{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T22:12:08Z","timestamp":1767046328864,"version":"3.40.3"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030695408"},{"type":"electronic","value":"9783030695415"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-69541-5_9","type":"book-chapter","created":{"date-parts":[[2021,2,25]],"date-time":"2021-02-25T11:03:47Z","timestamp":1614251027000},"page":"137-153","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["RE-Net: A Relation Embedded Deep Model for AU Occurrence and Intensity Estimation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0517-5187","authenticated-orcid":false,"given":"Huiyuan","family":"Yang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0343-7190","authenticated-orcid":false,"given":"Lijun","family":"Yin","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,2,26]]},"reference":[{"issue":"2","key":"9_CR1","first-page":"5","volume":"3","author":"E Friesen","year":"1978","unstructured":"Friesen, E., Ekman, P.: Facial action coding system: a technique for the measurement of facial movement. Palo Alto 3(2), 5 (1978)","journal-title":"Palo Alto"},{"key":"9_CR2","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1109\/T-AFFC.2013.5","volume":"4","author":"Y Li","year":"2013","unstructured":"Li, Y., Chen, J., Zhao, Y., Ji, Q.: Data-free prior model for facial action unit recognition. IEEE Trans. Affect. Comput. 4, 127\u2013141 (2013)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"9_CR3","doi-asserted-by":"crossref","unstructured":"Wang, Z., Li, Y., Wang, S., Ji, Q.: Capturing global semantic relationships for facial action unit recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3304\u20133311 (2013)","DOI":"10.1109\/ICCV.2013.410"},{"key":"9_CR4","unstructured":"Tong, Y., Ji, Q.: Learning bayesian networks with qualitative constraints. In: 2008 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20138. IEEE (2008)"},{"key":"9_CR5","doi-asserted-by":"publisher","first-page":"3046","DOI":"10.1016\/j.patcog.2009.04.006","volume":"42","author":"W Liao","year":"2009","unstructured":"Liao, W., Ji, Q.: Learning bayesian network parameters under incomplete data with domain knowledge. Pattern Recognit. 42, 3046\u20133056 (2009)","journal-title":"Pattern Recognit."},{"key":"9_CR6","doi-asserted-by":"crossref","unstructured":"Benitez-Quiroz, C.F., Wang, Y., Martinez, A.M.: Recognition of action units in the wild with deep nets and a new global-local loss. In: ICCV, pp. 3990\u20133999 (2017)","DOI":"10.1109\/ICCV.2017.428"},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Dong, W., Hu, B.G., Ji, Q.: Classifier learning with prior probabilities for facial action unit recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5108\u20135116 (2018)","DOI":"10.1109\/CVPR.2018.00536"},{"key":"9_CR8","doi-asserted-by":"crossref","unstructured":"Peng, G., Wang, S.: Weakly supervised facial action unit recognition through adversarial training. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2188\u20132196 (2018)","DOI":"10.1109\/CVPR.2018.00233"},{"key":"9_CR9","doi-asserted-by":"crossref","unstructured":"Peng, G., Wang, S.: Dual semi-supervised learning for facial action unit recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 8827\u20138834 (2019)","DOI":"10.1609\/aaai.v33i01.33018827"},{"key":"9_CR10","doi-asserted-by":"crossref","unstructured":"Zhao, K., Chu, W.S., De la Torre, F., Cohn, J.F., Zhang, H.: Joint patch and multi-label learning for facial action unit detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2207\u20132216 (2015)","DOI":"10.1109\/CVPR.2015.7298833"},{"key":"9_CR11","doi-asserted-by":"crossref","unstructured":"Zhao, K., Chu, W.S., Zhang, H.: Deep region and multi-label learning for facial action unit detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3391\u20133399 (2016)","DOI":"10.1109\/CVPR.2016.369"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"Corneanu, C., Madadi, M., Escalera, S.: Deep structure inference network for facial action unit recognition. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 298\u2013313 (2018)","DOI":"10.1007\/978-3-030-01258-8_19"},{"key":"9_CR13","doi-asserted-by":"crossref","unstructured":"Li, G., Zhu, X., Zeng, Y., Wang, Q., Lin, L.: Semantic relationships guided representation learning for facial action unit recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 8594\u20138601 (2019)","DOI":"10.1609\/aaai.v33i01.33018594"},{"key":"9_CR14","unstructured":"Shao, Z., Zou, L., Cai, J., Wu, Y., Ma, L.: Spatio-temporal relation and attention learning for facial action unit detection. arXiv preprint arXiv:2001.01168 (2020)"},{"key":"9_CR15","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: ICML (2015)"},{"key":"9_CR16","doi-asserted-by":"crossref","unstructured":"Mancini, M., Bulo, S.R., Caputo, B., Ricci, E.: Adagraph: unifying predictive and continuous domain adaptation through graphs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6568\u20136577 (2019)","DOI":"10.1109\/CVPR.2019.00673"},{"key":"9_CR17","doi-asserted-by":"crossref","unstructured":"Sun, Q., Liu, Y., Chua, T.S., Schiele, B.: Meta-transfer learning for few-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 403\u2013412 (2019)","DOI":"10.1109\/CVPR.2019.00049"},{"key":"9_CR18","doi-asserted-by":"crossref","unstructured":"Chang, W.G., You, T., Seo, S., Kwak, S., Han, B.: Domain-specific batch normalization for unsupervised domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7354\u20137362 (2019)","DOI":"10.1109\/CVPR.2019.00753"},{"key":"9_CR19","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/j.patcog.2018.03.005","volume":"80","author":"Y Li","year":"2018","unstructured":"Li, Y., Wang, N., Shi, J., Hou, X., Liu, J.: Adaptive batch normalization for practical domain adaptation. Pattern Recognit. 80, 109\u2013117 (2018)","journal-title":"Pattern Recognit."},{"key":"9_CR20","doi-asserted-by":"publisher","first-page":"692","DOI":"10.1016\/j.imavis.2014.06.002","volume":"32","author":"X Zhang","year":"2014","unstructured":"Zhang, X., et al.: Bp4d-spontaneous: a high-resolution spontaneous 3D dynamic facial expression database. Image Vision Comput. 32, 692\u2013706 (2014)","journal-title":"Image Vision Comput."},{"key":"9_CR21","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1109\/T-AFFC.2013.4","volume":"4","author":"SM Mavadati","year":"2013","unstructured":"Mavadati, S.M., Mahoor, M.H., Bartlett, K., Trinh, P., Cohn, J.F.: Disfa: a spontaneous facial action intensity database. IEEE Trans. Affect. Comput. 4, 151\u2013160 (2013)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"9_CR22","doi-asserted-by":"crossref","unstructured":"Zhang, Z., et al.: Multimodal spontaneous emotion corpus for human behavior analysis. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.374"},{"key":"9_CR23","doi-asserted-by":"crossref","unstructured":"Li, W., Abtahi, F., Zhu, Z., Yin, L.: Eac-net: a region-based deep enhancing and cropping approach for facial action unit detection. arXiv preprint arXiv:1702.02925 (2017)","DOI":"10.1109\/FG.2017.136"},{"key":"9_CR24","doi-asserted-by":"publisher","first-page":"420","DOI":"10.1037\/0033-2909.86.2.420","volume":"86","author":"PE Shrout","year":"1979","unstructured":"Shrout, P.E., Fleiss, J.L.: Intraclass correlations: uses in assessing rater reliability. Psychol. Bull. 86, 420 (1979)","journal-title":"Psychol. Bull."},{"key":"9_CR25","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"9_CR26","unstructured":"Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, pp. 8024\u20138035 (2019)"},{"key":"9_CR27","first-page":"1871","volume":"9","author":"RE Fan","year":"2008","unstructured":"Fan, R.E., Chang, K.W., Hsieh, C.J., Wang, X.R., Lin, C.J.: Liblinear: a library for large linear classification. J. Mach. Learn. Res. 9, 1871\u20131874 (2008)","journal-title":"J. Mach. Learn. Res."},{"key":"9_CR28","doi-asserted-by":"crossref","unstructured":"Shao, Z., Liu, Z., Cai, J., Ma, L.: Deep adaptive attention for joint facial action unit detection and face alignment. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 705\u2013720 (2018)","DOI":"10.1007\/978-3-030-01261-8_43"},{"key":"9_CR29","doi-asserted-by":"crossref","unstructured":"Yang, H., Yin, L.: Learning temporal information from a single image for au detection. In: 2019 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019), pp. 1\u20138. IEEE (2019)","DOI":"10.1109\/FG.2019.8756556"},{"key":"9_CR30","doi-asserted-by":"crossref","unstructured":"Niu, X., Han, H., Yang, S., Huang, Y., Shan, S.: Local relationship learning with person-specific shape regularization for facial action unit detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 11917\u201311926 (2019)","DOI":"10.1109\/CVPR.2019.01219"},{"key":"9_CR31","doi-asserted-by":"crossref","unstructured":"Mei, C., Jiang, F., Shen, R., Hu, Q.: Region and temporal dependency fusion for multi-label action unit detection. In: 2018 24th International Conference on Pattern Recognition (ICPR), pp. 848\u2013853. IEEE (2018)","DOI":"10.1109\/ICPR.2018.8545069"},{"key":"9_CR32","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1016\/j.neucom.2019.03.082","volume":"355","author":"C Ma","year":"2019","unstructured":"Ma, C., Chen, L., Yong, J.: Au R-CNN: encoding expert prior knowledge into R-CNN for action unit detection. Neurocomputing 355, 35\u201347 (2019)","journal-title":"Neurocomputing"},{"key":"9_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/978-3-319-54184-6_10","volume-title":"Computer Vision \u2013 ACCV 2016","author":"S Eleftheriadis","year":"2017","unstructured":"Eleftheriadis, S., Rudovic, O., Deisenroth, M.P., Pantic, M.: Variational Gaussian process auto-encoder for ordinal prediction of facial action units. In: Lai, S.