{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,12]],"date-time":"2026-04-12T18:30:03Z","timestamp":1776018603767,"version":"3.50.1"},"publisher-location":"Cham","reference-count":93,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031250743","type":"print"},{"value":"9783031250750","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-25075-0_12","type":"book-chapter","created":{"date-parts":[[2023,2,19]],"date-time":"2023-02-19T09:16:53Z","timestamp":1676798213000},"page":"157-172","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":75,"title":["ABAW: Learning from\u00a0Synthetic Data & Multi-task Learning Challenges"],"prefix":"10.1007","author":[{"given":"Dimitrios","family":"Kollias","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,2,19]]},"reference":[{"key":"12_CR1","doi-asserted-by":"crossref","unstructured":"Antoniadis, P., Pikoulis, I., Filntisis, P.P., Maragos, P.: An audiovisual and contextual approach for categorical and continuous emotion recognition in-the-wild. arXiv preprint arXiv:2107.03465 (2021)","DOI":"10.1109\/ICCVW54120.2021.00407"},{"key":"12_CR2","unstructured":"Caridakis, G., Raouzaiou, A., Karpouzis, K., Kollias, S.: Synthesizing gesture expressivity based on real sequences. In: Workshop Programme, vol. 10, p. 19"},{"key":"12_CR3","unstructured":"Chang, Y., Wu, Y., Miao, X., Wang, J., Wang, S.: Multi-task learning for emotion descriptors estimation at the fourth ABAW challenge. arXiv preprint arXiv:2207.09716 (2022)"},{"key":"12_CR4","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780195112719.001.0001","volume-title":"The Expression of the Emotions in Man and Animals","author":"C Darwin","year":"1998","unstructured":"Darwin, C., Prodger, P.: The Expression of the Emotions in Man and Animals. Oxford University Press, Oxford (1998)"},{"key":"12_CR5","unstructured":"Deng, D.: Multiple emotion descriptors estimation at the ABAW3 challenge. arXiv preprint arXiv:2203.12845 (2022)"},{"key":"12_CR6","unstructured":"Deng, D., Chen, Z., Shi, B.E.: FAU, facial expressions, valence and arousal: a multi-task solution. arXiv preprint arXiv:2002.03557 (2020)"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Deng, D., Chen, Z., Shi, B.E.: Multitask emotion recognition with incomplete labels. In: 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020), pp. 592\u2013599. IEEE (2020)","DOI":"10.1109\/FG47880.2020.00131"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Deng, D., Shi, B.E.: Estimating multiple emotion descriptors by separating description and inference. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 2392\u20132400, June 2022","DOI":"10.1109\/CVPRW56347.2022.00267"},{"key":"12_CR9","unstructured":"Deng, D., Wu, L., Shi, B.E.: Towards better uncertainty: iterative training of efficient networks for multitask emotion recognition. arXiv preprint arXiv:2108.04228 (2021)"},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Ververas, E., Kotsia, I., Zafeiriou, S.: RetinaFace: single-shot multi-level face localisation in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5203\u20135212 (2020)","DOI":"10.1109\/CVPR42600.2020.00525"},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"Do, N.T., Nguyen-Quynh, T.T., Kim, S.H.: Affective expression analysis in-the-wild using multi-task temporal statistical deep learning model. In: 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020), pp. 624\u2013628. IEEE (2020)","DOI":"10.1109\/FG47880.2020.00093"},{"key":"12_CR12","unstructured":"Dresvyanskiy, D., Ryumina, E., Kaya, H., Markitantov, M., Karpov, A., Minker, W.: An audio-video deep and transfer learning framework for multimodal emotion recognition in the wild. arXiv preprint arXiv:2010.03692 (2020)"},{"key":"12_CR13","unstructured":"Ekman, P.: Facial action coding system (FACS). A human face (2002)"},{"key":"12_CR14","volume-title":"The Emotions","author":"NH Frijda","year":"1986","unstructured":"Frijda, N.H., et al.: The Emotions. Cambridge University Press, Cambridge (1986)"},{"key":"12_CR15","unstructured":"Gera, D., Balasubramanian, S.: Affect expression behaviour analysis in the wild using spatio-channel attention and complementary context information. arXiv preprint arXiv:2009.14440 (2020)"},{"key":"12_CR16","unstructured":"Gera, D., Balasubramanian, S.: Affect expression behaviour analysis in the wild using consensual collaborative training. arXiv preprint arXiv:2107.05736 (2021)"},{"key":"12_CR17","unstructured":"Gera, D., Kumar, B.N.S., Kumar, B.V.R., Balasubramanian, S.: SS-MFAR: semi-supervised multi-task facial affect recognition. arXiv preprint arXiv:2207.09012 (2022)"},{"key":"12_CR18","unstructured":"Haider, I., Tran, M.T., Kim, S.H., Yang, H.J., Lee, G.S.: An ensemble approach for multiple emotion descriptors estimation using multi-task learning. arXiv preprint arXiv:2207.10878 (2022)"},{"key":"12_CR19","unstructured":"Han, S., Meng, Z., Khan, A.S., Tong, Y.: Incremental boosting convolutional neural network for facial action unit recognition. In: Advances in Neural Information Processing Systems, pp. 109\u2013117 (2016)"},{"key":"12_CR20","unstructured":"Hoai, D.L., et al.: An attention-based method for action unit detection at the 3rd ABAW competition. arXiv preprint arXiv:2203.12428 (2022)"},{"key":"12_CR21","unstructured":"Jeong, E., Oh, G., Lim, S.: Multitask emotion recognition model with knowledge distillation and task discriminator. arXiv preprint arXiv:2203.13072 (2022)"},{"key":"12_CR22","doi-asserted-by":"crossref","unstructured":"Jeong, J.Y., Hong, Y.G., Kim, D., Jeong, J.W., Jung, Y., Kim, S.H.: Classification of facial expression in-the-wild based on ensemble of multi-head cross attention networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 2353\u20132358, June 2022","DOI":"10.1109\/CVPRW56347.2022.00262"},{"key":"12_CR23","unstructured":"Jeong, J.Y., Hong, Y.G., Kim, D., Jung, Y., Jeong, J.W.: Facial expression recognition based on multi-head cross attention network. arXiv preprint arXiv:2203.13235 (2022)"},{"key":"12_CR24","unstructured":"Jeong, J.Y., Hong, Y.G., Oh, J., Hong, S., Jeong, J.W., Jung, Y.: Learning from synthetic data: facial expression classification based on ensemble of multi-task networks. arXiv preprint arXiv:2207.10025 (2022)"},{"key":"12_CR25","unstructured":"Ji, X., Ding, Y., Li, L., Chen, Y., Fan, C.: Multi-label relation modeling in facial action units detection. arXiv preprint arXiv:2002.01105 (2020)"},{"key":"12_CR26","unstructured":"Jiang, W., Wu, Y., Qiao, F., Meng, L., Deng, Y., Liu, C.: Facial action unit recognition with multi-models ensembling. arXiv preprint arXiv:2203.13046 (2022)"},{"key":"12_CR27","doi-asserted-by":"crossref","unstructured":"Jiang, W., Wu, Y., Qiao, F., Meng, L., Deng, Y., Liu, C.: Model level ensemble for facial action unit recognition at the 3rd ABAW challenge. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 2337\u20132344, June 2022","DOI":"10.1109\/CVPRW56347.2022.00260"},{"key":"12_CR28","doi-asserted-by":"crossref","unstructured":"Jin, Y., Zheng, T., Gao, C., Xu, G.: A multi-modal and multi-task learning method for action unit and expression recognition. arXiv preprint arXiv:2107.04187 (2021)","DOI":"10.1109\/ICCVW54120.2021.00401"},{"key":"12_CR29","doi-asserted-by":"crossref","unstructured":"Karas, V., Tellamekala, M.K., Mallol-Ragolta, A., Valstar, M., Schuller, B.W.: Continuous-time audiovisual fusion with recurrence vs. attention for in-the-wild affect recognition. arXiv preprint arXiv:2203.13285 (2022)","DOI":"10.1109\/CVPRW56347.2022.00266"},{"key":"12_CR30","doi-asserted-by":"crossref","unstructured":"Karas, V., Tellamekala, M.K., Mallol-Ragolta, A., Valstar, M., Schuller, B.W.: Time-continuous audiovisual fusion with recurrence vs attention for in-the-wild affect recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 2382\u20132391, June 2022","DOI":"10.1109\/CVPRW56347.2022.00266"},{"key":"12_CR31","unstructured":"Kim, J.H., Kim, N., Won, C.S.: Facial expression recognition with swin transformer. arXiv preprint arXiv:2203.13472 (2022)"},{"key":"12_CR32","doi-asserted-by":"crossref","unstructured":"Kollias, D.: ABAW: learning from synthetic data & multi-task learning challenges. arXiv preprint arXiv:2207.01138 (2022)","DOI":"10.1007\/978-3-031-25075-0_12"},{"key":"12_CR33","doi-asserted-by":"crossref","unstructured":"Kollias, D.: ABAW: valence-arousal estimation, expression recognition, action unit detection & multi-task learning challenges. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2328\u20132336 (2022)","DOI":"10.1109\/CVPRW56347.2022.00259"},{"key":"12_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"475","DOI":"10.1007\/978-3-030-11012-3_36","volume-title":"Computer Vision \u2013 ECCV 2018 Workshops","author":"D Kollias","year":"2019","unstructured":"Kollias, D., Cheng, S., Pantic, M., Zafeiriou, S.: Photorealistic facial synthesis in the dimensional affect space. In: Leal-Taix\u00e9, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11130, pp. 475\u2013491. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-11012-3_36"},{"key":"12_CR35","doi-asserted-by":"publisher","first-page":"1455","DOI":"10.1007\/s11263-020-01304-3","volume":"128","author":"D Kollias","year":"2020","unstructured":"Kollias, D., Cheng, S., Ververas, E., Kotsia, I., Zafeiriou, S.: Deep neural network augmentation: generating faces for affect analysis. Int. J. Comput. Vis. 128, 1455\u20131484 (2020). https:\/\/doi.org\/10.1007\/s11263-020-01304-3","journal-title":"Int. J. Comput. Vis."},{"key":"12_CR36","doi-asserted-by":"crossref","unstructured":"Kollias, D., Nicolaou, M.A., Kotsia, I., Zhao, G., Zafeiriou, S.: Recognition of affect in the wild using deep neural networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 1972\u20131979. IEEE (2017)","DOI":"10.1109\/CVPRW.2017.247"},{"key":"12_CR37","doi-asserted-by":"crossref","unstructured":"Kollias, D., Schulc, A., Hajiyev, E., Zafeiriou, S.: Analysing affective behavior in the first ABAW 2020 competition. In: 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020), pp. 794\u2013800. IEEE Computer Society (2020)","DOI":"10.1109\/FG47880.2020.00126"},{"key":"12_CR38","unstructured":"Kollias, D., Sharmanska, V., Zafeiriou, S.: Face behavior a la carte: expressions, affect and action units in a single network. arXiv preprint arXiv:1910.11111 (2019)"},{"key":"12_CR39","unstructured":"Kollias, D., Sharmanska, V., Zafeiriou, S.: Distribution matching for heterogeneous multi-task