{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T02:53:24Z","timestamp":1768272804638,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":44,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819556755","type":"print"},{"value":"9789819556762","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\/978-981-95-5676-2_30","type":"book-chapter","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T20:32:00Z","timestamp":1768249920000},"page":"440-454","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Variational Vision Transformer with\u00a0Anti-Over-Smoothing Strategy for\u00a0Robust Face Recognition"],"prefix":"10.1007","author":[{"given":"Yuying","family":"Zhao","sequence":"first","affiliation":[]},{"given":"Jiani","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Chun-Guang","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,13]]},"reference":[{"key":"30_CR1","doi-asserted-by":"crossref","unstructured":"Ai, H., Liao, Q., Chen, Y., Qian, J.: Gaussian mixture distribution makes data uncertainty learning better. In: FG, pp. 01\u201308 (2021)","DOI":"10.1109\/FG52635.2021.9666964"},{"key":"30_CR2","unstructured":"Alemi, A.A., Fischer, I., Dillon, J.V., Murphy, K.: Deep variational information bottleneck. In: ICLR (2017)"},{"key":"30_CR3","doi-asserted-by":"crossref","unstructured":"Bai, J., Yuan, L., Xia, S., Yan, S., Li, Z., Liu, W.: Improving vision transformers by revisiting high-frequency components. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20053-3_1"},{"key":"30_CR4","doi-asserted-by":"crossref","unstructured":"Chang, J., Lan, Z., Cheng, C., Wei, Y.: Data uncertainty learning in face recognition. In: CVPR, pp. 5710\u20135719 (2020)","DOI":"10.1109\/CVPR42600.2020.00575"},{"key":"30_CR5","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Zhu, X., Gong, S.: Low-resolution face recognition. In: ACCV, pp. 605\u2013621 (2018)","DOI":"10.1007\/978-3-030-20893-6_38"},{"key":"30_CR6","doi-asserted-by":"crossref","unstructured":"Dan, J., et al.: TransFace: calibrating transformer training for face recognition from a data-centric perspective. In: ICCV, pp. 20642\u201320653 (2023)","DOI":"10.1109\/ICCV51070.2023.01887"},{"key":"30_CR7","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Xue, N., Zafeiriou, S.: ArcFace: additive angular margin loss for deep face recognition. In: CVPR, pp. 4690\u20134699 (2019)","DOI":"10.1109\/CVPR.2019.00482"},{"key":"30_CR8","unstructured":"Dong, Y., Cordonnier, J.B., Loukas, A.: Attention is not all you need: pure attention loses rank doubly exponentially with depth. In: ICML, pp. 2793\u20132803. PMLR (2021)"},{"key":"30_CR9","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2020)"},{"key":"30_CR10","unstructured":"Gong, C., Wang, D., Li, M., Chandra, V., Liu, Q.: Vision transformers with patch diversification. arXiv preprint arXiv:2104.12753 (2021)"},{"key":"30_CR11","unstructured":"Guo, X., Wang, Y., Du, T., Wang, Y.: ContraNorm: a contrastive learning perspective on oversmoothing and beyond. In: ICLR (2023)"},{"key":"30_CR12","doi-asserted-by":"crossref","unstructured":"Kim, G., Park, G., Kang, S., Woo, S.S.: S-ViT: sparse vision transformer for accurate face recognition. In: SAC, pp. 1130\u20131138 (2023)","DOI":"10.1145\/3555776.3577640"},{"key":"30_CR13","doi-asserted-by":"crossref","unstructured":"Kim, M., Jain, A.K., Liu, X.: AdaFace: quality adaptive margin for face recognition. In: CVPR, pp. 18750\u201318759 (2022)","DOI":"10.1109\/CVPR52688.2022.01819"},{"key":"30_CR14","doi-asserted-by":"crossref","unstructured":"Kim, M., Su, Y., Liu, F., Jain, A., Liu, X.: Keypoint relative position encoding for face recognition. In: CVPR, pp. 244\u2013255 (2024)","DOI":"10.1109\/CVPR52733.2024.00031"},{"key":"30_CR15","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"30_CR16","doi-asserted-by":"crossref","unstructured":"Knoche, M., Hormann, S., Rigoll, G.: Cross-quality LFW: a database for analyzing cross-resolution image face recognition in unconstrained environments. In: FG, pp.