{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T15:19:57Z","timestamp":1781104797889,"version":"3.54.1"},"publisher-location":"Cham","reference-count":95,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031727535","type":"print"},{"value":"9783031727542","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"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\/978-3-031-72754-2_14","type":"book-chapter","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T14:57:07Z","timestamp":1730300227000},"page":"240-260","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Faceptor: A Generalist Model for\u00a0Face Perception"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-3899-6245","authenticated-orcid":false,"given":"Lixiong","family":"Qin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3559-9346","authenticated-orcid":false,"given":"Mei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1428-3261","authenticated-orcid":false,"given":"Xuannan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4161-5020","authenticated-orcid":false,"given":"Yuhang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3886-6907","authenticated-orcid":false,"given":"Wei","family":"Deng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8870-1759","authenticated-orcid":false,"given":"Xiaoshuai","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9416-7666","authenticated-orcid":false,"given":"Weiran","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5952-6996","authenticated-orcid":false,"given":"Weihong","family":"Deng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,31]]},"reference":[{"key":"14_CR1","doi-asserted-by":"publisher","unstructured":"Acharya, D., Huang, Z., Paudel, D.P., Gool, L.V.: Covariance pooling for facial expression recognition. In: CVPR Workshops, pp. 367\u2013374. Computer Vision Foundation\/IEEE Computer Society (2018). https:\/\/doi.org\/10.1109\/CVPRW.2018.00077","DOI":"10.1109\/CVPRW.2018.00077"},{"key":"14_CR2","unstructured":"Bao, H., Dong, L., Piao, S., Wei, F.: BEiT: BERT pre-training of image transformers. In: ICLR. OpenReview.net (2022)"},{"key":"14_CR3","doi-asserted-by":"publisher","unstructured":"Barsoum, E., Zhang, C., Canton-Ferrer, C., Zhang, Z.: Training deep networks for facial expression recognition with crowd-sourced label distribution. In: ICMI, pp. 279\u2013283. ACM (2016). https:\/\/doi.org\/10.1145\/2993148.2993165","DOI":"10.1145\/2993148.2993165"},{"key":"14_CR4","doi-asserted-by":"publisher","unstructured":"Berg, A., Oskarsson, M., O\u2019Connor, M.: Deep ordinal regression with label diversity. In: ICPR, pp. 2740\u20132747. IEEE (2020). https:\/\/doi.org\/10.1109\/ICPR48806.2021.9412608","DOI":"10.1109\/ICPR48806.2021.9412608"},{"key":"14_CR5","doi-asserted-by":"publisher","unstructured":"Bulat, A., Cheng, S., Yang, J., Garbett, A., Sanchez, E., Tzimiropoulos, G.: Pre-training strategies and datasets for facial representation learning. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13673, pp. 107\u2013125. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19778-9_7","DOI":"10.1007\/978-3-031-19778-9_7"},{"key":"14_CR6","doi-asserted-by":"publisher","unstructured":"Burgos-Artizzu, X.P., Perona, P., Doll\u00e1r, P.: Robust face landmark estimation under occlusion. In: ICCV, pp. 1513\u20131520. IEEE Computer Society (2013). https:\/\/doi.org\/10.1109\/ICCV.2013.191","DOI":"10.1109\/ICCV.2013.191"},{"key":"14_CR7","doi-asserted-by":"publisher","unstructured":"Cao, W., Mirjalili, V., Raschka, S.: Rank consistent ordinal regression for neural networks with application to age estimation. Pattern Recognit. Lett. 140, 325\u2013331 (2020). https:\/\/doi.org\/10.1016\/J.PATREC.2020.11.008","DOI":"10.1016\/J.PATREC.2020.11.008"},{"key":"14_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"14_CR9","unstructured":"Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. In: NeurIPS (2020)"},{"key":"14_CR10","doi-asserted-by":"publisher","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation. In: CVPR, pp. 1280\u20131289. IEEE (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.00135","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"14_CR11","unstructured":"Cheng, B., Schwing, A.G., Kirillov, A.: Per-pixel classification is not all you need for semantic segmentation. In: NeurIPS, pp. 17864\u201317875 (2021)"},{"key":"14_CR12","doi-asserted-by":"publisher","unstructured":"Cubuk, E.D., Zoph, B., Shlens, J., Le, Q.V.: RandAugment: practical automated data augmentation with a reduced search space. In: CVPR Workshops, pp. 3008\u20133017. Computer Vision Foundation\/IEEE (2020). https:\/\/doi.org\/10.1109\/CVPRW50498.2020.00359","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"14_CR13","doi-asserted-by":"publisher","unstructured":"Dapogny, A., Cord, M., Bailly, K.: DeCaFA: deep convolutional cascade for face alignment in the wild. In: ICCV, pp. 6892\u20136900. IEEE (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00699","DOI":"10.1109\/ICCV.2019.00699"},{"key":"14_CR14","doi-asserted-by":"publisher","unstructured":"Deng, J., Guo, J., Xue, N., Zafeiriou, S.: ArcFace: additive angular margin loss for deep face recognition. In: CVPR, pp. 4690\u20134699. Computer Vision Foundation\/IEEE (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00482","DOI":"10.1109\/CVPR.2019.00482"},{"key":"14_CR15","doi-asserted-by":"publisher","unstructured":"Deng, Z., Liu, H., Wang, Y., Wang, C., Yu, Z., Sun, X.: PML: progressive margin loss for long-tailed age classification. In: CVPR, pp. 10503\u201310512. Computer Vision Foundation\/IEEE (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.01036","DOI":"10.1109\/CVPR46437.2021.01036"},{"key":"14_CR16","doi-asserted-by":"publisher","unstructured":"Dong, X., Yan, Y., Ouyang, W., Yang, Y.: Style aggregated network for facial landmark detection. In: CVPR, pp. 379\u2013388. Computer Vision Foundation\/IEEE Computer Society (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00047","DOI":"10.1109\/CVPR.2018.00047"},{"key":"14_CR17","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. In: ICLR. OpenReview.net (2021)"},{"key":"14_CR18","doi-asserted-by":"publisher","unstructured":"Farzaneh, A.H., Qi, X.: Facial expression recognition in the wild via deep attentive center loss. In: WACV, pp. 2401\u20132410. IEEE (2021). https:\/\/doi.org\/10.1109\/WACV48630.2021.00245","DOI":"10.1109\/WACV48630.2021.00245"},{"key":"14_CR19","doi-asserted-by":"publisher","unstructured":"Feng, Z., Kittler, J., Awais, M., Huber, P., Wu, X.: Wing loss for robust facial landmark localisation with convolutional neural networks. In: CVPR, pp. 2235\u20132245. Computer Vision Foundation\/IEEE Computer Society (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00238","DOI":"10.1109\/CVPR.2018.00238"},{"key":"14_CR20","unstructured":"Gao, B., Liu, X., Zhou, H., Wu, J., Geng, X.: Learning expectation of label distribution for facial age and attractiveness estimation. CoRR abs\/2007.01771 (2020)"},{"issue":"6","key":"14_CR21","doi-asserted-by":"publisher","first-page":"2825","DOI":"10.1109\/TIP.2017.2689998","volume":"26","author":"B Gao","year":"2017","unstructured":"Gao, B., Xing, C., Xie, C., Wu, J., Geng, X.: Deep label distribution learning with label ambiguity. IEEE Trans. Image Process. 26(6), 2825\u20132838 (2017). https:\/\/doi.org\/10.1109\/TIP.2017.2689998","journal-title":"IEEE Trans. Image Process."},{"key":"14_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1007\/978-3-319-46487-9_6","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Y Guo","year":"2016","unstructured":"Guo, Y., Zhang, L., Hu, Y., He, X., Gao, J.: MS-Celeb-1M: a dataset and benchmark for large-scale face recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 87\u2013102. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_6"},{"key":"14_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"325","DOI":"10.1007\/978-3-030-58565-5_20","volume-title":"Computer Vision \u2013 ECCV 2020","author":"FK Gustafsson","year":"2020","unstructured":"Gustafsson, F.K., Danelljan, M., Bhat, G., Sch\u00f6n, T.B.: Energy-based models for deep probabilistic regression. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12365, pp. 325\u2013343. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58565-5_20"},{"key":"14_CR24","doi-asserted-by":"publisher","unstructured":"Hand, E.M., Chellappa, R.: Attributes for improved attributes: a multi-task network utilizing implicit and explicit relationships for facial attribute classification. In: AAAI, pp. 4068\u20134074. AAAI Press (2017). https:\/\/doi.org\/10.1609\/AAAI.V31I1.11229","DOI":"10.1609\/AAAI.V31I1.11229"},{"key":"14_CR25","unstructured":"Huang, G.B., Mattar, M., Berg, T., Learned-Miller, E.: Labeled faces in the wild: A database forstudying face recognition in unconstrained environments. In: Workshop on faces in\u2019Real-Life\u2019Images: detection, alignment, and recognition (2008)"},{"key":"14_CR26","doi-asserted-by":"publisher","unstructured":"Huang, Y., Yang, H., Li, C., Kim, J., Wei, F.: ADNet: leveraging error-bias towards normal direction in face alignment. In: ICCV, pp. 3060\u20133070. IEEE (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00307","DOI":"10.1109\/ICCV48922.2021.00307"},{"key":"14_CR27","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: ICML. Proceedings of Machine Learning Research, vol.\u00a0139, pp. 4904\u20134916. PMLR (2021)"},{"issue":"12","key":"14_CR28","doi-asserted-by":"publisher","first-page":"3174","DOI":"10.1007\/S11263-021-01521-4","volume":"129","author":"H Jin","year":"2021","unstructured":"Jin, H., Liao, S., Shao, L.: Pixel-in-pixel net: towards efficient facial landmark detection in the wild. Int. J. Comput. Vis. 129(12), 3174\u20133194 (2021). https:\/\/doi.org\/10.1007\/S11263-021-01521-4","journal-title":"Int. J. Comput. Vis."},{"key":"14_CR29","doi-asserted-by":"publisher","unstructured":"Jr., K.R., Tesafaye, T.: MORPH: a longitudinal image database of normal adult age-progression. In: FGR, pp. 341\u2013345. IEEE Computer Society (2006). https:\/\/doi.org\/10.1109\/FGR.2006.78","DOI":"10.1109\/FGR.2006.78"},{"key":"14_CR30","doi-asserted-by":"publisher","unstructured":"Kowalski, M., Naruniec, J., Trzcinski, T.: Deep alignment network: a convolutional neural network for robust face alignment. In: CVPR Workshops, pp. 2034\u20132043. IEEE Computer Society (2017).https:\/\/doi.org\/10.1109\/CVPRW.2017.254","DOI":"10.1109\/CVPRW.2017.254"},{"key":"14_CR31","doi-asserted-by":"publisher","unstructured":"Kumar, A., et al.: LUVLi face alignment: estimating landmarks\u2019 location, uncertainty, and visibility likelihood. In: CVPR, pp. 8233\u20138243. Computer Vision Foundation\/IEEE (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00826","DOI":"10.1109\/CVPR42600.2020.00826"},{"issue":"10","key":"14_CR32","doi-asserted-by":"publisher","first-page":"1962","DOI":"10.1109\/TPAMI.2011.48","volume":"33","author":"N Kumar","year":"2011","unstructured":"Kumar, N., Berg, A.C., Belhumeur, P.N., Nayar, S.K.: Describable visual attributes for face verification and image search. IEEE Trans. Pattern Anal. Mach. Intell. 33(10), 1962\u20131977 (2011). https:\/\/doi.org\/10.1109\/TPAMI.2011.48","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"14_CR33","doi-asserted-by":"publisher","unstructured":"Lee, C., Liu, Z., Wu, L., Luo, P.: MaskGAN: towards diverse and interactive facial image manipulation. In: CVPR, pp. 5548\u20135557. Computer Vision Foundation\/IEEE (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00559","DOI":"10.1109\/CVPR42600.2020.00559"},{"key":"14_CR34","unstructured":"Lee, S., Kim, C.: Deep repulsive clustering of ordered data based on order-identity decomposition. In: ICLR. OpenReview.net (2021)"},{"key":"14_CR35","doi-asserted-by":"publisher","first-page":"2016","DOI":"10.1109\/TIP.2021.3049955","volume":"30","author":"H Li","year":"2021","unstructured":"Li, H., Wang, N., Ding, X., Yang, X., Gao, X.: Adaptively learning facial expression representation via C-F labels and distillation. IEEE Trans. Image Process. 