learning: a large-scale face study. arXiv preprint arXiv:2105.03790 (2021)"},{"issue":"6\u20137","key":"12_CR40","doi-asserted-by":"publisher","first-page":"907","DOI":"10.1007\/s11263-019-01158-4","volume":"127","author":"D Kollias","year":"2019","unstructured":"Kollias, D., et al.: Deep affect prediction in-the-wild: aff-wild database and challenge, deep architectures, and beyond. Int. J. Comput. Vis. 127(6\u20137), 907\u2013929 (2019). https:\/\/doi.org\/10.1007\/s11263-019-01158-4","journal-title":"Int. J. Comput. Vis."},{"key":"12_CR41","unstructured":"Kollias, D., Zafeiriou, S.: Aff-wild2: extending the aff-wild database for affect recognition. arXiv preprint arXiv:1811.07770 (2018)"},{"key":"12_CR42","unstructured":"Kollias, D., Zafeiriou, S.: A multi-task learning & generation framework: valence-arousal, action units & primary expressions. arXiv preprint arXiv:1811.07771 (2018)"},{"key":"12_CR43","unstructured":"Kollias, D., Zafeiriou, S.: Expression, affect, action unit recognition: aff-wild2, multi-task learning and arcface. arXiv preprint arXiv:1910.04855 (2019)"},{"key":"12_CR44","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1007\/978-3-030-40605-9_20","volume-title":"Advanced Concepts for Intelligent Vision Systems","author":"D Kollias","year":"2020","unstructured":"Kollias, D., Zafeiriou, S.: VA-StarGAN: continuous affect generation. In: Blanc-Talon, J., Delmas, P., Philips, W., Popescu, D., Scheunders, P. (eds.) ACIVS 2020. LNCS, vol. 12002, pp. 227\u2013238. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-40605-9_20"},{"key":"12_CR45","unstructured":"Kollias, D., Zafeiriou, S.: Affect analysis in-the-wild: valence-arousal, expressions, action units and a unified framework. arXiv preprint arXiv:2103.15792 (2021)"},{"key":"12_CR46","doi-asserted-by":"crossref","unstructured":"Kollias, D., Zafeiriou, S.: Analysing affective behavior in the second ABAW2 competition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3652\u20133660 (2021)","DOI":"10.1109\/ICCVW54120.2021.00408"},{"key":"12_CR47","doi-asserted-by":"crossref","unstructured":"Kuhnke, F., Rumberg, L., Ostermann, J.: Two-stream aural-visual affect analysis in the wild. arXiv preprint arXiv:2002.03399 (2020)","DOI":"10.1109\/FG47880.2020.00056"},{"key":"12_CR48","doi-asserted-by":"crossref","unstructured":"Le Hoai, D., et al.: An attention-based method for multi-label facial action unit detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 2454\u20132459, June 2022","DOI":"10.1109\/CVPRW56347.2022.00274"},{"key":"12_CR49","doi-asserted-by":"crossref","unstructured":"Lee, H., Lim, H., Lim, S.: BYEL: bootstrap on your emotion latent. arXiv preprint arXiv:2207.10003 (2022)","DOI":"10.1007\/978-3-031-25075-0_9"},{"key":"12_CR50","doi-asserted-by":"crossref","unstructured":"Lei, J., et al.: Mid-level representation enhancement and graph embedded uncertainty suppressing for facial expression recognition. arXiv preprint arXiv:2207.13235 (2022)","DOI":"10.1007\/978-3-031-25075-0_7"},{"key":"12_CR51","unstructured":"Li, I., et al.: Technical report for valence-arousal estimation on affwild2 dataset. arXiv preprint arXiv:2105.01502 (2021)"},{"key":"12_CR52","unstructured":"Li, S., et al.: Facial affect analysis: learning from synthetic data & multi-task learning challenges. arXiv preprint arXiv:2207.09748 (2022)"},{"key":"12_CR53","doi-asserted-by":"crossref","unstructured":"Li, Y., Sun, H., Liu, Z., Han, H.: Affective behaviour analysis using pretrained