{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T15:14:20Z","timestamp":1784301260503,"version":"3.55.0"},"reference-count":63,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T00:00:00Z","timestamp":1729123200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T00:00:00Z","timestamp":1729123200000},"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":["Int J Comput Vis"],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1007\/s11263-024-02258-6","type":"journal-article","created":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T19:03:08Z","timestamp":1729191788000},"page":"1711-1726","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":24,"title":["Facial Action Unit Detection by Adaptively Constraining Self-Attention and Causally Deconfounding Sample"],"prefix":"10.1007","volume":"133","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9383-8384","authenticated-orcid":false,"given":"Zhiwen","family":"Shao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hancheng","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Xiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bing","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lizhuang","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,17]]},"reference":[{"key":"2258_CR1","unstructured":"Besserve, M., Mehrjou, A., Sun, R., Sch\u00f6lkopf, B. (2020). Counterfactuals uncover the modular structure of deep generative models. In: International Conference on Learning Representations."},{"key":"2258_CR2","doi-asserted-by":"crossref","unstructured":"Chang, Y., Wang, S. (2022). Knowledge-driven self-supervised representation learning for facial action unit recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, IEEE, pp. 20417\u201320426.","DOI":"10.1109\/CVPR52688.2022.01977"},{"issue":"1","key":"2258_CR3","doi-asserted-by":"publisher","first-page":"374","DOI":"10.1609\/aaai.v36i1.19914","volume":"36","author":"Yingjie Chen","year":"2022","unstructured":"Chen, Yingjie, Chen, Diqi, Wang, Tao, Wang, Yizhou, & Liang, Yun. (2022). Causal intervention for subject-deconfounded facial action unit recognition. Proceedings of the AAAI Conference on Artificial Intelligence, 36(1), 374\u2013382. https:\/\/doi.org\/10.1609\/aaai.v36i1.19914","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2258_CR4","doi-asserted-by":"crossref","unstructured":"Chu, W.S., De\u00a0la Torre, F., Cohn, J.F. (2017). Learning spatial and temporal cues for multi-label facial action unit detection. In: IEEE International Conference on Automatic Face & Gesture Recognition, IEEE, pp. 25\u201332.","DOI":"10.1109\/FG.2017.13"},{"key":"2258_CR5","doi-asserted-by":"crossref","unstructured":"Corneanu, C. A., Madadi, M., & Escalera, S. (2018). In: European Conference on Computer Vision. Deep structure inference network for facial action unit recognition (pp. 309\u2013324). Springer.","DOI":"10.1007\/978-3-030-01258-8_19"},{"key":"2258_CR6","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N. (2021). An image is worth 16x16 words: Transformers for image recognition at scale. In: International Conference on Learning Representations."},{"key":"2258_CR7","doi-asserted-by":"crossref","unstructured":"Ekman, P., & Friesen, W. .V. (1978). Facial action coding system: A technique for the measurement of facial movement. Consulting Psychologists Press.","DOI":"10.1037\/t27734-000"},{"key":"2258_CR8","unstructured":"Ekman, P., Friesen, W.V., Hager, J.C. (2002). Facial action coding system. Research Nexus."},{"issue":"2","key":"2258_CR9","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1109\/TBIOM.2020.2977225","volume":"2","author":"IO Ertugrul","year":"2020","unstructured":"Ertugrul, I. O., Cohn, J. F., Jeni, L. A., Zhang, Z., Yin, L., & Ji, Q. (2020). Crossing domains for au coding: Perspectives, approaches, and measures. IEEE Transactions on Biometrics, Behavior, and Identity Science, 2(2), 158\u2013171.","journal-title":"IEEE Transactions on Biometrics, Behavior, and Identity Science"},{"key":"2258_CR10","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. (2008). Liblinear: A library for large linear classification. Journal of Machine Learning Research, 9, 1871\u20131874.","journal-title":"Journal of Machine Learning