{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T16:12:37Z","timestamp":1775837557963,"version":"3.50.1"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2024,11,25]],"date-time":"2024-11-25T00:00:00Z","timestamp":1732492800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,25]],"date-time":"2024-11-25T00:00:00Z","timestamp":1732492800000},"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":["Multimedia Systems"],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1007\/s00530-024-01552-0","type":"journal-article","created":{"date-parts":[[2024,11,25]],"date-time":"2024-11-25T06:05:51Z","timestamp":1732514751000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Facial action unit detection with emotion consistency: a cross-modal learning approach"],"prefix":"10.1007","volume":"30","author":[{"given":"Wenyu","family":"Song","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongxin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gaoyun","family":"An","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yun","family":"Duan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Laifu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,25]]},"reference":[{"key":"1552_CR1","doi-asserted-by":"crossref","unstructured":"Chen, Y., Chen, D., Wang, T., Wang, Y., Liang, Y.: Causal intervention for subject-deconfounded facial action unit recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a036, pp. 374\u2013382 (2022)","DOI":"10.1609\/aaai.v36i1.19914"},{"key":"1552_CR2","doi-asserted-by":"publisher","first-page":"108355","DOI":"10.1016\/j.patcog.2021.108355","volume":"122","author":"Y Chen","year":"2022","unstructured":"Chen, Y., Song, G., Shao, Z., Cai, J., Cham, T.J., Zheng, J.: Geoconv: Geodesic guided convolution for facial action unit recognition. Pattern Recogn. 122, 108355 (2022)","journal-title":"Pattern Recogn."},{"key":"1552_CR3","doi-asserted-by":"crossref","unstructured":"Cho, K., Van\u00a0Merri\u00ebnboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., Bengio, Y.: Learning phrase representations using rnn encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"1552_CR4","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":"1552_CR5","doi-asserted-by":"crossref","unstructured":"Cui, Z., Kuang, C., Gao, T., Talamadupula, K., Ji, Q.: Biomechanics-guided facial action unit detection through force modeling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 8694\u20138703 (2023)","DOI":"10.1109\/CVPR52729.2023.00840"},{"issue":"15","key":"1552_CR6","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":"1552_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":"1552_CR8","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1007\/BF01115465","volume":"1","author":"P Ekman","year":"1976","unstructured":"Ekman, P., Friesen, W.V.: Measuring facial movement. Environ. Psychol. Nonverbal Behav. 1, 56\u201375 (1976)","journal-title":"Environ. Psychol. Nonverbal Behav."},{"key":"1552_CR9","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":"1552_CR10","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":"1552_CR11","doi-asserted-by":"crossref","unstructured":"Jyoti, S., Sharma, G., Dhall, A.: A single hierarchical network for face, action unit and emotion detection. In: 2018 Digital Image Computing: Techniques and Applications (DICTA). pp.\u00a01\u20138. IEEE (2018)","DOI":"10.1109\/DICTA.2018.8615852"},{"key":"1552_CR12","doi-asserted-by":"crossref","unstructured":"Li, W., Abtahi, F., Zhu, Z.: Action unit detection with region adaptation, multi-labeling learning and optimal temporal fusing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 1841\u20131850 (2017)","DOI":"10.1109\/CVPR.2017.716"},{"key":"1552_CR13","doi-asserted-by":"crossref","unstructured":"Li, Z., Yin, L.: Multimodal facial action unit detection with physiological signals. In: ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). pp.\u00a01\u20135. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10096863"},{"key":"1552_CR14","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.\u00a033, pp. 8594\u20138601 (2019)","DOI":"10.1609\/aaai.v33i01.33018594"},{"issue":"11","key":"1552_CR15","doi-asserted-by":"publisher","first-page":"2583","DOI":"10.1109\/TPAMI.2018.2791608","volume":"40","author":"W Li","year":"2018","unstructured":"Li, W., Abtahi, F., Zhu, Z., Yin, L.: Eac-net: Deep nets with enhancing and cropping for facial action unit detection. IEEE Trans. Pattern Anal. Mach. Intell. 40(11), 2583\u20132596 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1552_CR16","doi-asserted-by":"crossref","unstructured":"Liu, Z., Dong, J., Zhang, C., Wang, L., Dang, J.: Relation modeling with graph convolutional networks for facial action unit detection. In: MultiMedia Modeling: 26th International Conference, MMM 2020, Daejeon, South Korea, January 5\u20138, 2020, Proceedings, Part II 26. pp. 489\u2013501. Springer (2020)","DOI":"10.1007\/978-3-030-37734-2_40"},{"key":"1552_CR17","doi-asserted-by":"crossref","unstructured":"Liu, P., Zhang, Z., Yang, H., Yin, L.: Multi-modality empowered network for facial action unit detection. In: 2019 IEEE Winter Conference on Applications of Computer Vision (WACV). pp. 2175\u20132184. IEEE (2019)","DOI":"10.1109\/WACV.2019.00235"},{"key":"1552_CR18","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":"1552_CR19","unstructured":"MacQueen, J., et\u00a0al.: Some methods for classification and analysis of multivariate observations. In: Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability. vol.