model with facial priori. arXiv preprint arXiv:2207.11679 (2022)","DOI":"10.1007\/978-3-031-25075-0_2"},{"key":"12_CR54","unstructured":"Liu, H., Zeng, J., Shan, S., Chen, X.: Emotion recognition for in-the-wild videos. arXiv preprint arXiv:2002.05447 (2020)"},{"issue":"1","key":"12_CR55","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1007\/s10489-007-0076-9","volume":"30","author":"L Malatesta","year":"2009","unstructured":"Malatesta, L., Raouzaiou, A., Karpouzis, K., Kollias, S.: Towards modeling embodied conversational agent character profiles using appraisal theory predictions in expression synthesis. Appl. Intell. 30(1), 58\u201364 (2009). https:\/\/doi.org\/10.1007\/s10489-007-0076-9","journal-title":"Appl. Intell."},{"key":"12_CR56","unstructured":"Mao, S., Fan, X., Peng, X.: Spatial and temporal networks for facial expression recognition in the wild videos. arXiv preprint arXiv:2107.05160 (2021)"},{"key":"12_CR57","unstructured":"Meng, L., et al.: Multi-modal emotion estimation for in-the-wild videos. arXiv preprint arXiv:2203.13032 (2022)"},{"key":"12_CR58","doi-asserted-by":"crossref","unstructured":"Meng, L., et al.: Valence and arousal estimation based on multimodal temporal-aware features for videos in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 2345\u20132352, June 2022","DOI":"10.1109\/CVPRW56347.2022.00261"},{"key":"12_CR59","unstructured":"Nguyen, D.K., Pant, S., Ho, N.H., Lee, G.S., Kim, S.H., Yang, H.J.: Multi-task cross attention network in facial behavior analysis. arXiv preprint arXiv:2207.10293 (2022)"},{"key":"12_CR60","doi-asserted-by":"crossref","unstructured":"Nguyen, H.H., Huynh, V.T., Kim, S.H.: An ensemble approach for facial behavior analysis in-the-wild video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 2512\u20132517, June 2022","DOI":"10.1109\/CVPRW56347.2022.00281"},{"key":"12_CR61","doi-asserted-by":"crossref","unstructured":"Nguyen, H.H., Huynh, V.T., Kim, S.H.: An ensemble approach for facial expression analysis in video. arXiv preprint arXiv:2203.12891 (2022)","DOI":"10.1109\/CVPRW56347.2022.00281"},{"key":"12_CR62","doi-asserted-by":"crossref","unstructured":"Oh, G., Jeong, E., Lim, S.: Causal affect prediction model using a facial image sequence. arXiv preprint arXiv:2107.03886 (2021)","DOI":"10.1109\/ICCVW54120.2021.00395"},{"key":"12_CR63","doi-asserted-by":"crossref","unstructured":"Pahl, J., Rieger, I., Seuss, D.: Multi-label class balancing algorithm for action unit detection. arXiv preprint arXiv:2002.03238 (2020)","DOI":"10.1109\/FG47880.2020.00101"},{"key":"12_CR64","doi-asserted-by":"crossref","unstructured":"Phan, K.N., Nguyen, H.H., Huynh, V.T., Kim, S.H.: Expression classification using concatenation of deep neural network for the 3rd ABAW3 competition. arXiv preprint arXiv:2203.12899 (2022)","DOI":"10.1109\/CVPRW56347.2022.00280"},{"key":"12_CR65","doi-asserted-by":"crossref","unstructured":"Psaroudakis, A., Kollias, D.: MixAugment & Mixup: augmentation methods for facial expression recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2367\u20132375 (2022)","DOI":"10.1109\/CVPRW56347.2022.00264"},{"key":"12_CR66","unstructured":"Rajasekar, G.P., et al.: A joint cross-attention model for audio-visual fusion in dimensional emotion recognition. arXiv preprint arXiv:2203.14779 (2022)"},{"issue":"10","key":"12_CR67","doi-asserted-by":"publisher","first-page":"1152","DOI":"10.1037\/0022-3514.36.10.1152","volume":"36","author":"JA Russell","year":"1978","unstructured":"Russell, J.A.: Evidence of convergent validity on the dimensions of affect. J. Pers. Soc. Psychol. 