Research"},{"key":"2258_CR11","doi-asserted-by":"crossref","unstructured":"Girard, J.M., Chu, W.S., Jeni, L.A., Cohn, J.F. (2017). Sayette group formation task (gft) spontaneous facial expression database. In: IEEE International Conference on Automatic Face & Gesture Recognition, IEEE, pp. 581\u2013588.","DOI":"10.1109\/FG.2017.144"},{"key":"2258_CR12","doi-asserted-by":"crossref","unstructured":"He, J., Li, D., Yang, B., Cao, S., Sun, B., Yu, L. (2017). Multi view facial action unit detection based on cnn and blstm-rnn. In: IEEE International Conference on Automatic Face & Gesture Recognition, IEEE, pp. 848\u2013853.","DOI":"10.1109\/FG.2017.108"},{"key":"2258_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J. (2016). Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, IEEE, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"2258_CR14","unstructured":"Jacob, G.M., Stenger, B. (2021). Facial action unit detection with transformers. In: IEEE Conference on Computer Vision and Pattern Recognition, IEEE, pp. 7680\u20137689."},{"key":"2258_CR15","unstructured":"Kingma, D.P., Welling, M. (2014). Auto-encoding variational bayes. In: Bengio Y, LeCun Y (eds) International Conference on Learning Representations."},{"key":"2258_CR16","unstructured":"Kollias, D., Zafeiriou, S. (2019). Expression, affect, action unit recognition: Aff-wild2, multi-task learning and arcface. In: British Machine Vision Conference, BMVA Press, p 297."},{"key":"2258_CR17","doi-asserted-by":"crossref","unstructured":"Kollias, D., Zafeiriou, S. (2021). Analysing affective behavior in the second abaw2 competition. In: IEEE International Conference on Computer Vision Workshops, IEEE, pp 3652\u20133660.","DOI":"10.1109\/ICCVW54120.2021.00408"},{"key":"2258_CR18","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E. (2012). Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, Curran Associates, Inc., pp 1097\u20131105."},{"issue":"1","key":"2258_CR19","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1214\/aoms\/1177729694","volume":"22","author":"S Kullback","year":"1951","unstructured":"Kullback, S., & Leibler, R. A. (1951). On information and sufficiency. The Annals of Mathematical Statistics, 22(1), 79\u201386.","journal-title":"The Annals of Mathematical Statistics"},{"key":"2258_CR20","doi-asserted-by":"crossref","unstructured":"Li, G., Zhu, X., Zeng, Y., Wang, Q., Lin, L. (2019a). Semantic relationships guided representation learning for facial action unit recognition. In: AAAI Conference on Artificial Intelligence, pp 8594\u20138601.","DOI":"10.1609\/aaai.v33i01.33018594"},{"issue":"11","key":"2258_CR21","doi-asserted-by":"crossref","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. (2018). Eac-net: Deep nets with enhancing and cropping for facial action unit detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(11), 2583\u20132596.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"7","key":"2258_CR22","doi-asserted-by":"crossref","first-page":"2559","DOI":"10.1109\/TIP.2013.2253477","volume":"22","author":"Y Li","year":"2013","unstructured":"Li, Y., Wang, S., Zhao, Y., & Ji, Q. (2013). Simultaneous facial feature tracking and facial expression recognition. IEEE Transactions on Image Processing, 22(7), 2559\u20132573.","journal-title":"IEEE Transactions on Image Processing"},{"key":"2258_CR23","doi-asserted-by":"crossref","unstructured":"Li, Y., Zeng, J., Shan, S., Chen, X. (2019b). Self-supervised representation learning from videos for facial action unit detection. In: IEEE Conference on Computer Vision and Pattern Recognition, IEEE, pp 10924\u201310933.","DOI":"10.1109\/CVPR.2019.01118"},{"key":"2258_CR24","doi-asserted-by":"crossref","unstructured":"Liu, B., Wang, D., Yang, X., Zhou, Y., Yao, R., Shao, Z., Zhao, J. (2022). Show, deconfound and tell: Image captioning with causal inference. In: IEEE Conference on Computer Vision and Pattern Recognition, IEEE, pp 18041\u201318050.","DOI":"10.1109\/CVPR52688.2022.01751"},{"key":"2258_CR25","first-page":"489","volume-title":"Relation Modeling with Graph Convolutional Networks for Facial Action Unit Detection","author":"Z Liu","year":"2020","unstructured":"Liu, Z., Dong, J., Zhang, C., Wang, L., & Dang, J. (2020). In: International Conference on Multimedia Modeling. Relation Modeling with Graph Convolutional Networks for Facial Action Unit Detection (pp. 489\u2013501). Springer."