{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T19:07:05Z","timestamp":1788894425166,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370433","type":"print"},{"value":"9783032370440","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-37044-0_8","type":"book-chapter","created":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T18:19:54Z","timestamp":1788891594000},"page":"133-150","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ECC: Encoder-Centric Corruption for\u00a0Fine-Grained Vision in\u00a0VLMs"],"prefix":"10.1007","author":[{"given":"Hyesong","family":"Choi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daeun","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sungmin","family":"Cha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kwang Moo","family":"Yi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongbo","family":"Min","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,9]]},"reference":[{"key":"8_CR1","doi-asserted-by":"crossref","unstructured":"Alayrac, J.B., Donahue, J., Luc, P., et al.: Flamingo: a visual language model for few-shot learning. In: Advances in Neural Information Processing Systems (NeurIPS) (2022)","DOI":"10.52202\/068431-1723"},{"key":"8_CR2","doi-asserted-by":"crossref","unstructured":"Assran, M., et al.: Self-supervised learning from images with a joint-embedding predictive architecture. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15619\u201315629 (2023)","DOI":"10.1109\/CVPR52729.2023.01499"},{"key":"8_CR3","unstructured":"Bao, H., Dong, L., Piao, S., Wei, F.: Beit: Bert pre-training of image transformers. In: International Conference on Learning Representations (2021)"},{"issue":"1","key":"8_CR4","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. Vision 132(1), 208\u2013223 (2024)","journal-title":"Int. J. Comput. Vision"},{"key":"8_CR5","unstructured":"Chen, X., Liu, Z., Xie, S., He, K.: Deconstructing denoising diffusion models for self-supervised learning. arXiv preprint arXiv:2401.14404 (2024)"},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Choi, H., Lee, H., Joung, S., Park, H., Kim, J., Min, D.: Emerging property of masked token for effective pre-training. arXiv preprint arXiv:2404.08330 (2024)","DOI":"10.1007\/978-3-031-73116-7_16"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Choi, H., Park, H., Yi, K.M., Cha, S., Min, D.: Salience-based adaptive masking: revisiting token dynamics for enhanced pre-training. In: European Conference on Computer Vision, pp. 343\u2013359. Springer (2025)","DOI":"10.1007\/978-3-031-73229-4_20"},{"key":"8_CR8","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":"8_CR9","doi-asserted-by":"crossref","unstructured":"Dong, X., et al.: Bootstrapped masked autoencoders for vision bert pretraining. In: European Conference on Computer Vision, pp. 247\u2013264. Springer (2022)","DOI":"10.1007\/978-3-031-20056-4_15"},{"key":"8_CR10","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"Fini, E., et al.: Multimodal autoregressive pre-training of large vision encoders. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9641\u20139654 (2025)","DOI":"10.1109\/CVPR52734.2025.00901"},{"key":"8_CR12","unstructured":"Geirhos, R.: Imagenet-trained CNNs are biased towards texture. In: ICLR (2019)"},{"key":"8_CR13","unstructured":"Goyal, S., et\u00a0al.: Object hallucination in vision-language models. arXiv (2023)"},{"key":"8_CR14","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":"8_CR15","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"8_CR16","doi-asserted-by":"crossref","unstructured":"Hoogeboom, E., Mensink, T., Heek, J., Lamerigts, K., Gao, R., Salimans, T.: Simpler diffusion (sid2): 1.5 fid on imagenet512 with pixel-space diffusion. arXiv preprint arXiv:2410.19324 (2024)","DOI":"10.1109\/CVPR52734.2025.01683"},{"key":"8_CR17","doi-asserted-by":"publisher","first-page":"26565","DOI":"10.52202\/068431-1926","volume":"35","author":"T Karras","year":"2022","unstructured":"Karras, T., Aittala, M., Aila, T., Laine, S.: Elucidating the design space of diffusion-based generative models. Adv. Neural. Inf. Process. Syst. 35, 26565\u201326577 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"8_CR18","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"},{"key":"8_CR19","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: International Conference on Machine Learning (ICML) (2023)"},{"key":"8_CR20","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning (ICML) (2022)"},{"key":"8_CR21","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft coco: common objects in