36(10), 1152 (1978)","journal-title":"J. Pers. Soc. Psychol."},{"key":"12_CR68","unstructured":"Saito, J., Mi, X., Uchida, A., Youoku, S., Yamamoto, T., Murase, K.: Action units recognition using improved pairwise deep architecture. arXiv preprint arXiv:2107.03143 (2021)"},{"key":"12_CR69","unstructured":"Savchenko, A.V.: Frame-level prediction of facial expressions, valence, arousal and action units for mobile devices. arXiv preprint arXiv:2203.13436 (2022)"},{"key":"12_CR70","unstructured":"Savchenko, A.V.: HSE-NN team at the 4th ABAW competition: multi-task emotion recognition and learning from synthetic images. arXiv preprint arXiv:2207.09508 (2022)"},{"key":"12_CR71","doi-asserted-by":"crossref","unstructured":"Savchenko, A.V.: Video-based frame-level facial analysis of affective behavior on mobile devices using EfficientNets. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 2359\u20132366, June 2022","DOI":"10.1109\/CVPRW56347.2022.00263"},{"key":"12_CR72","doi-asserted-by":"crossref","unstructured":"Sun, H., Lian, Z., Liu, B., Tao, J., Sun, L., Cai, C.: Two-aspect information fusion model for ABAW4 multi-task challenge. arXiv preprint arXiv:2207.11389 (2022)","DOI":"10.1007\/978-3-031-25075-0_13"},{"key":"12_CR73","doi-asserted-by":"crossref","unstructured":"Tallec, G., Yvinec, E., Dapogny, A., Bailly, K.: Multi-label transformer for action unit detection. arXiv preprint arXiv:2203.12531 (2022)","DOI":"10.1109\/TAFFC.2022.3178524"},{"key":"12_CR74","doi-asserted-by":"crossref","unstructured":"Vu, M.T., Beurton-Aimar, M.: Multitask multi-database emotion recognition. arXiv preprint arXiv:2107.04127 (2021)","DOI":"10.1109\/ICCVW54120.2021.00406"},{"key":"12_CR75","unstructured":"Wang, L., Li, H., Liu, C.: Hybrid CNN-transformer model for facial affect recognition in the ABAW4 challenge. arXiv preprint arXiv:2207.10201 (2022)"},{"key":"12_CR76","doi-asserted-by":"crossref","unstructured":"Wang, L., Qi, J., Cheng, J., Suzuki, K.: Action unit detection by exploiting spatial-temporal and label-wise attention with transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 2470\u20132475, June 2022","DOI":"10.1109\/CVPRW56347.2022.00276"},{"key":"12_CR77","doi-asserted-by":"crossref","unstructured":"Wang, L., Wang, S.: A multi-task mean teacher for semi-supervised facial affective behavior analysis. arXiv preprint arXiv:2107.04225 (2021)","DOI":"10.1109\/ICCVW54120.2021.00402"},{"key":"12_CR78","unstructured":"Wang, L., Wang, S., Qi, J.: Multi-modal multi-label facial action unit detection with transformer. arXiv preprint arXiv:2203.13301 (2022)"},{"key":"12_CR79","unstructured":"Wang, S., Chang, Y., Wang, J.: Facial action unit recognition based on transfer learning. arXiv preprint arXiv:2203.14694 (2022)"},{"key":"12_CR80","unstructured":"Whissel, C.: The dictionary of affect in language. In: Plutchik, R., Kellerman, H. (eds.) Emotion: Theory, Research and Experience: Volume 4, The Measurement of Emotions. Academic, New York (1989)"},{"key":"12_CR81","unstructured":"Xie, H.X., Li, I., Lo, L., Shuai, H.H., Cheng, W.H., et al.: Technical report for valence-arousal estimation in ABAW2 challenge. arXiv preprint arXiv:2107.03891 (2021)"},{"key":"12_CR82","doi-asserted-by":"crossref","unstructured":"Xue, F., Tan, Z., Zhu, Y., Ma, Z., Guo, G.: Coarse-to-fine cascaded networks with smooth predicting for video facial expression