},{"key":"2258_CR26","doi-asserted-by":"crossref","unstructured":"Lopez-Paz, D., Nishihara, R., Chintala, S., Scholkopf, B., Bottou, L. (2017). Discovering causal signals in images. In: IEEE Conference on Computer Vision and Pattern Recognition, IEEE, pp 6979\u20136987.","DOI":"10.1109\/CVPR.2017.14"},{"key":"2258_CR27","unstructured":"Loshchilov, I., Hutter, F. (2019). Decoupled weight decay regularization. In: International Conference on Learning Representations."},{"key":"2258_CR28","doi-asserted-by":"crossref","unstructured":"Luo, B., Shen, J., Cheng, S., Wang, Y., Pantic, M. (2020). Shape constrained network for eye segmentation in the wild. In: IEEE Winter Conference on Applications of Computer Vision, IEEE, pp 1952\u20131960.","DOI":"10.1109\/WACV45572.2020.9093483"},{"key":"2258_CR29","doi-asserted-by":"crossref","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. (2019). Au R-CNN: Encoding expert prior knowledge into R-CNN for action unit detection. Neurocomputing, 355, 35\u201347.","journal-title":"Neurocomputing"},{"issue":"2","key":"2258_CR30","doi-asserted-by":"crossref","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. (2013). Disfa: A spontaneous facial action intensity database. IEEE Transactions on Affective Computing, 4(2), 151\u2013160.","journal-title":"IEEE Transactions on Affective Computing"},{"key":"2258_CR31","first-page":"483","volume-title":"Stacked Hourglass Networks for Human Pose Estimation","author":"A Newell","year":"2016","unstructured":"Newell, A., Yang, K., & Deng, J. (2016). In: European Conference on Computer Vision. Stacked Hourglass Networks for Human Pose Estimation (pp. 483\u2013499). Springer."},{"key":"2258_CR32","doi-asserted-by":"crossref","unstructured":"Niu, X., Han, H., Yang, S., Huang, Y., Shan, S. (2019). Local relationship learning with person-specific shape regularization for facial action unit detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 11917\u201311926.","DOI":"10.1109\/CVPR.2019.01219"},{"key":"2258_CR33","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., Desmaison, A., Kopf, A., Yang, E., DeVito, Z., Raison, M., Tejani, A., Chilamkurthy, S., Steiner, B., Fang, L., Bai, J., Chintala, S. (2019). Pytorch: An imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, Curran Associates, Inc., pp 8024\u20138035."},{"key":"2258_CR34","unstructured":"Pearl, J., Glymour, M., Jewell, N.P. (2016). Causal inference in statistics: A primer. John Wiley & Sons."},{"key":"2258_CR35","unstructured":"Pearl, J., et al. (2000). Models, reasoning and inference.Cambridge, UK: CambridgeUniversityPress, 19(2), 3."},{"key":"2258_CR36","doi-asserted-by":"crossref","unstructured":"Qi, J., Niu, Y., Huang, J., Zhang, H. (2020). Two causal principles for improving visual dialog. In: IEEE Conference on Computer Vision and Pattern Recognition, IEEE, pp 10860\u201310869.","DOI":"10.1109\/CVPR42600.2020.01087"},{"issue":"469","key":"2258_CR37","doi-asserted-by":"crossref","first-page":"322","DOI":"10.1198\/016214504000001880","volume":"100","author":"DB Rubin","year":"2005","unstructured":"Rubin, D. B. (2005). Causal inference using potential outcomes: Design, modeling, decisions. Journal of the American Statistical Association, 100(469), 322\u2013331.","journal-title":"Journal of the American Statistical Association"},{"key":"2258_CR38","doi-asserted-by":"crossref","unstructured":"Sankaran, N., Mohan, D.D., Setlur, S., Govindaraju, V., Fedorishin, D. (2019). Representation learning through cross-modality supervision. In: IEEE International Conference on Automatic Face & Gesture Recognition, IEEE, pp 1\u20138.","DOI":"10.1109\/FG.2019.8756519"},{"issue":"2","key":"2258_CR39","doi-asserted-by":"crossref","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. (2021). J\u00e2a-net: Joint facial action unit detection and face alignment via adaptive attention. International Journal of Computer Vision, 129(2), 321\u2013340.","journal-title":"International Journal of Computer Vision"},{"key":"2258_CR40","doi-asserted-by":"crossref","first-page":"4610","DOI":"10.1109\/TIP.2021.3073857","volume":"30","author":"Z Shao","year":"2021","unstructured":"Shao, Z., Zhu, H., Tang, J., Lu, X., & Ma, L. (2021). Explicit