\u00a01, pp. 281\u2013297. Oakland, CA, USA (1967)"},{"issue":"2","key":"1552_CR20","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(2), 151\u2013160 (2013)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"1552_CR21","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\/CVF Conference on Computer Vision and Pattern Recognition. pp. 11917\u201311926 (2019)","DOI":"10.1109\/CVPR.2019.01219"},{"key":"1552_CR22","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: Glove: Global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"1552_CR23","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":"1552_CR24","doi-asserted-by":"crossref","unstructured":"Shao, Z., Liu, Z., Cai, J., Wu, Y., Ma, L.: Facial action unit detection using attention and relation learning. IEEE Trans. Affect. Comput. 13(3), 1274\u20131289 (2019)","DOI":"10.1109\/TAFFC.2019.2948635"},{"key":"1552_CR25","doi-asserted-by":"crossref","unstructured":"Shao, Z., Zhou, Y., Cai, J., Zhu, H., Yao, R.: Facial action unit detection via adaptive attention and relation. IEEE Trans. Image Process. 32, 3354\u20133366 (2023)","DOI":"10.1109\/TIP.2023.3277794"},{"key":"1552_CR26","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1007\/s11263-020-01378-z","volume":"129","author":"Z Shao","year":"2021","unstructured":"Shao, Z., Liu, Z., Cai, J., Ma, L.: Jaa-net: joint facial action unit detection and face alignment via adaptive attention. Int. J. Comput. Vis. 129, 321\u2013340 (2021)","journal-title":"Int. J. Comput. Vis."},{"key":"1552_CR27","doi-asserted-by":"crossref","unstructured":"Song, T., Chen, L., Zheng, W., Ji, Q.: Uncertain graph neural networks for facial action unit detection. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a035, pp. 5993\u20136001 (2021)","DOI":"10.1609\/aaai.v35i7.16748"},{"key":"1552_CR28","doi-asserted-by":"crossref","unstructured":"Song, T., Cui, Z., Zheng, W., Ji, Q.: Hybrid message passing with performance-driven structures for facial action unit detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 6267\u20136276 (2021)","DOI":"10.1109\/CVPR46437.2021.00620"},{"key":"1552_CR29","doi-asserted-by":"crossref","unstructured":"Tang, Y., Zeng, W., Zhao, D., Zhang, H.: Piap-df: Pixel-interested and anti person-specific facial action unit detection net with discrete feedback learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 12899\u201312908 (2021)","DOI":"10.1109\/ICCV48922.2021.01266"},{"key":"1552_CR30","unstructured":"Van der Maaten, L., Hinton, G.: Visualizing data using t-sne. J. Mach. Learn. Res. 9(86), 2579\u20132605 (2008)"},{"key":"1552_CR31","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30, 5998\u20136008 (2017)"},{"key":"1552_CR32","unstructured":"Wang, L., Wang, S., Qi, J.: Multi-modal multi-label facial action unit detection with transformer. arXiv preprint arXiv:2203.13301 (2022)"},{"key":"1552_CR33","doi-asserted-by":"crossref","unstructured":"Wang, C., Zeng, J., Shan, S., Chen, X.: Multi-task learning of emotion recognition and facial action unit detection with adaptively weights sharing network. In: 2019 IEEE International Conference on Image Processing (icip). pp. 56\u201360. IEEE (2019)","DOI":"10.1109\/ICIP.2019.8802914"},{"key":"1552_CR34","doi-asserted-by":"crossref","unstructured":"Yan, J., Wang, J., Li, Q., Wang, C., Pu, S.: Self-supervised regional and temporal auxiliary tasks for facial action unit recognition. In: Proceedings of the 29th ACM International Conference on Multimedia. pp. 1038\u20131046 (2021)","DOI":"10.1145\/3474085.3475674"},{"key":"1552_CR35","doi-asserted-by":"crossref","unstructured":"Yang, H., Yin, L., Zhou, Y., Gu, J.: Exploiting semantic embedding and visual feature for facial action unit detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 10482\u201310491 (2021)","DOI":"10.1109\/CVPR46437.2021.01034"},{"key":"1552_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Wang, T., Yin, L.: Region of interest based graph convolution: a heatmap regression approach for action unit detection. In: Proceedings of the 28th ACM International Conference on Multimedia. pp. 2890\u20132898 (2020)","DOI":"10.1145\/3394171.3413674"},{"key":"1552_CR37","doi-asserted-by":"crossref","unstructured":"Zhang, X., Yin, L., Cohn, J.F., Canavan, S., Reale, M., Horowitz, A., Liu, P.: A high-resolution spontaneous 3d dynamic facial expression database. In: 2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG). pp.\u00a01\u20136. IEEE (2013)","DOI":"10.1109\/FG.2013.6553788"},{"issue":"10","key":"1552_CR38","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., Yin, L., Cohn, J.F., Canavan, S., Reale, M., Horowitz, A., Liu, P., Girard, J.M.: Bp4d-spontaneous: a high-resolution spontaneous 3d dynamic facial expression database. Image Vis. Comput. 32(10), 692\u2013706 (2014)","journal-title":"Image Vis. Comput."},{"key":"1552_CR39","doi-asserted-by":"crossref","unstructured":"Zhao, K., Chu, W.S., De\u00a0la 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":"1552_CR40","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"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-024-01552-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-024-01552-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-024-01552-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T09:17:59Z","timestamp":1734340679000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-024-01552-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,25]]},"references-count":40,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2024,12]]}},"alternative-id":["1552"],"URL":"https:\/\/doi.org\/10.1007\/s00530-024-01552-0","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,25]]},"assertion":[{"value":"9 July 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 November 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 November 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"358"}}