\u00a01\u20135 (2021)","DOI":"10.1109\/FG52635.2021.9666960"},{"key":"30_CR17","doi-asserted-by":"crossref","unstructured":"Le, N., Nguyen, K., Tran, Q., Tjiputra, E., Le, B., Nguyen, A.: Uncertainty-aware label distribution learning for facial expression recognition. In: WACV, pp. 6088\u20136097 (2023)","DOI":"10.1109\/WACV56688.2023.00603"},{"key":"30_CR18","doi-asserted-by":"crossref","unstructured":"Li, S., Xu, J., Xu, X., Shen, P., Li, S., Hooi, B.: Spherical confidence learning for face recognition. In: CVPR, pp. 15629\u201315637 (2021)","DOI":"10.1109\/CVPR46437.2021.01537"},{"key":"30_CR19","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2019)"},{"issue":"1","key":"30_CR20","doi-asserted-by":"publisher","first-page":"654","DOI":"10.1038\/s41467-024-44824-z","volume":"15","author":"J Ma","year":"2024","unstructured":"Ma, J., He, Y., Li, F., Han, L., You, C., Wang, B.: Segment anything in medical images. Nat. Commun. 15(1), 654 (2024)","journal-title":"Nat. Commun."},{"key":"30_CR21","doi-asserted-by":"crossref","unstructured":"Maze, B., et\u00a0al.: IARPA Janus benchmark-C: Face dataset and protocol. In: ICB, pp. 158\u2013165 (2018)","DOI":"10.1109\/ICB2018.2018.00033"},{"key":"30_CR22","doi-asserted-by":"crossref","unstructured":"Moschoglou, S., Papaioannou, A., Sagonas, C., Deng, J., Kotsia, I., Zafeiriou, S.: AgeDB: the first manually collected, in-the-wild age database. In: CVPR Workshops, pp. 51\u201359 (2017)","DOI":"10.1109\/CVPRW.2017.250"},{"key":"30_CR23","unstructured":"Noci, L., Anagnostidis, S., Biggio, L., Orvieto, A., Singh, S.P., Lucchi, A.: Signal propagation in transformers: theoretical perspectives and the role of rank collapse. In: NIPS (2022)"},{"key":"30_CR24","unstructured":"Park, N., Kim, S.: How do vision transformers work? In: ICLR (2022)"},{"key":"30_CR25","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: ICCV, pp. 4195\u20134205 (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"issue":"4","key":"30_CR26","doi-asserted-by":"publisher","first-page":"2223","DOI":"10.1109\/TCSVT.2023.3304724","volume":"34","author":"L Qin","year":"2024","unstructured":"Qin, L., et al.: SwinFace: a multi-task transformer for face recognition, expression recognition, age estimation and attribute estimation. IEEE Trans. Cir. Syst. Video Technol. 34(4), 2223\u20132234 (2024)","journal-title":"IEEE Trans. Cir. Syst. Video Technol."},{"key":"30_CR27","doi-asserted-by":"crossref","unstructured":"Sengupta, S., Chen, J.C., Castillo, C., Patel, V.M., Chellappa, R., Jacobs, D.W.: Frontal to profile face verification in the wild. In: WACV, pp.\u00a01\u20139 (2016)","DOI":"10.1109\/WACV.2016.7477558"},{"key":"30_CR28","unstructured":"Shi, H., et al.: Revisiting over-smoothing in BERT from the perspective of graph. In: ICLR (2022)"},{"key":"30_CR29","doi-asserted-by":"crossref","unstructured":"Shi, Y., Jain, A.K.: Probabilistic face embeddings. In: ICCV, pp. 6902\u20136911 (2019)","DOI":"10.1109\/ICCV.2019.00700"},{"key":"30_CR30","doi-asserted-by":"crossref","unstructured":"Shi, Y., Yu, X., Sohn, K., Chandraker, M., Jain, A.K.: Towards universal representation learning for deep face recognition. In: CVPR, pp. 6817\u20136826 (2020)","DOI":"10.1109\/CVPR42600.2020.00685"},{"issue":"9","key":"30_CR31","first-page":"16769","volume":"11","author":"Y Song","year":"2024","unstructured":"Song, Y., Wang, C., Tang, H., Han, S., Li, M., Tong, G.: LLRFaceFormer: lightweight face transformer for real-world low-resolution recognition. IEEE IoT J. 11(9), 16769\u201316787 (2024)","journal-title":"IEEE IoT J."