{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T19:04:35Z","timestamp":1783969475850,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":24,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819233991","type":"print"},{"value":"9789819234004","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T00:00:00Z","timestamp":1783987200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T00:00:00Z","timestamp":1783987200000},"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":[[2027]]},"DOI":"10.1007\/978-981-92-3400-4_36","type":"book-chapter","created":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T18:14:50Z","timestamp":1783966490000},"page":"437-449","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Attention Patterns in Vision Transformers for Robustness"],"prefix":"10.1007","author":[{"given":"Yi","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haofei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanyang","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenda","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoze","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiacong","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tian","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengxuming","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingli","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,14]]},"reference":[{"key":"36_CR1","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Proces. Syst. 30 (2017)"},{"key":"36_CR2","unstructured":"Dosovitskiy, A., et al.: An image is worth 16\u00a0\u00d7\u00a016 words: transformers for image recognition at scale. arXiv Preprint https:\/\/arxiv.org\/abs\/2010.11929 (2020)"},{"key":"36_CR3","first-page":"10347","volume-title":"International Conference on Machine Learning","author":"H Touvron","year":"2021","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers and distillation through attention. In: International Conference on Machine Learning, pp. 10347\u201310357. PMLR (2021)"},{"key":"36_CR4","unstructured":"Hendrycks, D., Dietterich, T.: Benchmarking neural network robustness to common corruptions and perturbations. arXiv Preprint https:\/\/arxiv.org\/abs\/1903.12261 (2019)"},{"key":"36_CR5","first-page":"404","volume-title":"European Conference on Computer Vision","author":"J Gu","year":"2022","unstructured":"Gu, J., Tresp, V., Qin, Y.: Are vision transformers robust to patch perturbations? In: European Conference on Computer Vision, pp. 404\u2013421. Springer (2022)"},{"key":"36_CR6","doi-asserted-by":"crossref","unstructured":"Herrmann, C., et al.: Pyramid adversarial training improves ViT performance. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 13419\u201313429 (2022)","DOI":"10.1109\/CVPR52688.2022.01306"},{"key":"36_CR7","doi-asserted-by":"crossref","unstructured":"Nafez, M., Koochakian, A., Maleki, A., Habibi, J., Rohban, M.H.: PatchGuard: Adversarially robust anomaly detection and localization through vision transformers and pseudo anomalies. In: Proceedings of the Computer Vision and Pattern Recognition Conference. pp. 20383\u201320394 (2025)","DOI":"10.1109\/CVPR52734.2025.01898"},{"key":"36_CR8","unstructured":"Menon, R., Franco, N., G\u00fcnnemann, S.: LipShiFT: a certifiably robust shift-based vision transformer. arXiv Preprint https:\/\/arxiv.org\/abs\/2503.14751 (2025)"},{"key":"36_CR9","first-page":"27378","volume-title":"International Conference on Machine Learning","author":"D Zhou","year":"2022","unstructured":"Zhou, D., et al.: Understanding the robustness in vision transformers. In: International Conference on Machine Learning, pp. 27378\u201327394. PMLR (2022)"},{"key":"36_CR10","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 https:\/\/arxiv.org\/abs\/2106.10270 (2021)"},{"key":"36_CR11","volume-title":"Learning Multiple Layers of Features from Tiny Images","author":"A Krizhevsky","year":"2009","unstructured":"Krizhevsky, A., Hinton, G.: Learning Multiple Layers of Features from Tiny Images. (2009)."},{"key":"36_CR12","doi-asserted-by":"publisher","first-page":"33618","DOI":"10.52202\/068431-2436","volume":"35","author":"H Chefer","year":"2022","unstructured":"Chefer, H., Schwartz, I., Wolf, L.: Optimizing relevance maps of vision transformers improves robustness. Adv. Neural Inf. Proces. Syst. 35, 33618\u201333632 (2022)","journal-title":"Adv. Neural Inf. Proces. Syst."},{"key":"36_CR13","first-page":"13937","volume":"34","author":"Y Rao","year":"2021","unstructured":"Rao, Y., Zhao, W., Liu, B., Lu, J., Zhou, J., Hsieh, C.-J.: DynamicViT: efficient vision transformers with dynamic token sparsification. Adv. Neural Inf. Proces. Syst. 34, 13937\u201313949 (2021)","journal-title":"Adv. Neural Inf. Proces. Syst."},{"key":"36_CR14","doi-asserted-by":"publisher","first-page":"9598","DOI":"10.1109\/IROS55552.2023.10342025","volume-title":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","author":"Y Li","year":"2023","unstructured":"Li, Y., et al.: LocalViT: analyzing locality in vision transformers. In: 2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 9598\u20139605. IEEE (2023)"},{"key":"36_CR15","unstructured":"Amir, S., Gandelsman, Y., Bagon, S., Dekel, T.: Deep ViT features as dense visual descriptors. arXiv Preprint https:\/\/arxiv.org\/abs\/2112.05814. 2, 4 (2021)"},{"key":"36_CR16","unstructured":"Cordonnier, J.-B., Loukas, A., Jaggi, M.: On the relationship between self-attention and convolutional layers. arXiv Preprint https:\/\/arxiv.org\/abs\/1911.03584 (2019)"},{"key":"36_CR17","doi-asserted-by":"crossref","unstructured":"Heo, B., Yun, S., Han, D., Chun, S., Choe, J., Oh, S.J.: Rethinking spatial dimensions of vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11936\u201311945 (2021)","DOI":"10.1109\/ICCV48922.2021.01172"},{"key":"36_CR18","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv Preprint https:\/\/arxiv.org\/abs\/1711.05101 (2017)"},{"key":"36_CR19","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: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 3008\u20133017 (2019)","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"36_CR20","unstructured":"Zhang, H., Ciss\u00e9, M., Dauphin, Y., Lopez-Paz, D.: Mixup: Beyond Empirical Risk Minimization. arXiv Preprint https:\/\/arxiv.org\/abs\/1710.09412 (2017)."},{"key":"36_CR21","doi-asserted-by":"crossref","unstructured":"Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., Yoo, Y.J.: CutMix: regularization strategy to train strong classifiers with localizable features. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 6022\u20136031 (2019)","DOI":"10.1109\/ICCV.2019.00612"},{"key":"36_CR22","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Adv. Neural Inf. Proces. Syst. 25 (2012)"},{"key":"36_CR23","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., Zhao, K., Basart, S., Steinhardt, J., Song, D.: Natural adversarial examples. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15262\u201315271 (2021)","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"36_CR24","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., et al.: The many faces of robustness: a critical analysis of out-of-distribution generalization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8340\u20138349 (2021)","DOI":"10.1109\/ICCV48922.2021.00823"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-3400-4_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T18:14:52Z","timestamp":1783966492000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3400-4_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,14]]},"ISBN":["9789819233991","9789819234004"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3400-4_36","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,14]]},"assertion":[{"value":"14 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Toronto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","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":"22 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2026a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2026\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}