30, 2016\u20132028 (2021). https:\/\/doi.org\/10.1109\/TIP.2021.3049955","journal-title":"IEEE Trans. Image Process."},{"key":"14_CR36","doi-asserted-by":"publisher","unstructured":"Li, H., Guo, Z., Rhee, S., Han, S., Han, J.: Towards accurate facial landmark detection via cascaded transformers. In: CVPR, pp. 4166\u20134175. IEEE (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.00414","DOI":"10.1109\/CVPR52688.2022.00414"},{"key":"14_CR37","doi-asserted-by":"publisher","unstructured":"Li, S., Deng, W., Du, J.: Reliable crowdsourcing and deep locality-preserving learning for expression recognition in the wild. In: CVPR, pp. 2584\u20132593. IEEE Computer Society (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.277","DOI":"10.1109\/CVPR.2017.277"},{"key":"14_CR38","doi-asserted-by":"publisher","unstructured":"Li, W., Lu, J., Feng, J., Xu, C., Zhou, J., Tian, Q.: BridgeNet: a continuity-aware probabilistic network for age estimation. In: CVPR, pp. 1145\u20131154. Computer Vision Foundation\/IEEE (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00124","DOI":"10.1109\/CVPR.2019.00124"},{"key":"14_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"266","DOI":"10.1007\/978-3-030-58545-7_16","volume-title":"Computer Vision \u2013 ECCV 2020","author":"W Li","year":"2020","unstructured":"Li, W., et al.: Structured landmark detection via topology-adapting deep graph learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 266\u2013283. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58545-7_16"},{"issue":"5","key":"14_CR40","doi-asserted-by":"publisher","first-page":"2439","DOI":"10.1109\/TIP.2018.2886767","volume":"28","author":"Y Li","year":"2019","unstructured":"Li, Y., Zeng, J., Shan, S., Chen, X.: Occlusion aware facial expression recognition using CNN with attention mechanism. IEEE Trans. Image Process. 28(5), 2439\u20132450 (2019). https:\/\/doi.org\/10.1109\/TIP.2018.2886767","journal-title":"IEEE Trans. Image Process."},{"key":"14_CR41","unstructured":"Lim, K., Shin, N., Lee, Y., Kim, C.: Order learning and its application to age estimation. In: ICLR. OpenReview.net (2020)"},{"key":"14_CR42","doi-asserted-by":"publisher","unstructured":"Lin, J., Yang, H., Chen, D., Zeng, M., Wen, F., Yuan, L.: Face parsing with RoI tanh-warping. In: CVPR, pp. 5654\u20135663. Computer Vision Foundation\/IEEE (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00580","DOI":"10.1109\/CVPR.2019.00580"},{"key":"14_CR43","doi-asserted-by":"publisher","unstructured":"Liu, W., Wen, Y., Yu, Z., Li, M., Raj, B., Song, L.: SphereFace: deep hypersphere embedding for face recognition. In: CVPR, pp. 6738\u20136746. IEEE Computer Society (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.713","DOI":"10.1109\/CVPR.2017.713"},{"key":"14_CR44","doi-asserted-by":"publisher","unstructured":"Liu, Y., Shi, H., Shen, H., Si, Y., Wang, X., Mei, T.: A new dataset and boundary-attention semantic segmentation for face parsing. In: AAAI, pp. 11637\u201311644. AAAI Press (2020). https:\/\/doi.org\/10.1609\/AAAI.V34I07.6832","DOI":"10.1609\/AAAI.V34I07.6832"},{"key":"14_CR45","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: ICCV, pp. 3730\u20133738. IEEE Computer Society (2015), https:\/\/doi.org\/10.1109\/ICCV.2015.425","DOI":"10.1109\/ICCV.2015.425"},{"key":"14_CR46","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (Poster). OpenReview.net (2019)"},{"issue":"9","key":"14_CR47","doi-asserted-by":"publisher","first-page":"3135","DOI":"10.3390\/app10093135","volume":"10","author":"L Luo","year":"2020","unstructured":"Luo, L., Xue, D., Feng, X.: EHANet: an effective hierarchical aggregation network for face parsing. Appl. Sci. 10(9), 3135 (2020)","journal-title":"Appl. Sci."},{"issue":"4","key":"14_CR48","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1109\/TAFFC.2018.2820048","volume":"11","author":"U Mahbub","year":"2020","unstructured":"Mahbub, U., Sarkar, S., Chellappa, R.: Segment-based methods for facial attribute detection from partial faces. IEEE Trans. Affect. Comput. 