Ermolov, A., Siarohin, A., Sangineto, E., Sebe, N.: Whitening for self-supervised representation learning. In: International Conference on Machine Learning, pp. 3015\u20133024. PMLR (2021)"},{"key":"25_CR20","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2015","unstructured":"Everingham, M., Eslami, S.A., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes challenge: a retrospective. Int. J. Comput. Vis. 111, 98\u2013136 (2015)","journal-title":"Int. J. Comput. Vis."},{"key":"25_CR21","doi-asserted-by":"crossref","unstructured":"Feng, Z., Zhang, S.: Evolved part masking for self-supervised learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10386\u201310395 (2023)","DOI":"10.1109\/CVPR52729.2023.01001"},{"key":"25_CR22","unstructured":"Gonzalez, R.C., Woods, R.E.: Digital Image Processing. Prentice Hall (2008)"},{"key":"25_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":"25_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":"25_CR25","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"25_CR26","unstructured":"Hjelm, R.D., et al.: Learning deep representations by mutual information estimation and maximization. arXiv preprint arXiv:1808.06670 (2018)"},{"key":"25_CR27","doi-asserted-by":"publisher","unstructured":"Kakogeorgiou, I., et al.: What to hide from your students: attention-guided masked image modeling. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision, ECCV 2022. LNCS, vol. 13690, pp. 300\u2013318. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20056-4_18","DOI":"10.1007\/978-3-031-20056-4_18"},{"issue":"12","key":"25_CR28","doi-asserted-by":"publisher","first-page":"2424","DOI":"10.1109\/5.735449","volume":"86","author":"DL Lau","year":"1998","unstructured":"Lau, D.L., Arce, G.R., Gallagher, N.C.: Green-noise digital halftoning. Proc. IEEE 86(12), 2424\u20132444 (1998)","journal-title":"Proc. IEEE"},{"issue":"4","key":"25_CR29","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1109\/MSP.2003.1215229","volume":"20","author":"DL Lau","year":"2003","unstructured":"Lau, D.L., Ulichney, R., Arce, G.R.: Blue and green noise halftoning models. IEEE Sig. Process. Mag. 20(4), 28\u201338 (2003)","journal-title":"IEEE Sig. Process. Mag."},{"key":"25_CR30","first-page":"14290","volume":"35","author":"G Li","year":"2022","unstructured":"Li, G., Zheng, H., Liu, D., Wang, C., Su, B., Zheng, C.: SemMAE: semantic-guided masking for learning masked autoencoders. Adv. Neural. Inf. Process. Syst. 35, 14290\u201314302 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR31","unstructured":"Li, X., Wang, W., Yang, L., Yang, J.: Uniform masking: enabling MAE pre-training for pyramid-based vision transformers with locality. arXiv preprint arXiv:2205.10063 (2022)"},{"key":"25_CR32","doi-asserted-by":"publisher","unstructured":"Li, Y., Mao, H., Girshick, R., He, K.: Exploring plain vision transformer backbones for object detection. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision, ECCV 2022. LNCS, vol. 13669, pp. 280\u2013296. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_17","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"25_CR33","first-page":"13165","volume":"34","author":"Z Li","year":"2021","unstructured":"Li, Z., et al.: MST: masked self-supervised transformer for visual representation. Adv. Neural. Inf. Process. Syst. 34, 13165\u201313176 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR34","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, Part V 13. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"25_CR35","doi-asserted-by":"crossref","unstructured":"Muhammad, M.B., Yeasin, M.: Eigen-CAM: class activation map using principal components. In: 2020 International Joint Conference on Neural Networks (IJCNN), pp.\u00a01\u20137. IEEE (2020)","DOI":"10.1109\/IJCNN48605.2020.9206626"},{"key":"25_CR36","unstructured":"Oord, A.v.d., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"25_CR37","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115, 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vis."},{"key":"25_CR38","unstructured":"Shi, Y., Siddharth, N., Torr, P., Kosiorek, A.R.: Adversarial masking for self-supervised learning. In: International Conference on Machine Learning, pp. 20026\u201320040. PMLR (2022)"},{"key":"25_CR39","doi-asserted-by":"crossref","unstructured":"Ulichney, R.A.: Void-and-cluster method for dither array generation. In: Human Vision, Visual Processing, and Digital Display IV, vol.\u00a01913, pp. 332\u2013343. SPIE (1993)","DOI":"10.1117\/12.152707"},{"issue":"4","key":"25_CR40","doi-asserted-by":"publisher","first-page":"1146","DOI":"10.1890\/02-3122","volume":"85","author":"DA Vasseur","year":"2004","unstructured":"Vasseur, D.A., Yodzis, P.: The color of environmental noise. Ecology 85(4), 1146\u20131152 (2004)","journal-title":"Ecology"},{"key":"25_CR41","unstructured":"Wang, H., Fan, J., Wang, Y., Song, K., Wang, T., Zhang, Z.X.: DropPos: pre-training vision transformers by reconstructing dropped positions. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"25_CR42","doi-asserted-by":"crossref","unstructured":"Wang, H., Song, K., Fan, J., Wang, Y., Xie, J., Zhang, Z.: Hard patches mining for masked image modeling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10375\u201310385 (2023)","DOI":"10.1109\/CVPR52729.2023.01000"},{"key":"25_CR43","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. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14668\u201314678 (2022)","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"25_CR44","unstructured":"Wolfe, A., Morrical, N., Akenine-M\u00f6ller, T., Ramamoorthi, R., Ghosh, A., Wei, L.: Spatiotemporal blue noise masks. In: Eurographics Symposium on Rendering, pp. 117\u2013126 (2022)"},{"key":"25_CR45","doi-asserted-by":"crossref","unstructured":"Wu, Z., Xiong, Y., Yu, S.X., Lin, D.: Unsupervised feature learning via non-parametric instance discrimination. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3733\u20133742 (2018)","DOI":"10.1109\/CVPR.2018.00393"},{"key":"25_CR46","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":"25_CR47","unstructured":"Xie, J., et al.: Masked frequency modeling for self-supervised visual pre-training. In: The Eleventh International Conference on Learning Representations (2022)"},{"key":"25_CR48","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":"25_CR49","first-page":"27127","volume":"35","author":"Q Zhang","year":"2022","unstructured":"Zhang, Q., Wang, Y., Wang, Y.: How mask matters: towards theoretical understandings of masked autoencoders. Adv. Neural. Inf. Process. Syst. 35, 27127\u201327139 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR50","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ADE20K dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 633\u2013641 (2017)","DOI":"10.1109\/CVPR.2017.544"},{"key":"25_CR51","unstructured":"Zhou, J., et al.: iBOT: image BERT pre-training with online tokenizer. arXiv preprint arXiv:2111.07832 (2021)"}],"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\/978-3-031-72661-3_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T08:24:43Z","timestamp":1732609483000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72661-3_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,27]]},"ISBN":["9783031726606","9783031726613"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72661-3_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,27]]},"assertion":[{"value":"27 November 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"}}]}}