{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T03:48:07Z","timestamp":1774410487045,"version":"3.50.1"},"publisher-location":"Cham","reference-count":92,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031876561","type":"print"},{"value":"9783031876578","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\/978-3-031-87657-8_27","type":"book-chapter","created":{"date-parts":[[2025,5,9]],"date-time":"2025-05-09T05:07:27Z","timestamp":1746767247000},"page":"386-401","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Self-supervised Auxiliary Learning for\u00a0Texture and\u00a0Model-Based Hybrid Robust and\u00a0Fair Featuring in\u00a0Face Analysis"],"prefix":"10.1007","author":[{"given":"Shukesh","family":"Reddy","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nishit","family":"Poddar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Srijan","family":"Das","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abhijit","family":"Das","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,10]]},"reference":[{"key":"27_CR1","first-page":"09","volume":"33","author":"B Abirami","year":"2020","unstructured":"Abirami, B., Subashini, T., Mahavaishnavi, V.: Gender and age prediction from real time facial images using CNN. Mater. Today Proc. 33, 09 (2020)","journal-title":"Mater. Today Proc."},{"key":"27_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"469","DOI":"10.1007\/978-3-540-24670-1_36","volume-title":"Computer Vision - ECCV 2004","author":"T Ahonen","year":"2004","unstructured":"Ahonen, T., Hadid, A., Pietik\u00e4inen, M.: Face recognition with local binary patterns. In: Pajdla, T., Matas, J. (eds.) ECCV 2004. LNCS, vol. 3021, pp. 469\u2013481. Springer, Heidelberg (2004). https:\/\/doi.org\/10.1007\/978-3-540-24670-1_36"},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lu\u010di\u0107, M., Schmid, C.: A video vision transformer, Vivit (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"27_CR4","doi-asserted-by":"crossref","unstructured":"Aashutosh, A.V., Das, S., Das, A., et\u00a0al.: Latent flow diffusion for deepfake video generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3781\u20133790 (2024)","DOI":"10.1109\/CVPRW63382.2024.00382"},{"key":"27_CR5","doi-asserted-by":"crossref","unstructured":"Balaji, P., Das, A., Das, S., Dantcheva, A.: Attending generalizability in course of deep fake detection by exploring multi-task learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 475\u2013484 (2023)","DOI":"10.1109\/ICCVW60793.2023.00054"},{"key":"27_CR6","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? (2021)"},{"key":"27_CR7","doi-asserted-by":"publisher","first-page":"325","DOI":"10.1016\/j.patrec.2020.11.008","volume":"140","author":"W Cao","year":"2020","unstructured":"Cao, W., Mirjalili, V., Raschka, S.: Rank consistent ordinal regression for neural networks with application to age estimation. Pattern Recogn. Lett. 140, 325\u2013331 (2020)","journal-title":"Pattern Recogn. Lett."},{"key":"27_CR8","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"27_CR9","doi-asserted-by":"crossref","unstructured":"Chen, L.-C., Yang, Y., Wang, J., Xu, W., Yuille, A.L.: Attention to scale: scale-aware semantic image segmentation. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3640\u20133649 (2016)","DOI":"10.1109\/CVPR.2016.396"},{"key":"27_CR10","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: Daum\u00e9 III, H., Singh, A., (eds.), Proceedings of the 37th International Conference on Machine Learning, vol. 119. Proceedings of Machine Learning Research, pp. 1597\u20131607. PMLR, 13\u201318 July 2020"},{"key":"27_CR11","unstructured":"Cheng, B., Schwing, A.G., Kirillov, A.: Per-pixel classification is not all you need for semantic segmentation (2021)"},{"key":"27_CR12","doi-asserted-by":"crossref","unstructured":"Cui, K., Rongliang, W., Zhan, F., Lu, S.: Face transformer: towards high fidelity and accurate face swapping (2023)","DOI":"10.1109\/CVPRW59228.2023.00074"},{"key":"27_CR13","doi-asserted-by":"crossref","unstructured":"Dai, R., Das, S., Kahatapitiya, K., Ryoo, M.S., Bremond, F.: Multi-scale temporal convtransformer for action detection, MS-TCT (2022)","DOI":"10.1109\/CVPR52688.2022.01941"},{"key":"27_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"573","DOI":"10.1007\/978-3-030-11009-3_35","volume-title":"Computer Vision \u2013 ECCV 2018 Workshops","author":"A Das","year":"2019","unstructured":"Das, A., Dantcheva, A., Bremond, F.: Mitigating bias in gender, age and ethnicity classification: a multi-task convolution neural network approach. In: Leal-Taix\u00e9, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11129, pp. 573\u2013585. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-11009-3_35"},{"key":"27_CR15","doi-asserted-by":"crossref","unstructured":"Das, A., Das, S., Dantcheva, A.: Demystifying attention mechanisms for deepfake detection. In: 2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021), pp. 1\u20137. IEEE (2021)","DOI":"10.1109\/FG52635.2021.9667026"},{"key":"27_CR16","doi-asserted-by":"crossref","unstructured":"Das, A., Lu, H., Han, H., Dantcheva, A., Shan, S., Chen, X.: BVPnet: video-to-BVP signal prediction for remote heart rate estimation. In: 2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021), pp. 1\u20138. IEEE (2021)","DOI":"10.1109\/FG52635.2021.9666996"},{"issue":"5","key":"27_CR17","doi-asserted-by":"publisher","first-page":"2561","DOI":"10.1109\/TCSVT.2021.3082857","volume":"32","author":"A Das","year":"2021","unstructured":"Das, A., et al.: A spatio-temporal approach for apathy classification. IEEE Trans. Circuits Syst. Video Technol. 32(5), 2561\u20132573 (2021)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"27_CR18","doi-asserted-by":"crossref","unstructured":"Das, S., et al.: Limited data, unlimited potential: a study on ViTs augmented by masked autoencoders. In: 2024 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV) (2024)","DOI":"10.1109\/WACV57701.2024.00673"},{"key":"27_CR19","unstructured":"Dolhansky, B., Bitton, J., Pflaum, B., Lu, J., Wang, M., Ferrer, C.C.: The deepfake detection challenge dataset, Russ Howes (2020)"},{"key":"27_CR20","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale (2021)"},{"issue":"8","key":"27_CR21","doi-asserted-by":"publisher","first-page":"1724","DOI":"10.1364\/JOSAA.14.001724","volume":"14","author":"K Etemad","year":"1997","unstructured":"Etemad, K., Chellappa, R.: Discriminant analysis for recognition of human face images. J. Opt. Soc. Am. A 14(8), 1724\u20131733 (1997)","journal-title":"J. Opt. Soc. Am. A"},{"key":"27_CR22","doi-asserted-by":"crossref","unstructured":"Fan, H., et al.: Multiscale vision transformers (2021)","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"27_CR23","unstructured":"Gani, H., Naseer, M., Yaqub, M.: How to train vision transformer on small-scale datasets? arXiv preprint: arXiv:2210.07240 (2022)"},{"key":"27_CR24","unstructured":"Gao, P., Ma, T., Li, H., Dai, J., Qiao, Y.: Convmae: masked convolution meets masked autoencoders. arXiv preprint: arXiv:2205.03892 (2022)"},{"key":"27_CR25","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"27_CR26","first-page":"21271","volume":"33","author":"J-B Grill","year":"2020","unstructured":"Grill, J.-B., et al.: Bootstrap your own latent-a new approach to self-supervised learning. Adv. Neural Inf. Proces. Syst. 33, 21271\u201321284 (2020)","journal-title":"Adv. Neural Inf. Proces. Syst."},{"key":"27_CR27","doi-asserted-by":"crossref","unstructured":"Happy, S.L., Dantcheva, A., Das, A., Bremond, F., Zeghari, R., Robert, P.: Apathy classification by exploiting task relatedness. In: 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020), pp. 489\u2013494. IEEE (2020)","DOI":"10.1109\/FG47880.2020.00116"},{"key":"27_CR28","doi-asserted-by":"crossref","unstructured":"Happy, S.L., Dantcheva, A., Das, A., Zeghari, R., Robert, P., Bremond, F.: Characterizing the state of apathy with facial expression and motion analysis. In: 2019 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019), pp. 1\u20138. IEEE (2019)","DOI":"10.1109\/FG.2019.8756545"},{"key":"27_CR29","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":"27_CR30","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"27_CR31","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"27_CR32","doi-asserted-by":"crossref","unstructured":"Hsieh, H.