recognition. arXiv preprint arXiv:2203.13052 (2022)","DOI":"10.1109\/CVPRW56347.2022.00269"},{"key":"12_CR83","unstructured":"Youoku, S., et al.: A multi-term and multi-task analyzing framework for affective analysis in-the-wild. arXiv preprint arXiv:2009.13885 (2020)"},{"key":"12_CR84","unstructured":"Yu, J., Cai, Z., He, P., Xie, G., Ling, Q.: Multi-model ensemble learning method for human expression recognition. arXiv preprint arXiv:2203.14466 (2022)"},{"key":"12_CR85","doi-asserted-by":"crossref","unstructured":"Zafeiriou, S., Kollias, D., Nicolaou, M.A., Papaioannou, A., Zhao, G., Kotsia, I.: Aff-wild: valence and arousal \u2018in-the-wild\u2019 challenge. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 34\u201341 (2017)","DOI":"10.1109\/CVPRW.2017.248"},{"key":"12_CR86","doi-asserted-by":"crossref","unstructured":"Zhang, S., An, R., Ding, Y., Guan, C.: Continuous emotion recognition using visual-audio-linguistic information: a technical report for ABAW3. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 2376\u20132381, June 2022","DOI":"10.1109\/CVPRW56347.2022.00265"},{"key":"12_CR87","doi-asserted-by":"crossref","unstructured":"Zhang, S., An, R., Ding, Y., Guan, C.: Continuous emotion recognition using visual-audio-linguistic information: a technical report for ABAW3. arXiv preprint arXiv:2203.13031 (2022)","DOI":"10.1109\/CVPRW56347.2022.00265"},{"key":"12_CR88","unstructured":"Zhang, S., Ding, Y., Wei, Z., Guan, C.: Audio-visual attentive fusion for continuous emotion recognition. arXiv preprint arXiv:2107.01175 (2021)"},{"key":"12_CR89","unstructured":"Zhang, T., et al.: Emotion recognition based on multi-task learning framework in the ABAW4 challenge. arXiv preprint arXiv:2207.09373 (2022)"},{"key":"12_CR90","doi-asserted-by":"crossref","unstructured":"Zhang, W., Guo, Z., Chen, K., Li, L., Zhang, Z., Ding, Y.: Prior aided streaming network for multi-task affective recognitionat the 2nd ABAW2 competition. arXiv preprint arXiv:2107.03708 (2021)","DOI":"10.1109\/ICCVW54120.2021.00394"},{"key":"12_CR91","doi-asserted-by":"crossref","unstructured":"Zhang, W., et al.: Prior aided streaming network for multi-task affective analysis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) Workshops, pp. 3539\u20133549, October 2021","DOI":"10.1109\/ICCVW54120.2021.00394"},{"key":"12_CR92","doi-asserted-by":"crossref","unstructured":"Zhang, W., et al.: Transformer-based multimodal information fusion for facial expression analysis. arXiv preprint arXiv:2203.12367 (2022)","DOI":"10.1109\/CVPRW56347.2022.00271"},{"key":"12_CR93","doi-asserted-by":"crossref","unstructured":"Zhang, Y.H., Huang, R., Zeng, J., Shan, S., Chen, X.: M$$^{3}$$T: multi-modal continuous valence-arousal estimation in the wild. arXiv preprint arXiv:2002.02957 (2020)","DOI":"10.1109\/FG47880.2020.00098"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-25075-0_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,7]],"date-time":"2023-12-07T04:51:38Z","timestamp":1701924698000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-25075-0_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031250743","9783031250750"],"references-count":93,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-25075-0_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"19 February 2023","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"From the workshops, 367 reviewed full papers have been selected for publication","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}