11(4), 601\u2013613 (2020). https:\/\/doi.org\/10.1109\/TAFFC.2018.2820048","journal-title":"IEEE Trans. Affect. Comput."},{"issue":"2","key":"14_CR49","doi-asserted-by":"publisher","first-page":"818","DOI":"10.1109\/TAFFC.2020.2969189","volume":"13","author":"L Mao","year":"2022","unstructured":"Mao, L., Yan, Y., Xue, J., Wang, H.: Deep multi-task multi-label CNN for effective facial attribute classification. IEEE Trans. Affect. Comput. 13(2), 818\u2013828 (2022). https:\/\/doi.org\/10.1109\/TAFFC.2020.2969189","journal-title":"IEEE Trans. Affect. Comput."},{"issue":"1","key":"14_CR50","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/TAFFC.2017.2740923","volume":"10","author":"A Mollahosseini","year":"2019","unstructured":"Mollahosseini, A., Hassani, B., Mahoor, M.H.: AffectNet: a database for facial expression, valence, and arousal computing in the wild. IEEE Trans. Affect. Comput. 10(1), 18\u201331 (2019). https:\/\/doi.org\/10.1109\/TAFFC.2017.2740923","journal-title":"IEEE Trans. Affect. Comput."},{"key":"14_CR51","doi-asserted-by":"publisher","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. 1997\u20132005. IEEE Computer Society (2017). https:\/\/doi.org\/10.1109\/CVPRW.2017.250","DOI":"10.1109\/CVPRW.2017.250"},{"key":"14_CR52","doi-asserted-by":"publisher","unstructured":"Niu, Z., Zhou, M., Wang, L., Gao, X., Hua, G.: Ordinal regression with multiple output CNN for age estimation. In: CVPR, pp. 4920\u20134928. IEEE Computer Society (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.532","DOI":"10.1109\/CVPR.2016.532"},{"key":"14_CR53","unstructured":"van\u00a0den Oord, A., Vinyals, O., Kavukcuoglu, K.: Neural discrete representation learning. In: NIPS, pp. 6306\u20136315 (2017)"},{"key":"14_CR54","doi-asserted-by":"publisher","unstructured":"Pan, H., Han, H., Shan, S., Chen, X.: Mean-variance loss for deep age estimation from a face. In: CVPR, pp. 5285\u20135294. Computer Vision Foundation\/IEEE Computer Society (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00554","DOI":"10.1109\/CVPR.2018.00554"},{"key":"14_CR55","doi-asserted-by":"publisher","unstructured":"Qian, S., Sun, K., Wu, W., Qian, C., Jia, J.: Aggregation via separation: boosting facial landmark detector with semi-supervised style translation. In: ICCV, pp. 10152\u201310162. IEEE (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.01025","DOI":"10.1109\/ICCV.2019.01025"},{"key":"14_CR56","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3304724","author":"L Qin","year":"2023","unstructured":"Qin, L., et al.: SwinFace: a multi-task transformer for face recognition, expression recognition, age estimation and attribute estimation. IEEE Trans. Circuit Syst. Video Technol. (2023). https:\/\/doi.org\/10.1109\/TCSVT.2023.3304724","journal-title":"IEEE Trans. Circuit Syst. Video Technol."},{"key":"14_CR57","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML. Proceedings of Machine Learning Research, vol.\u00a0139, pp. 8748\u20138763. PMLR (2021)"},{"key":"14_CR58","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML. Proceedings of Machine Learning Research, vol.\u00a0139, pp. 8748\u20138763. PMLR (2021)"},{"issue":"1","key":"14_CR59","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1109\/TPAMI.2017.2781233","volume":"41","author":"R Ranjan","year":"2019","unstructured":"Ranjan, R., Patel, V.M., Chellappa, R.: HyperFace: a deep multi-task learning framework for face detection, landmark localization, pose estimation, and gender recognition. IEEE Trans. Pattern Anal. Mach. Intell. 41(1), 121\u2013135 (2019). https:\/\/doi.org\/10.1109\/TPAMI.2017.2781233","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"14_CR60","doi-asserted-by":"publisher","unstructured":"Ranjan, R., Sankaranarayanan, S., Castillo, C.D., Chellappa, R.: An all-in-one convolutional neural network for face analysis. In: FG, pp. 17\u201324. IEEE Computer Society (2017). https:\/\/doi.org\/10.1109\/FG.2017.137","DOI":"10.1109\/FG.2017.137"},{"issue":"2\u20134","key":"14_CR61","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1007\/S11263-016-0940-3","volume":"126","author":"R Rothe","year":"2018","unstructured":"Rothe, R., Timofte, R., Gool, L.V.: Deep expectation of real and apparent age from a single image without facial landmarks. Int. J. Comput. Vis. 126(2\u20134), 144\u2013157 (2018). https:\/\/doi.org\/10.1007\/S11263-016-0940-3","journal-title":"Int. J. Comput. Vis."