-L., Hsu, W., Chen, Y.-Y.: Multi-task learning for face identification and attribute estimation. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2981\u20132985 (2017)","DOI":"10.1109\/ICASSP.2017.7952703"},{"key":"27_CR33","doi-asserted-by":"crossref","unstructured":"Jabid, T., Kabir, M.H., Chae, O.: Local directional pattern (LDP) - a robust image descriptor for object recognition. In: 2010 7th IEEE International Conference on Advanced Video and Signal Based Surveillance, pp. 482\u2013487 (2010)","DOI":"10.1109\/AVSS.2010.17"},{"key":"27_CR34","doi-asserted-by":"crossref","unstructured":"Juefei-Xu, F., Boddeti, V.N., Savvides, M.: Local binary convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 19\u201328 (2017)","DOI":"10.1109\/CVPR.2017.456"},{"key":"27_CR35","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In Pereira, F., Burges, C.J., Bottou, L., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, vol. 25. Curran Associates, Inc. (2012)"},{"key":"27_CR36","doi-asserted-by":"crossref","unstructured":"Kuckreja, K., Hoque, X., Poddar, N., Reddy, S., Dhall, A., Das, A.: Indiface: illuminating India\u2019s deepfake landscape with a comprehensive synthetic dataset. In: 2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG), pp. 1\u20139. IEEE (2024)","DOI":"10.1109\/FG59268.2024.10582046"},{"key":"27_CR37","doi-asserted-by":"crossref","unstructured":"Kumar, A., et al.: Luvli face alignment: estimating landmarks\u2019 location, uncertainty, and visibility likelihood. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2020","DOI":"10.1109\/CVPR42600.2020.00826"},{"key":"27_CR38","doi-asserted-by":"crossref","unstructured":"Kuprashevich, M., Tolstykh, I.: Mivolo: multi-input transformer for age and gender estimation (2023)","DOI":"10.1007\/978-3-031-54534-4_15"},{"key":"27_CR39","unstructured":"Lan, X., Qinghao, H., Chen, Q., Xue, J., Cheng, J.: Towards more accurate face alignment via heatmap in heatmap, Hih (2022)"},{"key":"27_CR40","unstructured":"Lee, S.H., Lee, S., Song, B.C.: Vision transformer for small-size datasets. CoRR, abs\/2112.13492 (2021)"},{"key":"27_CR41","doi-asserted-by":"crossref","unstructured":"Levi, G., Hassncer, T.: Age and gender classification using convolutional neural networks. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 34\u201342 (2015)","DOI":"10.1109\/CVPRW.2015.7301352"},{"key":"27_CR42","doi-asserted-by":"publisher","unstructured":"Li, K., Yu, R., Wang, Z., Yuan, L., Song, G., Chen, J.: Locality guidance for improving vision transformers on tiny datasets. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision. ECCV 2022. LNCS, vol. 13684, pp. 110\u2013127. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20053-3_7","DOI":"10.1007\/978-3-031-20053-3_7"},{"key":"27_CR43","doi-asserted-by":"crossref","unstructured":"Li, W., Huang, X., Lu, J., Feng, J., Zhou, J.: Learning probabilistic ordinal embeddings for uncertainty-aware regression (2021)","DOI":"10.1109\/CVPR46437.2021.01368"},{"key":"27_CR44","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Mvitv2: Improved multiscale vision transformers for classification and detection (2022)","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"27_CR45","doi-asserted-by":"crossref","unstructured":"Lin, J., Yang, H., Chen, D., Wen, F., Yuan, L., Zeng, M.: Face parsing with ROI tanh-warping (2019)","DOI":"10.1109\/CVPR.2019.00580"},{"key":"27_CR46","unstructured":"Liu, Y., Sangineto, E., Bi, W., Sebe, N., Lepri, B., De\u00a0Nadai, M.: Efficient training of visual transformers with small datasets. In: Conference on Neural Information Processing Systems (NeurIPS) (2021)"},{"key":"27_CR47","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9992\u201310002 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"27_CR48","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Video Swin transformer (2021)","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"27_CR49","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: Proceedings of International Conference on Computer Vision (ICCV), December 2015","DOI":"10.1109\/ICCV.2015.425"},{"key":"27_CR50","doi-asserted-by":"crossref","unstructured":"Mi, C., et al.: Visibility prediction based on landmark detection in foggy weather. In: 2020 International Conference on Robots and Intelligent System (ICRIS), pp. 134\u2013137 (2020)","DOI":"10.1109\/ICRIS52159.2020.00041"},{"key":"27_CR51","unstructured":"Ming, Z., Xia, J., Luqman, M.M., Burie, J.-C., Zhao, K.: Dynamic multi-task learning for face recognition with facial expression (2019)"},{"issue":"8","key":"27_CR52","doi-asserted-by":"publisher","first-page":"1979","DOI":"10.1109\/TPAMI.2018.2858821","volume":"41","author":"T Miyato","year":"2019","unstructured":"Miyato, T., Maeda, S.-I., Koyama, M., Ishii, S.: Virtual adversarial training: a regularization method for supervised and semi-supervised learning. IEEE Trans. Pattern Anal. Mach. Intell. 41(8), 1979\u20131993 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"27_CR53","doi-asserted-by":"crossref","unstructured":"Mollahosseini, A., Hasani, B., Mahoor, M.H.: Affectnet: a database for facial expression, valence, and arousal computing in the wild. In: Proceedings of the IEEE Conference on Affective Computing, pp. 18\u201331 (2019)","DOI":"10.1109\/TAFFC.2017.2740923"},{"key":"27_CR54","doi-asserted-by":"crossref","unstructured":"Murphy-Chutorian, E., Doshi, A., Trivedi, M.: Head pose estimation for driver assistance systems: A robust algorithm and experimental evaluation. In: IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC, pp. 709 \u2013 714, November 2007","DOI":"10.1109\/ITSC.2007.4357803"},{"key":"27_CR55","doi-asserted-by":"crossref","unstructured":"Niu, X., et al.: Robust remote heart rate estimation from face utilizing spatial-temporal attention. In: 2019 14th IEEE international conference on automatic face & gesture recognition (FG 2019), pp. 1\u20138. IEEE (2019)","DOI":"10.1109\/FG.2019.8756554"},{"key":"27_CR56","doi-asserted-by":"crossref","unstructured":"Noroozi, M., Favaro, P.: Unsupervised learning of visual representations by solving jigsaw puzzles (2017)","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"27_CR57","doi-asserted-by":"crossref","unstructured":"Ojala, T., Pietikainen, M., Harwood, D.: Performance evaluation of texture measures with classification based on kullback discrimination of distributions. In: Proceedings of 12th International Conference on Pattern Recognition, vol. 1, pp. 582\u2013585. IEEE (1994)","DOI":"10.1109\/ICPR.1994.576366"},{"key":"27_CR58","unstructured":"Park, N., Kim, S.: How do vision transformers work? (2022)"},{"key":"27_CR59","doi-asserted-by":"crossref","unstructured":"Rachalwar, H., Fang, M., Damer, N., Das, A.: Depth-guided robust face morphing attack detection. In: 2023 IEEE International Joint Conference on Biometrics (IJCB), pp. 1\u20139. IEEE (2023)","DOI":"10.1109\/IJCB57857.2023.10449186"},{"key":"27_CR60","doi-asserted-by":"crossref","unstructured":"Ranasinghe, K., Naseer, M., Khan, F.S., Ryoo, M., Khan, S.: Self-supervised video transformer (2022)","DOI":"10.1109\/CVPR52688.2022.00289"},{"issue":"1","key":"27_CR61","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)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"27_CR62","doi-asserted-by":"crossref","unstructured":"Ranjan, R., Sankaranarayanan, S., Castillo, C.D., Chellappa, R.: An all-in-one convolutional neural network for face analysis. In: 2017 12th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2017), pp. 17\u201324 (2017)","DOI":"10.1109\/FG.2017.137"},{"key":"27_CR63","doi-asserted-by":"crossref","unstructured":"Ravi, R., Yadhukrishna, S.V., et\u00a0al.: A face expression recognition using CNN & LBP. In: 2020 Fourth International Conference on Computing Methodologies and Communication (ICCMC), pp. 684\u2013689. IEEE (2020)","DOI":"10.1109\/ICCMC48092.2020.ICCMC-000127"},{"key":"27_CR64","doi-asserted-by":"crossref","unstructured":"R\u00f6ssler, A., Cozzolino, D., Verdoliva, L., Riess, C., Thies, J., Nie\u00dfner, M.: FaceForensics++: learning to detect manipulated facial images. In: International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00009"},{"key":"27_CR65","doi-asserted-by":"publisher","unstructured":"Roy, R., Joshi, I., Das, A., Dantcheva, A.: 3d CNN architectures and attention mechanisms for deepfake detection. In Rathgeb, C., Tolosana, R., Vera-Rodriguez, R., Busch, C. (eds.) Handbook of Digital Face Manipulation and Detection. Advances in Computer Vision and Pattern Recognition, pp. 213\u2013234. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-030-87664-7_10","DOI":"10.1007\/978-3-030-87664-7_10"},{"key":"27_CR66","unstructured":"Ryoo, M., Piergiovanni, A.J., Arnab, A., Dehghani, M., Angelova, A.: okenlearner: adaptive space-time tokenization for videos. In: Ranzato, M., Beygelzimer, A., Dauphin, Y., Liang, P.S., Wortman Vaughan, J. (eds.), Advances in Neural Information Processing Systems, vol. 34, pp. 12786\u201312797. Curran Associates, Inc. (2021)"},{"key":"27_CR67","doi-asserted-by":"crossref","unstructured":"Schroff, F., Kalenichenko, D., Philbin, J.: Facenet: a unified embedding for face recognition and clustering. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, June 2015","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"27_CR68","doi-asserted-by":"crossref","unstructured":"Shu, Y., Yan, Y., Chen, S., Xue, J.-H., Shen, C., Wang, H.: Learning spatial-semantic relationship for facial attribute recognition with limited labeled data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11916\u201311925, June 2021","DOI":"10.1109\/CVPR46437.2021.01174"},{"key":"27_CR69","doi-asserted-by":"publisher","first-page":"5366","DOI":"10.3390\/app11125366","volume":"11","author":"D Strazdas","year":"2021","unstructured":"Strazdas, D., Hintz, J., Al-Hamadi, A.: Robo-hud: Interaction concept for contactless operation of industrial cobotic systems. Appl. Sci. 11, 5366 (2021)","journal-title":"Appl. Sci."},{"key":"27_CR70","unstructured":"Sun, Y., Chen, Y., Wang, X., Tang, X.: Deep learning face representation by joint identification-verification. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N., Weinberger, K.Q., (eds.) Advances in Neural Information Processing Systems, vol. 27. Curran Associates, Inc. (2014)"},{"key":"27_CR71","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions (2014)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"27_CR72","doi-asserted-by":"crossref","unstructured":"Taigman, Y., Yang, M., Ranzato, M.A., Wolf, L.: DeepFace: closing the gap to human-level performance in face verification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2014","DOI":"10.1109\/CVPR.2014.220"},{"key":"27_CR73","unstructured":"Tong, Z., Song, Y., Wang, J., Wang, L.: Videomae: masked autoencoders are data-efficient learners for self-supervised video pre-training. arXiv preprint: arXiv:2203.12602 (2022)"},{"key":"27_CR74","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention (2021)"},{"key":"27_CR75","unstructured":"Turk, M.A., Pentland, A.P.: Face recognition using eigenfaces. In: Proceedings of 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 586\u2013591 (1991)"},{"key":"27_CR76","doi-asserted-by":"crossref","unstructured":"van\u00a0de Sande, K.E.A., Uijlings, J.R.R., Gevers, T., Smeulders, A.W.M.: Segmentation as selective search for object recognition. In: 2011 International Conference on Computer Vision, pp. 1879\u20131886 (2011)","DOI":"10.1109\/ICCV.2011.6126456"},{"key":"27_CR77","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"issue":"3","key":"27_CR78","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1007\/s41095-022-0274-8","volume":"8","author":"W