-H., Lepetit, V., Nishino, K., Sato, Y. (eds.) ACCV 2016. LNCS, vol. 10112, pp. 154\u2013170. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-54184-6_10"},{"key":"9_CR34","doi-asserted-by":"crossref","unstructured":"Walecki, R., Pavlovic, V., Schuller, B., Pantic, M., et al.: Deep structured learning for facial action unit intensity estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3405\u20133414 (2017)","DOI":"10.1109\/CVPR.2017.605"},{"key":"9_CR35","doi-asserted-by":"crossref","unstructured":"Niu, Z., Zhou, M., Wang, L., Gao, X., Hua, G.: Ordinal regression with multiple output CNN for age estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4920\u20134928 (2016)","DOI":"10.1109\/CVPR.2016.532"},{"key":"9_CR36","doi-asserted-by":"crossref","unstructured":"Linh Tran, D., Walecki, R., Eleftheriadis, S., Schuller, B., Pantic, M., et al.: Deepcoder: semi-parametric variational autoencoders for automatic facial action coding. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3190\u20133199 (2017)","DOI":"10.1109\/ICCV.2017.346"},{"key":"9_CR37","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"9_CR38","unstructured":"S\u00e1nchez-Lozano, E., Tzimiropoulos, G., Valstar, M.: Joint action unit localisation and intensity estimation through heatmap regression. In: BMVC (2018)"},{"key":"9_CR39","doi-asserted-by":"crossref","unstructured":"Kaltwang, S., Todorovic, S., Pantic, M.: Latent trees for estimating intensity of facial action units. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 296\u2013304 (2015)","DOI":"10.1109\/CVPR.2015.7298626"},{"key":"9_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhao, R., Dong, W., Hu, B.G., Ji, Q.: Bilateral ordinal relevance multi-instance regression for facial action unit intensity estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7034\u20137043 (2018)","DOI":"10.1109\/CVPR.2018.00735"},{"key":"9_CR41","doi-asserted-by":"crossref","unstructured":"Zhang, Y., et al.: Joint representation and estimator learning for facial action unit intensity estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3457\u20133466 (2019)","DOI":"10.1109\/CVPR.2019.00357"},{"key":"9_CR42","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Jiang, H., Wu, B., Fan, Y., Ji, Q.: Context-aware feature and label fusion for facial action unit intensity estimation with partially labeled data. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 733\u2013742 (2019)","DOI":"10.1109\/ICCV.2019.00082"},{"key":"9_CR43","first-page":"2579","volume":"9","author":"LVD Maaten","year":"2008","unstructured":"Maaten, L.V.D., Hinton, G.: Visualizing data using T-SNE. J. Mach. Learn. Res. 9, 2579\u20132605 (2008)","journal-title":"J. Mach. Learn. Res."}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2020"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-69541-5_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,2,25]],"date-time":"2021-02-25T11:05:40Z","timestamp":1614251140000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-69541-5_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030695408","9783030695415"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-69541-5_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"26 February 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kyoto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 December 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2020.kyoto\/","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":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"768","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":"254","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":"33% - 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","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","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":"The conference was held virtually.","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)"}}]}}