{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T15:49:45Z","timestamp":1781797785349,"version":"3.54.5"},"publisher-location":"Cham","reference-count":35,"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_11","type":"book-chapter","created":{"date-parts":[[2023,2,19]],"date-time":"2023-02-19T09:16:53Z","timestamp":1676798213000},"page":"143-156","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Multi-Task Learning Framework for\u00a0Emotion Recognition In-the-Wild"],"prefix":"10.1007","author":[{"given":"Tenggan","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuanhe","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaolong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuchen","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liyu","family":"Meng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenqiang","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fengyuan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinming","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qin","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,2,19]]},"reference":[{"key":"11_CR1","doi-asserted-by":"crossref","unstructured":"An, X., et al.: Partial FC: training 10 million identities on a single machine. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1445\u20131449 (2021)","DOI":"10.1109\/ICCVW54120.2021.00166"},{"key":"11_CR2","doi-asserted-by":"crossref","unstructured":"Barsoum, E., Zhang, C., Canton Ferrer, C., Zhang, Z.: Training deep networks for facial expression recognition with crowd-sourced label distribution. In: ACM International Conference on Multimodal Interaction (ICMI) (2016)","DOI":"10.1145\/2993148.2993165"},{"key":"11_CR3","doi-asserted-by":"publisher","unstructured":"Benitez-Quiroz, C.F., Srinivasan, R., Mart\u00ednez, A.M.: Emotionet: an accurate, real-time algorithm for the automatic annotation of a million facial expressions in the wild. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, 27\u201330 June 2016, pp. 5562\u20135570. IEEE Computer Society (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.600","DOI":"10.1109\/CVPR.2016.600"},{"key":"11_CR4","unstructured":"Chung, J., Gulcehre, C., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555 (2014)"},{"key":"11_CR5","doi-asserted-by":"crossref","unstructured":"Fan, Y., Lam, J., Li, V.: Facial action unit intensity estimation via semantic correspondence learning with dynamic graph convolution. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 12701\u201312708 (2020)","DOI":"10.1609\/aaai.v34i07.6963"},{"key":"11_CR6","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.B.: Masked autoencoders are scalable vision learners. CoRR abs\/2111.06377 (2021). https:\/\/arxiv.org\/abs\/2111.06377"},{"key":"11_CR7","unstructured":"Iandola, F., Moskewicz, M., Karayev, S., Girshick, R., Darrell, T., Keutzer, K.: Densenet: implementing efficient convnet descriptor pyramids. arXiv preprint arXiv:1404.1869 (2014)"},{"key":"11_CR8","unstructured":"Jacob, G.M., Stenger, B.: Facial action unit detection with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7680\u20137689 (2021)"},{"key":"11_CR9","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, pp. 2337\u20132344 (2022)","DOI":"10.1109\/CVPRW56347.2022.00260"},{"key":"11_CR10","doi-asserted-by":"crossref","unstructured":"Jin, C., Jin, R., Chen, K., Dou, Y.: A community detection approach to cleaning extremely large face database. Comput. Intell. Neurosci. 2018 (2018)","DOI":"10.1155\/2018\/4512473"},{"key":"11_CR11","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"11_CR12","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":"11_CR13","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":"11_CR14","doi-asserted-by":"crossref","unstructured":"Kollias, D., Cheng, S., Pantic, M., Zafeiriou, S.: Photorealistic facial synthesis in the dimensional affect space. In: Proceedings of the European Conference on Computer Vision (ECCV) Workshops (2018)","DOI":"10.1007\/978-3-030-11012-3_36"},{"issue":"5","key":"11_CR15","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":"11_CR16","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":"11_CR17","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":"11_CR18","doi-asserted-by":"publisher","first-page":"1","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. Vision 127, 1\u201323 (2019)","journal-title":"Int. J. Comput. Vision"},{"key":"11_CR19","unstructured":"Kollias, D., Zafeiriou, S.: Aff-wild2: extending the aff-wild database for affect recognition. CoRR abs\/1811.07770 (2018). http:\/\/arxiv.org\/abs\/1811.07770"},{"key":"11_CR20","unstructured":"Kollias, D., Zafeiriou, S.: Expression, affect, action unit recognition: Aff-wild2, multi-task learning and arcface. arXiv preprint arXiv:1910.04855 (2019)"},{"key":"11_CR21","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":"11_CR22","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)"},{"issue":"1","key":"11_CR23","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1109\/TIP.2018.2868382","volume":"28","author":"S Li","year":"2019","unstructured":"Li, S., Deng, W.: Reliable crowdsourcing and deep locality-preserving learning for unconstrained facial expression recognition. IEEE Trans. Image Process. 28(1), 356\u2013370 (2019)","journal-title":"IEEE Trans. Image Process."},{"key":"11_CR24","doi-asserted-by":"crossref","unstructured":"Li, S., Deng, W., Du, J.: Reliable crowdsourcing and deep locality-preserving learning for expression recognition in the wild. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2584\u20132593. IEEE (2017)","DOI":"10.1109\/CVPR.2017.277"},{"key":"11_CR25","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, pp. 2345\u20132352 (2022)","DOI":"10.1109\/CVPRW56347.2022.00261"},{"issue":"1","key":"11_CR26","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/TAFFC.2017.2740923","volume":"10","author":"A Mollahosseini","year":"2017","unstructured":"Mollahosseini, A., Hasani, 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 (2017)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"11_CR27","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":"11_CR28","unstructured":"Ruder, S.: An overview of multi-task learning in deep neural networks. CoRR abs\/1706.05098 (2017). http:\/\/arxiv.org\/abs\/1706.05098"},{"key":"11_CR29","doi-asserted-by":"crossref","unstructured":"Sak, H., Senior, A., Beaufays, F.: Long short-term memory based recurrent neural network architectures for large vocabulary speech recognition. arXiv preprint arXiv:1402.1128 (2014)","DOI":"10.21437\/Interspeech.2014-80"},{"key":"11_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"981","DOI":"10.1007\/11573548_125","volume-title":"Affective Computing and Intelligent Interaction","author":"J Tao","year":"2005","unstructured":"Tao, J., Tan, T.: Affective computing: a review. In: Tao, J., Tan, T., Picard, R.W. (eds.) ACII 2005. LNCS, vol. 3784, pp. 981\u2013995. Springer, Heidelberg (2005). https:\/\/doi.org\/10.1007\/11573548_125"},{"key":"11_CR31","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"11_CR32","doi-asserted-by":"crossref","unstructured":"Wen, Z., Lin, W., Wang, T., Xu, G.: Distract your attention: multi-head cross attention network for facial expression recognition. arXiv preprint arXiv:2109.07270 (2021)","DOI":"10.1109\/FG52635.2021.9667041"},{"key":"11_CR33","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":"11_CR34","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":"11_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, W., et al.: Transformer-based multimodal information fusion for facial expression analysis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2428\u20132437 (2022)","DOI":"10.1109\/CVPRW56347.2022.00271"}],"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_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,25]],"date-time":"2023-03-25T19:11:14Z","timestamp":1679771474000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-25075-0_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031250743","9783031250750"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-25075-0_11","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)"}}]}}