Wang","year":"2022","unstructured":"Wang, W., et al.: PVT v2: improved baselines with pyramid vision transformer. Comput. Visual Media 8(3), 415\u2013424 (2022)","journal-title":"Comput. Visual Media"},{"key":"27_CR79","doi-asserted-by":"crossref","unstructured":"Wood, E., et al.: 3d face reconstruction with dense landmarks (2022)","DOI":"10.1007\/978-3-031-19778-9_10"},{"key":"27_CR80","unstructured":"Xie, E., et al.: SegFormer: simple and efficient design for semantic segmentation with transformers (2021)"},{"key":"27_CR81","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":"27_CR82","doi-asserted-by":"crossref","unstructured":"Yan, X., Yang, J., Sohn, K., Lee, H.: Attribute2image: conditional image generation from visual attributes (2016)","DOI":"10.1007\/978-3-319-46493-0_47"},{"key":"27_CR83","doi-asserted-by":"crossref","unstructured":"Yin, X., Huang, D., Fu, Z., Wang, Y., Chen, L.: Segmentation-reconstruction-guided facial image de-occlusion. In: 2023 IEEE 17th International Conference on Automatic Face and Gesture Recognition (FG), pp. 1\u20138. IEEE Press (2023)","DOI":"10.1109\/FG57933.2023.10042570"},{"key":"27_CR84","doi-asserted-by":"crossref","unstructured":"Yuan, L., et al.: Tokens-to-token ViT: training vision transformers from scratch on imagenet (2021)","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"27_CR85","doi-asserted-by":"crossref","unstructured":"Zhang, C., Liu, H., Deng, Y., Xie, B., Li, Y.: TokenHPE: learning orientation tokens for efficient head pose estimation via transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8897\u20138906, June 2023","DOI":"10.1109\/CVPR52729.2023.00859"},{"key":"27_CR86","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1007\/978-3-319-10599-4_7","volume-title":"Computer Vision \u2013 ECCV 2014","author":"Z Zhang","year":"2014","unstructured":"Zhang, Z., Luo, P., Loy, C.C., Tang, X.: Facial landmark detection by deep multi-task learning. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 94\u2013108. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10599-4_7"},{"key":"27_CR87","doi-asserted-by":"crossref","unstructured":"Zhao, R., Liu, T., Xiao, J., Lun, D.P.K., Lam, K.-M.: Deep multi-task learning for facial expression recognition and synthesis based on selective feature sharing (2021)","DOI":"10.1109\/ICPR48806.2021.9413000"},{"key":"27_CR88","doi-asserted-by":"crossref","unstructured":"Zheng, Q., Deng, J., Zhu, Z., Li, Y., Zafeiriou, S.: Decoupled multi-task learning with cyclical self-regulation for face parsing (2022)","DOI":"10.1109\/CVPR52688.2022.00412"},{"key":"27_CR89","unstructured":"Zhou, D., et al.: DeepViT: towards deeper vision transformer (2021)"},{"key":"27_CR90","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Li, H., Liu, H., Wang, N., Gang, Y., Ji, R.: Star loss: reducing semantic ambiguity in facial landmark detection (2023)","DOI":"10.1109\/CVPR52729.2023.01485"},{"key":"27_CR91","doi-asserted-by":"crossref","unstructured":"Zhu, P., Abdal, R., Qin, Y., Wonka, P.: Sean: image synthesis with semantic region-adaptive normalization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2020","DOI":"10.1109\/CVPR42600.2020.00515"},{"key":"27_CR92","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection (2021)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition. ICPR 2024 International Workshops and Challenges"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-87657-8_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,9]],"date-time":"2025-05-09T05:08:38Z","timestamp":1746767318000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-87657-8_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031876561","9783031876578"],"references-count":92,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-87657-8_27","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":"10 May 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}