},{"key":"14_CR62","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/978-3-319-46454-1_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"EM Rudd","year":"2016","unstructured":"Rudd, E.M., G\u00fcnther, M., Boult, T.E.: MOON: a mixed objective optimization network for the recognition of facial attributes. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 19\u201335. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_2"},{"key":"14_CR63","doi-asserted-by":"publisher","unstructured":"Sagonas, C., Tzimiropoulos, G., Zafeiriou, S., Pantic, M.: 300 faces in-the-wild challenge: the first facial landmark localization challenge. In: ICCV Workshops, pp. 397\u2013403. IEEE Computer Society (2013). https:\/\/doi.org\/10.1109\/ICCVW.2013.59","DOI":"10.1109\/ICCVW.2013.59"},{"key":"14_CR64","doi-asserted-by":"publisher","unstructured":"Sengupta, S., Chen, J., Castillo, C.D., Patel, V.M., Chellappa, R., Jacobs, D.W.: Frontal to profile face verification in the wild. In: WACV, pp.\u00a01\u20139. IEEE Computer Society (2016). https:\/\/doi.org\/10.1109\/WACV.2016.7477558","DOI":"10.1109\/WACV.2016.7477558"},{"key":"14_CR65","doi-asserted-by":"publisher","unstructured":"She, J., Hu, Y., Shi, H., Wang, J., Shen, Q., Mei, T.: Dive into ambiguity: Latent distribution mining and pairwise uncertainty estimation for facial expression recognition. In: CVPR, pp. 6248\u20136257. Computer Vision Foundation\/IEEE (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.00618","DOI":"10.1109\/CVPR46437.2021.00618"},{"key":"14_CR66","doi-asserted-by":"publisher","unstructured":"Shen, W., Guo, Y., Wang, Y., Zhao, K., Wang, B., Yuille, A.L.: Deep regression forests for age estimation. In: CVPR, pp. 2304\u20132313. Computer Vision Foundation\/IEEE Computer Society (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00245","DOI":"10.1109\/CVPR.2018.00245"},{"issue":"2","key":"14_CR67","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1109\/TPAMI.2019.2937294","volume":"43","author":"W Shen","year":"2021","unstructured":"Shen, W., Guo, Y., Wang, Y., Zhao, K., Wang, B., Yuille, A.L.: Deep differentiable random forests for age estimation. IEEE Trans. Pattern Anal. Mach. Intell. 43(2), 404\u2013419 (2021). https:\/\/doi.org\/10.1109\/TPAMI.2019.2937294","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"14_CR68","doi-asserted-by":"publisher","unstructured":"Shin, N., Lee, S., Kim, C.: Moving window regression: a novel approach to ordinal regression. In: CVPR, pp. 18739\u201318748. IEEE (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01820","DOI":"10.1109\/CVPR52688.2022.01820"},{"key":"14_CR69","doi-asserted-by":"publisher","first-page":"8236","DOI":"10.1109\/TIP.2021.3113780","volume":"30","author":"G Te","year":"2021","unstructured":"Te, G., Hu, W., Liu, Y., Shi, H., Mei, T.: AGRNet: adaptive graph representation learning and reasoning for face parsing. IEEE Trans. Image Process. 30, 8236\u20138250 (2021). https:\/\/doi.org\/10.1109\/TIP.2021.3113780","journal-title":"IEEE Trans. Image Process."},{"key":"14_CR70","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1007\/978-3-030-58610-2_16","volume-title":"Computer Vision \u2013 ECCV 2020","author":"G Te","year":"2020","unstructured":"Te, G., Liu, Y., Hu, W., Shi, H., Mei, T.: Edge-aware graph representation learning and reasoning for face parsing. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12357, pp. 258\u2013274. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58610-2_16"},{"key":"14_CR71","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS, pp. 5998\u20136008 (2017)"},{"key":"14_CR72","doi-asserted-by":"publisher","unstructured":"Wang, H., et al.: CosFace: large margin cosine loss for deep face recognition. In: CVPR, pp. 5265\u20135274. Computer Vision Foundation\/IEEE Computer Society (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00552","DOI":"10.1109\/CVPR.2018.00552"},{"issue":"10","key":"14_CR73","doi-asserted-by":"publisher","first-page":"3349","DOI":"10.1109\/TPAMI.2020.2983686","volume":"43","author":"J Wang","year":"2021","unstructured":"Wang, J., et al.: Deep high-resolution representation learning for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 43(10), 3349\u20133364 (2021). https:\/\/doi.org\/10.1109\/TPAMI.2020.2983686","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"14_CR74","doi-asserted-by":"publisher","unstructured":"Wang, K., Peng, X., Yang, J., Lu, S., Qiao, Y.: Suppressing uncertainties for large-scale facial expression recognition. In: CVPR, pp. 6896\u20136905. Computer Vision Foundation\/IEEE (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00693","DOI":"10.1109\/CVPR42600.2020.00693"},{"key":"14_CR75","doi-asserted-by":"publisher","first-page":"4057","DOI":"10.1109\/TIP.2019.2956143","volume":"29","author":"K Wang","year":"2020","unstructured":"Wang, K., Peng, X., Yang, J., Meng, D., Qiao, Y.: Region attention networks for pose and occlusion robust facial expression recognition. IEEE Trans. Image Process. 29, 4057\u20134069 (2020). https:\/\/doi.org\/10.1109\/TIP.2019.2956143","journal-title":"IEEE Trans. Image Process."},{"key":"14_CR76","doi-asserted-by":"publisher","unstructured":"Wang, W., Sebe, N., Lepri, B.: Rethinking the learning paradigm for facial expression recognition. CoRR abs\/2209.15402 (2022). https:\/\/doi.org\/10.48550\/ARXIV.2209.15402","DOI":"10.48550\/ARXIV.2209.15402"},{"key":"14_CR77","doi-asserted-by":"publisher","unstructured":"Wang, X., Bo, L., Li, F.: Adaptive wing loss for robust face alignment via heatmap regression. In: ICCV, pp. 6970\u20136980. IEEE (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00707","DOI":"10.1109\/ICCV.2019.00707"},{"issue":"9","key":"14_CR78","doi-asserted-by":"publisher","first-page":"4659","DOI":"10.1109\/TIP.2019.2909652","volume":"28","author":"Z Wei","year":"2019","unstructured":"Wei, Z., Liu, S., Sun, Y., Ling, H.: Accurate facial image parsing at real-time speed. IEEE Trans. Image Process. 28(9), 4659\u20134670 (2019). https:\/\/doi.org\/10.1109\/TIP.2019.2909652","journal-title":"IEEE Trans. Image Process."},{"key":"14_CR79","doi-asserted-by":"publisher","unstructured":"Wu, W., Qian, C., Yang, S., Wang, Q., Cai, Y., Zhou, Q.: Look at boundary: a boundary-aware face alignment algorithm. In: CVPR, pp. 2129\u20132138. Computer Vision Foundation\/IEEE Computer Society (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00227","DOI":"10.1109\/CVPR.2018.00227"},{"key":"14_CR80","doi-asserted-by":"publisher","unstructured":"Wu, W., Qian, C., Yang, S., Wang, Q., Cai, Y., Zhou, Q.: Look at boundary: a boundary-aware face alignment algorithm. In: CVPR, pp. 2129\u20132138. Computer Vision Foundation\/IEEE Computer Society (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00227","DOI":"10.1109\/CVPR.2018.00227"},{"key":"14_CR81","doi-asserted-by":"publisher","unstructured":"Xia, J., Qu, W., Huang, W., Zhang, J., Wang, X., Xu, M.: Sparse local patch transformer for robust face alignment and landmarks inherent relation learning. In: CVPR, pp. 4042\u20134051. IEEE (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.00402","DOI":"10.1109\/CVPR52688.2022.00402"},{"key":"14_CR82","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":"14_CR83","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1007\/978-3-030-01261-8_14","volume-title":"Computer Vision \u2013 ECCV 2018","author":"J Zeng","year":"2018","unstructured":"Zeng, J., Shan, S., Chen, X.: Facial expression recognition with\u00a0inconsistently annotated datasets. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 227\u2013243. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01261-8_14"},{"issue":"5","key":"14_CR84","doi-asserted-by":"publisher","first-page":"2447","DOI":"10.1007\/S11760-022-02461-3","volume":"17","author":"C Zhang","year":"2023","unstructured":"Zhang, C., Zhong, W., Li, C., Deng, H.: Random walk-based erasing data augmentation for deep learning. Signal Image Video Process. 17(5), 2447\u20132454 (2023). https:\/\/doi.org\/10.1007\/S11760-022-02461-3","journal-title":"Signal Image Video Process."},{"key":"14_CR85","doi-asserted-by":"publisher","unstructured":"Zhang, N., Paluri, M., Ranzato, M., Darrell, T., Bourdev, L.D.: PANDA: pose aligned networks for deep attribute modeling. In: CVPR, pp. 1637\u20131644. IEEE Computer Society (2014). https:\/\/doi.org\/10.1109\/CVPR.2014.212","DOI":"10.1109\/CVPR.2014.212"},{"key":"14_CR86","unstructured":"Zhang, Y., Wang, C., Deng, W.: Relative uncertainty learning for facial expression recognition. In: NeurIPS, pp. 17616\u201317627 (2021)"},{"key":"14_CR87","doi-asserted-by":"publisher","unstructured":"Zhang, Y., Wang, C., Ling, X., Deng, W.: Learn from all: erasing attention consistency for noisy label facial expression recognition. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision - ECCV 2022. ECCV 2022. LNCS, vol. 13686, pp. 418\u2013434. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19809-0_24","DOI":"10.1007\/978-3-031-19809-0_24"},{"key":"14_CR88","doi-asserted-by":"publisher","unstructured":"Zhang, Z., Song, Y., Qi, H.: Age progression\/regression by conditional adversarial autoencoder. In: CVPR, pp. 4352\u20134360. IEEE Computer Society (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.463","DOI":"10.1109\/CVPR.2017.463"},{"key":"14_CR89","doi-asserted-by":"publisher","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: CVPR, pp. 6230\u20136239. IEEE Computer Society (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.660","DOI":"10.1109\/CVPR.2017.660"},{"key":"14_CR90","doi-asserted-by":"publisher","unstructured":"Zheng, Q., Deng, J., Zhu, Z., Li, Y., Zafeiriou, S.: Decoupled multi-task learning with cyclical self-regulation for face parsing. In: CVPR, pp. 4146\u20134155. IEEE (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.00412","DOI":"10.1109\/CVPR52688.2022.00412"},{"key":"14_CR91","unstructured":"Zheng, T., Deng, W.: Cross-pose LFW: A database for studying cross-pose face recognition in unconstrained environments. Beijing University of Posts and Telecommunications, Tech. Rep 5, 7 (2018)"},{"key":"14_CR92","unstructured":"Zheng, T., Deng, W., Hu, J.: Cross-age LFW: A database for studying cross-age face recognition in unconstrained environments. CoRR abs\/1708.08197 (2017)"},{"key":"14_CR93","doi-asserted-by":"publisher","unstructured":"Zheng, Y., et al.: General facial representation learning in a visual-linguistic manner. In: CVPR, pp. 18676\u201318688. IEEE (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01814","DOI":"10.1109\/CVPR52688.2022.01814"},{"key":"14_CR94","doi-asserted-by":"publisher","unstructured":"Zhu, S., Li, C., Loy, C.C., Tang, X.: Unconstrained face alignment via cascaded compositional learning. In: CVPR, pp. 3409\u20133417. IEEE Computer Society (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.371","DOI":"10.1109\/CVPR.2016.371"},{"key":"14_CR95","doi-asserted-by":"publisher","unstructured":"Zhuang, N., Yan, Y., Chen, S., Wang, H.: Multi-task learning of cascaded CNN for facial attribute classification. In: ICPR, pp. 2069\u20132074. IEEE Computer Society (2018). https:\/\/doi.org\/10.1109\/ICPR.2018.8545271","DOI":"10.1109\/ICPR.2018.8545271"}],"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\/978-3-031-72754-2_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T15:05:22Z","timestamp":1730300722000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72754-2_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,31]]},"ISBN":["9783031727535","9783031727542"],"references-count":95,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72754-2_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,31]]},"assertion":[{"value":"31 October 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"}}]}}