{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:17:40Z","timestamp":1778080660138,"version":"3.51.4"},"publisher-location":"Cham","reference-count":51,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031915802","type":"print"},{"value":"9783031915819","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\/978-3-031-91581-9_1","type":"book-chapter","created":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T11:22:36Z","timestamp":1748344956000},"page":"1-16","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["MMA-MRNNet: Harnessing Multiple Models of\u00a0Affect and\u00a0Dynamic Masked RNN for\u00a0Precise Facial Expression Intensity Estimation"],"prefix":"10.1007","author":[{"given":"Dimitrios","family":"Kollias","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andreas","family":"Psaroudakis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anastasios","family":"Arsenos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paraskevi","family":"Theofilou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunchang","family":"Shao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guanyu","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ioannis","family":"Patras","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"1_CR1","doi-asserted-by":"crossref","unstructured":"Arsenos, A., Davidhi, A., Kollias, D., Prassopoulos, P., Kollias, S.: Data-driven Covid-19 detection through medical imaging. In: 2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW), pp.\u00a01\u20135. IEEE (2023)","DOI":"10.1109\/ICASSPW59220.2023.10193437"},{"key":"1_CR2","doi-asserted-by":"crossref","unstructured":"Benitez-Quiroz, C., Srinivasan, R., Martinez, A.: EmotioNet: an accurate, real-time algorithm for the automatic annotation of a million facial expressions in the wild. In: Proceedings of IEEE International Conference on Computer Vision & Pattern Recognition (CVPR 2016), Las Vegas, NV, USA (2016)","DOI":"10.1109\/CVPR.2016.600"},{"key":"1_CR3","doi-asserted-by":"crossref","unstructured":"Christ, L., et al.: The muse 2022 multimodal sentiment analysis challenge: humor, emotional reactions, and stress. In: Proceedings of the 3rd Multimodal Sentiment Analysis Challenge. Association for Computing Machinery, Lisbon, Portugal (2022). Workshop held at ACM Multimedia 2022, to appear","DOI":"10.1145\/3551876.3554817"},{"key":"1_CR4","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"},{"issue":"15","key":"1_CR5","doi-asserted-by":"publisher","first-page":"E1454","DOI":"10.1073\/pnas.1322355111","volume":"111","author":"S Du","year":"2014","unstructured":"Du, S., Tao, Y., Martinez, A.M.: Compound facial expressions of emotion. Proc. Natl. Acad. Sci. 111(15), E1454\u2013E1462 (2014)","journal-title":"Proc. Natl. Acad. Sci."},{"key":"1_CR6","unstructured":"Ekman, P.: Facial action coding system (FACS). A human face (2002)"},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"Ekman, P., Friesen, W.V.: Facial action coding system. Environ. Psychol. Nonverbal Behav. (1978)","DOI":"10.1037\/t27734-000"},{"key":"1_CR8","doi-asserted-by":"crossref","unstructured":"Farzaneh, A.H., Qi, X.: Facial expression recognition in the wild via deep attentive center loss. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2402\u20132411 (2021)","DOI":"10.1109\/WACV48630.2021.00245"},{"key":"1_CR9","doi-asserted-by":"publisher","unstructured":"Guo, X., Polan\u00eda, L.F., Barner, K.E.: Audio-video emotion recognition in the wild using deep hybrid networks (2020). https:\/\/doi.org\/10.48550\/ARXIV.2002.09023, https:\/\/arxiv.org\/abs\/2002.09023","DOI":"10.48550\/ARXIV.2002.09023"},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Hu, G., Kollias, D., Papadopoulou, E., Tzouveli, P., Wei, J., Yang, X.: Rethinking affect analysis: a protocol for ensuring fairness and consistency. arXiv preprint arXiv:2408.02164 (2024)","DOI":"10.1109\/TBIOM.2025.3550000"},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"Hu, G., Papadopoulou, E., Kollias, D., Tzouveli, P., Wei, J., Yang, X.: Bridging the gap: protocol towards fair and consistent affect analysis. arXiv preprint arXiv:2405.06841 (2024)","DOI":"10.1109\/FG59268.2024.10582033"},{"key":"1_CR12","doi-asserted-by":"publisher","unstructured":"Hu, P., Cai, D., Wang, S., Yao, A., Chen, Y.: Learning supervised scoring ensemble for emotion recognition in the wild. In: Proceedings of the 19th ACM International Conference on Multimodal Interaction, ICMI 2017, pp. 553\u2013560. Association for Computing Machinery, New York (2017). https:\/\/doi.org\/10.1145\/3136755.3143009","DOI":"10.1145\/3136755.3143009"},{"key":"1_CR13","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","DOI":"10.1109\/FG47880.2020.00126"},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"Kollias, D.: ABAW: learning from synthetic data & multi-task learning challenges. In: European Conference on Computer Vision, pp. 157\u2013172. Springer (2022)","DOI":"10.1007\/978-3-031-25075-0_12"},{"key":"1_CR15","doi-asserted-by":"crossref","unstructured":"Kollias, D.: ABAW: valence-arousal estimation, expression recognition, action unit detection & multi-task learning challenges. arXiv preprint arXiv:2202.10659 (2022)","DOI":"10.1109\/CVPRW56347.2022.00259"},{"key":"1_CR16","doi-asserted-by":"crossref","unstructured":"Kollias, D.: ABAW: learning from synthetic data & multi-task learning challenges. In: European Conference on Computer Vision, pp. 157\u2013172. Springer (2023)","DOI":"10.1007\/978-3-031-25075-0_12"},{"key":"1_CR17","doi-asserted-by":"crossref","unstructured":"Kollias, D.: Multi-label compound expression recognition: C-expr database & network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5589\u20135598 (2023)","DOI":"10.1109\/CVPR52729.2023.00541"},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Kollias, D., Arsenos, A., Kollias, S.: AI-enabled analysis of 3-D CT scans for diagnosis of COVID-19 & its severity. In: 2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW), pp.\u00a01\u20135. IEEE (2023)","DOI":"10.1109\/ICASSPW59220.2023.10193422"},{"key":"1_CR19","doi-asserted-by":"publisher","first-page":"126244","DOI":"10.1016\/j.neucom.2023.126244","volume":"542","author":"D Kollias","year":"2023","unstructured":"Kollias, D., Arsenos, A., Kollias, S.: A deep neural architecture for harmonizing 3-D input data analysis and decision making in medical imaging. Neurocomputing 542, 126244 (2023)","journal-title":"Neurocomputing"},{"key":"1_CR20","doi-asserted-by":"crossref","unstructured":"Kollias, D., Arsenos, A., Kollias, S.: Domain adaptation, explainability & fairness in AI for medical image analysis: diagnosis of Covid-19 based on 3-D chest CT-scans. arXiv preprint arXiv:2403.02192 (2024)","DOI":"10.1109\/CVPRW63382.2024.00495"},{"issue":"5","key":"1_CR21","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. Vision 128(5), 1455\u20131484 (2020)","journal-title":"Int. J. Comput. Vision"},{"key":"1_CR22","doi-asserted-by":"crossref","unstructured":"Kollias, D., Cheng, S., Ververas, E., Kotsia, I., Zafeiriou, S.: Deep neural network augmentation: generating faces for affect analysis. Int. J. Comput. Vision 1\u201330 (2020)","DOI":"10.1007\/s11263-020-01304-3"},{"key":"1_CR23","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":"1_CR24","unstructured":"Kollias, D., Psaroudakis, A., Arsenos, A., Theofilou, P.: FacerNet: a facial expression intensity estimation network. arXiv preprint arXiv:2303.00180 (2023)"},{"key":"1_CR25","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":"1_CR26","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)"},{"key":"1_CR27","doi-asserted-by":"crossref","unstructured":"Kollias, D., Sharmanska, V., Zafeiriou, S.: Distribution matching for multi-task learning of classification tasks: a large-scale study on faces & beyond. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 2813\u20132821 (2024)","DOI":"10.1609\/aaai.v38i3.28061"},{"key":"1_CR28","doi-asserted-by":"crossref","unstructured":"Kollias, D., Tzirakis, P., Baird, A., Cowen, A., Zafeiriou, S.: ABAW: valence-arousal estimation, expression recognition, action unit detection & emotional reaction intensity estimation challenges. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5888\u20135897 (2023)","DOI":"10.1109\/CVPRW59228.2023.00626"},{"key":"1_CR29","doi-asserted-by":"crossref","unstructured":"Kollias, D., Tzirakis, P., Cowen, A., Zafeiriou, S., Shao, C., Hu, G.: The 6th affective behavior analysis in-the-wild (ABAW) competition. arXiv preprint arXiv:2402.19344 (2024)","DOI":"10.1109\/CVPRW63382.2024.00461"},{"key":"1_CR30","unstructured":"Kollias, D., et al.: Deep affect prediction in-the-wild: aff-wild database and challenge, deep architectures, and beyond. Int. J. Comput. Vision 1\u201323 (2019)"},{"key":"1_CR31","unstructured":"Kollias, D., Zafeiriou, S.: Expression, affect, action unit recognition: aff-wild2, multi-task learning and arcface. arXiv preprint arXiv:1910.04855 (2019)"},{"key":"1_CR32","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":"1_CR33","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":"1_CR34","doi-asserted-by":"crossref","unstructured":"Kollias, D., et al.: 7th ABAW competition: multi-task learning and compound expression recognition. arXiv preprint arXiv:2407.03835 (2024)","DOI":"10.1007\/978-3-031-91581-9_3"},{"key":"1_CR35","doi-asserted-by":"crossref","unstructured":"Li, J., et al.: Multimodal feature extraction and fusion