{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,7]],"date-time":"2025-06-07T04:03:20Z","timestamp":1749269000324,"version":"3.41.0"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031915772","type":"print"},{"value":"9783031915789","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-3-031-91578-9_9","type":"book-chapter","created":{"date-parts":[[2025,6,6]],"date-time":"2025-06-06T09:23:11Z","timestamp":1749201791000},"page":"148-157","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["RGMIM: Region-Guided Masked Image Modeling for Learning Meaningful Representations from X-Ray Images"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2898-2504","authenticated-orcid":false,"given":"Guang","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4474-3995","authenticated-orcid":false,"given":"Ren","family":"Togo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5332-8112","authenticated-orcid":false,"given":"Takahiro","family":"Ogawa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1496-1761","authenticated-orcid":false,"given":"Miki","family":"Haseyama","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"9_CR1","unstructured":"Bao, H., Dong, L., Wei, F.: Beit: bert pre-training of image transformers. In: Proceedings of the International Conference on Learning Representations (ICLR) (2022)"},{"key":"9_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101539","volume":"58","author":"L Chen","year":"2019","unstructured":"Chen, L., Bentley, P., Mori, K., Misawa, K., Fujiwara, M., Rueckert, D.: Self-supervised learning for medical image analysis using image context restoration. Med. Image Anal. 58, 101539 (2019)","journal-title":"Med. Image Anal."},{"key":"9_CR3","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: Proceedings of the International Conference on Machine Learning (ICML) (2020)"},{"key":"9_CR4","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 (CVPR), pp. 15750\u201315758 (2021)","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Z., Agarwal, D., Aggarwal, K., Safta, W., Balan, M.M., Brown, K.: Masked image modeling advances 3d medical image analysis. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 1969\u20131979 (2023)","DOI":"10.1109\/WACV56688.2023.00201"},{"key":"9_CR6","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"9_CR7","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL) (2019)"},{"key":"9_CR8","unstructured":"Dosovitskiy, A., et al.: An image is worth 16 $$\\times $$ 16 words: transformers for image recognition at scale. In: Proceedings of the International Conference on Learning Representations (ICLR) (2021)"},{"key":"9_CR9","unstructured":"Gidaris, S., Singh, P., Komodakis, N.: Unsupervised representation learning by predicting image rotations. In: Proceedings of the International Conference on Learning Representations (ICLR) (2018)"},{"key":"9_CR10","unstructured":"Grill, J.B., et al.: Bootstrap your own latent-a new approach to self-supervised learning. In: Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), pp. 21271\u201321284 (2020)"},{"key":"9_CR11","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 (CVPR), pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"9_CR13","doi-asserted-by":"crossref","unstructured":"Krishnan, R., Rajpurkar, P., Topol, E.J.: Self-supervised learning in medicine and healthcare. Nat. Biomed. Eng. 1\u20137 (2022)","DOI":"10.1038\/s41551-022-00914-1"},{"key":"9_CR14","doi-asserted-by":"crossref","unstructured":"Li, G., Togo, R., Ogawa, T., Haseyama, M.: COVID-19 detection based on self-supervised transfer learning using chest x-ray images. Int. J. Comput. Assisted Radiol. Surg.\u00a01\u20138 (2022)","DOI":"10.1007\/s11548-022-02813-x"},{"key":"9_CR15","doi-asserted-by":"crossref","unstructured":"Li, G., Togo, R., Ogawa, T., Haseyama, M.: Self-knowledge distillation based self-supervised learning for COVID-19 detection from chest x-ray images. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1371\u20131375 (2022)","DOI":"10.1109\/ICASSP43922.2022.9746540"},{"key":"9_CR16","doi-asserted-by":"crossref","unstructured":"Li, G., Togo, R., Ogawa, T., Haseyama, M.: Tribyol: triplet byol for self-supervised representation learning. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3458\u20133462 (2022)","DOI":"10.1109\/ICASSP43922.2022.9746967"},{"key":"9_CR17","doi-asserted-by":"crossref","unstructured":"Liu, X., et al.: Self-supervised learning: generative or contrastive. IEEE Trans. Knowl. Data Eng. (2021)","DOI":"10.1109\/TKDE.2021.3090866"},{"key":"9_CR18","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: Proceedings of the International Conference on Learning Representations (ICLR) (2019)"},{"key":"9_CR19","doi-asserted-by":"crossref","unstructured":"Noroozi, M., Favaro, P.: Unsupervised learning of visual representations by solving jigsaw puzzles. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 69\u201384 (2016)","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"9_CR20","doi-asserted-by":"crossref","unstructured":"Rahman, T., et al.: Exploring the effect of image enhancement techniques on COVID-19 detection using chest x-ray images. Comput. Biol. Med. 132, 104319 (2021)","DOI":"10.1016\/j.compbiomed.2021.104319"},{"issue":"5","key":"9_CR21","doi-asserted-by":"publisher","first-page":"1285","DOI":"10.1109\/TMI.2016.2528162","volume":"35","author":"HC Shin","year":"2016","unstructured":"Shin, H.C., et al.: Deep convolutional neural networks for computer-aided detection: cnn architectures, dataset characteristics and transfer learning. IEEE Trans. Med. Imaging 35(5), 1285\u20131298 (2016)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"9_CR22","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.1045","volume":"8","author":"S Shurrab","year":"2022","unstructured":"Shurrab, S., Duwairi, R.: Self-supervised learning methods and applications in medical imaging analysis: a survey. PeerJ Comput. Sci. 8, e1045 (2022)","journal-title":"PeerJ Comput. Sci."},{"key":"9_CR23","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 (CVPR), pp. 14668\u201314678 (2022)","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"9_CR24","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 (CVPR), pp. 9653\u20139663 (2022)","DOI":"10.1109\/CVPR52688.2022.00943"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-91578-9_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,6]],"date-time":"2025-06-06T09:23:21Z","timestamp":1749201801000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-91578-9_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031915772","9783031915789"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-91578-9_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","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"}}]}}