},{"key":"30_CR32","doi-asserted-by":"crossref","unstructured":"Sun, Z., Feng, C., Patras, I., Tzimiropoulos, G.: Lafs: landmark-based facial self-supervised learning for face recognition. In: CVPR, pp. 1639\u20131649 (2024)","DOI":"10.1109\/CVPR52733.2024.00162"},{"key":"30_CR33","unstructured":"Sun, Z., Tzimiropoulos, G.: Part-based face recognition with vision transformers. In: BMVC 2022, p.\u00a0611 (2022)"},{"key":"30_CR34","unstructured":"Tang, Y., et al.: Augmented shortcuts for vision transformers. In: NeurIPS (2021)"},{"key":"30_CR35","doi-asserted-by":"crossref","unstructured":"Wang, C., Fang, H., Zhong, Y., Deng, W.: MLFW: a database for face recognition on masked faces. In: CCBR, pp. 180\u2013188 (2022)","DOI":"10.1007\/978-3-031-20233-9_18"},{"key":"30_CR36","unstructured":"Wang, P., Zheng, W., Chen, T., Wang, Z.: Anti-oversmoothing in deep vision transformers via the Fourier domain analysis: From theory to practice. In: ICLR (2022)"},{"key":"30_CR37","doi-asserted-by":"crossref","unstructured":"Whitelam, C., et\u00a0al.: IARPA Janus benchmark-b face dataset. In: CVPR Workshops, pp. 90\u201398 (2017)","DOI":"10.1109\/CVPRW.2017.87"},{"key":"30_CR38","unstructured":"Yan, H., Gui, L., Li, W., He, Y.: Addressing token uniformity in transformers via singular value transformation. In: UAI, pp. 2181\u20132191 (2022)"},{"key":"30_CR39","unstructured":"Zheng, T., Deng, W.: Cross-pose LFW: a database for studying cross-pose face recognition in unconstrained environments, BUPT, Technical Report p.\u00a05 (2018)"},{"key":"30_CR40","unstructured":"Zheng, T., Deng, W., Hu, J.: Cross-age LFW: a database for studying cross-age face recognition in unconstrained environments. arXiv preprint arXiv:1708.08197 (2017)"},{"key":"30_CR41","unstructured":"Zhong, Y., Deng, W.: Face transformer for recognition. arXiv preprint arXiv:2103.14803 (2021)"},{"key":"30_CR42","unstructured":"Zhou, D., et al.: DeepViT: towards deeper vision transformer. arXiv preprint arXiv:2103.11886 (2021)"},{"key":"30_CR43","doi-asserted-by":"publisher","first-page":"3388","DOI":"10.1109\/TIFS.2023.3280717","volume":"18","author":"Y Zhu","year":"2023","unstructured":"Zhu, Y., Ren, M., Jing, H., Dai, L., Sun, Z., Li, P.: Joint holistic and masked face recognition. IEEE Trans. Inf. Forensics Secur. 18, 3388\u20133400 (2023)","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"30_CR44","doi-asserted-by":"crossref","unstructured":"Zhu, Z., et\u00a0al.: WebFace260M: a benchmark unveiling the power of million-scale deep face recognition. In: CVPR, pp. 10492\u201310502 (2021)","DOI":"10.1109\/CVPR46437.2021.01035"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-5676-2_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T20:32:05Z","timestamp":1768249925000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5676-2_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819556755","9789819556762"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5676-2_30","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":"13 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2025.prcv.cn\/index.asp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}