for emotional reaction intensity estimation and expression classification in videos with transformers. arXiv preprint arXiv:2303.09164 (2023)","DOI":"10.1109\/CVPRW59228.2023.00620"},{"key":"1_CR36","doi-asserted-by":"crossref","unstructured":"Liu, C., et al.: Facial expression recognition based on multi-modal features for videos in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5871\u20135878 (2023)","DOI":"10.1109\/CVPRW59228.2023.00624"},{"key":"1_CR37","doi-asserted-by":"crossref","unstructured":"Luo, C., Song, S., Xie, W., Shen, L., Gunes, H.: Learning multi-dimensional edge feature-based au relation graph for facial action unit recognition. In: Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, pp. 1239\u20131246 (2022)","DOI":"10.24963\/ijcai.2022\/173"},{"key":"1_CR38","unstructured":"Mao, J., Xu, R., Yin, X., Chang, Y., Nie, B., Huang, A.: Poster v2: a simpler and stronger facial expression recognition network. arXiv preprint arXiv:2301.12149 (2023)"},{"key":"1_CR39","unstructured":"Mollahosseini, A., Hasani, B., Mahoor, M.H.: AffectNet: a database for facial expression, valence, and arousal computing in the wild. arXiv preprint arXiv:1708.03985 (2017)"},{"key":"1_CR40","doi-asserted-by":"crossref","unstructured":"Plutchik, R.: A psychoevolutionary theory of emotions (1982)","DOI":"10.1177\/053901882021004003"},{"key":"1_CR41","doi-asserted-by":"crossref","unstructured":"Qiu, F., Ma, B., Zhang, W., Ding, Y.: Multi-modal emotion reaction intensity estimation with temporal augmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5777\u20135784 (2023)","DOI":"10.1109\/CVPRW59228.2023.00613"},{"key":"1_CR42","unstructured":"Romero, A., Le\u00f3n, J., Arbel\u00e1ez, P.: Multi-view dynamic facial action unit detection. Image Vision Comput. (2018)"},{"key":"1_CR43","doi-asserted-by":"crossref","unstructured":"Vaiani, L., La\u00a0Quatra, M., Cagliero, L., Garza, P.: Viper: Video-based perceiver for emotion recognition. In: Proceedings of the 3rd International on Multimodal Sentiment Analysis Workshop and Challenge, pp. 67\u201373 (2022)","DOI":"10.1145\/3551876.3554806"},{"key":"1_CR44","unstructured":"Wang, S., et al.: Emotional reaction intensity estimation based on multimodal data. arXiv preprint arXiv:2303.09167 (2023)"},{"issue":"2","key":"1_CR45","doi-asserted-by":"publisher","first-page":"199","DOI":"10.3390\/biomimetics8020199","volume":"8","author":"Z Wen","year":"2023","unstructured":"Wen, Z., Lin, W., Wang, T., Xu, G.: Distract your attention: multi-head cross attention network for facial expression recognition. Biomimetics 8(2), 199 (2023)","journal-title":"Biomimetics"},{"key":"1_CR46","doi-asserted-by":"crossref","unstructured":"Yu, J., et al.: Exploring large-scale unlabeled faces to enhance facial expression recognition. arXiv preprint arXiv:2303.08617 (2023)","DOI":"10.1109\/CVPRW59228.2023.00616"},{"key":"1_CR47","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: 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 1980\u20131987. IEEE (2017)","DOI":"10.1109\/CVPRW.2017.248"},{"key":"1_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, W., Ma, B., Qiu, F., Ding, Y.: Multi-modal facial affective analysis based on masked autoencoder. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5792\u20135801 (2023)","DOI":"10.1109\/CVPRW59228.2023.00615"},{"key":"1_CR49","doi-asserted-by":"crossref","unstructured":"Zhang, Z., An, L., Cui, Z., Dong, T., et\u00a0al.: Facial affect recognition based on transformer encoder and audiovisual fusion for the ABAW5 challenge. arXiv preprint arXiv:2303.09158 (2023)","DOI":"10.1109\/CVPRW59228.2023.00607"},{"key":"1_CR50","doi-asserted-by":"publisher","unstructured":"Zhao, S., et al.: An end-to-end visual-audio attention network for emotion recognition in user-generated videos (2020). https:\/\/doi.org\/10.48550\/ARXIV.2003.00832, https:\/\/arxiv.org\/abs\/2003.00832","DOI":"10.48550\/ARXIV.2003.00832"},{"key":"1_CR51","doi-asserted-by":"crossref","unstructured":"Zhou, W., Lu, J., Xiong, Z., Wang, W.: Leveraging TCN and transformer for effective visual-audio fusion in continuous emotion recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5756\u20135763 (2023)","DOI":"10.1109\/CVPRW59228.2023.00610"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-91581-9_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T15:51:57Z","timestamp":1757173917000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-91581-9_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031915802","9783031915819"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-91581-9_1","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":"12 May 2025","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"}}]}}