context. In: Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, 6\u201312 September 2014, Proceedings, Part V 13, pp. 740\u2013755. Springer (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"8_CR22","doi-asserted-by":"crossref","unstructured":"Liu, H., et\u00a0al.: Visual instruction tuning. In: NeurIPS (2023)","DOI":"10.52202\/075280-1516"},{"key":"8_CR23","unstructured":"Liu, X., Gong, C., Liu, Q.: Flow straight and fast: Learning to generate and transfer data with rectified flow. arXiv preprint arXiv:2209.03003 (2022)"},{"key":"8_CR24","doi-asserted-by":"publisher","first-page":"5775","DOI":"10.52202\/068431-0418","volume":"35","author":"C Lu","year":"2022","unstructured":"Lu, C., Zhou, Y., Bao, F., Chen, J., Li, C., Zhu, J.: DPM-solver: a fast ode solver for diffusion probabilistic model sampling in around 10 steps. Adv. Neural. Inf. Process. Syst. 35, 5775\u20135787 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"8_CR25","unstructured":"Maji, S., Rahtu, E., Kannala, J., Blaschko, M., Vedaldi, A.: Fine-grained visual classification of aircraft. arXiv preprint arXiv:1306.5151 (2013)"},{"key":"8_CR26","unstructured":"Nichol, A.Q., Dhariwal, P.: Improved denoising diffusion probabilistic models. In: International Conference on Machine Learning, pp. 8162\u20138171. PMLR (2021)"},{"key":"8_CR27","unstructured":"Radford, A., Kim, J.W., Hallacy, C., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning (ICML) (2021)"},{"key":"8_CR28","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: International Conference on Machine Learning, pp. 8821\u20138831. PMLR (2021)"},{"key":"8_CR29","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":"8_CR30","doi-asserted-by":"publisher","first-page":"36479","DOI":"10.52202\/068431-2643","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. Adv. Neural. Inf. Process. Syst. 35, 36479\u201336494 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"8_CR31","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"8_CR32","unstructured":"Tschannen, M., et al.: Siglip 2: multilingual vision-language encoders with improved semantic understanding, localization, and dense features. arXiv preprint arXiv:2502.14786 (2025)"},{"key":"8_CR33","doi-asserted-by":"crossref","unstructured":"Van\u00a0Horn, G., et al.: Building a bird recognition app and large scale dataset with citizen scientists: the fine print in fine-grained dataset collection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 595\u2013604 (2015)","DOI":"10.1109\/CVPR.2015.7298658"},{"key":"8_CR34","doi-asserted-by":"crossref","unstructured":"Van\u00a0Horn, G., et al.: The inaturalist species classification and detection dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8769\u20138778 (2018)","DOI":"10.1109\/CVPR.2018.00914"},{"key":"8_CR35","unstructured":"Van\u00a0Horn, G., et al.: The inaturalist challenge 2017 dataset. arXiv preprint arXiv:1707.066421(2), 4 (2017)"},{"key":"8_CR36","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The Caltech-UCSD birds-200-2011 dataset (2011)"},{"key":"8_CR37","doi-asserted-by":"crossref","unstructured":"Wang, H., et\u00a0al.: High-frequency components help explain the generalization of convolutional neural networks. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00871"},{"key":"8_CR38","unstructured":"Wei, C., et al.: Diffusion models as masked autoencoders. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 16284\u201316294 (2023)"},{"key":"8_CR39","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":"8_CR40","unstructured":"Yi, K., et al.: Masked image modeling with denoising contrast. arXiv preprint arXiv:2205.09616 (2022)"},{"key":"8_CR41","unstructured":"Yu, J., Wang, X., Zhang, W., et\u00a0al.: Coca: contrastive captioners are image-text foundation models. In: International Conference on Machine Learning (ICML) (2022)"},{"key":"8_CR42","unstructured":"Zheng, H., Nie, W., Vahdat, A., Anandkumar, A.: Fast training of diffusion models with masked transformers. arXiv preprint arXiv:2306.09305 (2023)"},{"key":"8_CR43","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"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37044-0_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T18:19:59Z","timestamp":1788891599000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37044-0_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370433","9783032370440"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37044-0_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"9 September 2026","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":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}