facial expression transfer via fine-grained representations. IEEE Transactions on Image Processing, 30, 4610\u20134621.","journal-title":"IEEE Transactions on Image Processing"},{"issue":"3","key":"2258_CR41","doi-asserted-by":"crossref","first-page":"1274","DOI":"10.1109\/TAFFC.2019.2948635","volume":"13","author":"Z Shao","year":"2022","unstructured":"Shao, Z., Liu, Z., Cai, J., Wu, Y., & Ma, L. (2022). Facial action unit detection using attention and relation learning. IEEE Transactions on Affective Computing, 13(3), 1274\u20131289.","journal-title":"IEEE Transactions on Affective Computing"},{"key":"2258_CR42","doi-asserted-by":"crossref","first-page":"3354","DOI":"10.1109\/TIP.2023.3277794","volume":"32","author":"Z Shao","year":"2023","unstructured":"Shao, Z., Zhou, Y., Cai, J., Zhu, H., & Yao, R. (2023). Facial action unit detection via adaptive attention and relation. IEEE Transactions on Image Processing, 32, 3354\u20133366.","journal-title":"IEEE Transactions on Image Processing"},{"key":"2258_CR43","doi-asserted-by":"crossref","unstructured":"Simonyan, K., Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations.","DOI":"10.1109\/ICCV.2015.314"},{"key":"2258_CR44","doi-asserted-by":"crossref","unstructured":"Song, T., Chen, L., Zheng, W., Ji, Q. (2021a). Uncertain graph neural networks for facial action unit detection. In: AAAI Conference on Artificial Intelligence, pp 5993\u20136001.","DOI":"10.1609\/aaai.v35i7.16748"},{"key":"2258_CR45","doi-asserted-by":"crossref","unstructured":"Song, T., Cui, Z., Zheng, W., Ji, Q. (2021b). Hybrid message passing with performance-driven structures for facial action unit detection. In: IEEE Conference on Computer Vision and Pattern Recognition, IEEE, pp 6267\u20136276.","DOI":"10.1109\/CVPR46437.2021.00620"},{"key":"2258_CR46","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z. (2016). Rethinking the inception architecture for computer vision. In: IEEE Conference on Computer Vision and Pattern Recognition, IEEE, pp 2818\u20132826.","DOI":"10.1109\/CVPR.2016.308"},{"issue":"1","key":"2258_CR47","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1038\/s42256-020-00280-0","volume":"3","author":"A Toisoul","year":"2021","unstructured":"Toisoul, A., Kossaifi, J., Bulat, A., Tzimiropoulos, G., & Pantic, M. (2021). Estimation of continuous valence and arousal levels from faces in naturalistic conditions. Nature Machine Intelligence, 3(1), 42\u201350.","journal-title":"Nature Machine Intelligence"},{"key":"2258_CR48","doi-asserted-by":"crossref","unstructured":"Valstar, M., Pantic, M. (2006). Fully automatic facial action unit detection and temporal analysis. In: IEEE Conference on Computer Vision and Pattern Recognition Workshop, IEEE, pp 149\u2013149.","DOI":"10.1109\/CVPRW.2006.85"},{"key":"2258_CR49","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., Polosukhin, I. (2017). Attention is all you need. In: Advances in Neural Information Processing Systems, Curran Associates, Inc., pp 5998\u20136008."},{"key":"2258_CR50","doi-asserted-by":"crossref","unstructured":"Wang, L., Qi, J., Cheng, J., Suzuki, K. (2022). Action unit detection by exploiting spatial-temporal and label-wise attention with transformer. In: IEEE Conference on Computer Vision and Pattern Recognition Workshops, IEEE, pp 2470\u20132475.","DOI":"10.1109\/CVPRW56347.2022.00276"},{"key":"2258_CR51","doi-asserted-by":"crossref","unstructured":"Wang, T., Huang, J., Zhang, H., Sun, Q. (2020). Visual commonsense r-cnn. In: IEEE Conference on Computer Vision and Pattern Recognition, IEEE, pp 10760\u201310770.","DOI":"10.1109\/CVPR42600.2020.01077"},{"key":"2258_CR52","unstructured":"Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhudinov, R., Zemel, R., Bengio, Y. (2015) Show, attend and tell: Neural image caption generation with visual attention. In: International Conference on Machine Learning, PMLR, pp 2048\u20132057."},{"issue":"10","key":"2258_CR53","doi-asserted-by":"crossref","first-page":"1198","DOI":"10.1109\/JPROC.2023.3257542","volume":"111","author":"J Yang","year":"2023","unstructured":"Yang, J., Hristov, Y., Shen, J., Lin, Y., & Pantic, M. (2023). Toward robust facial action units\u2019 detection. Proceedings of the IEEE, 111(10), 1198\u20131214.","journal-title":"Proceedings of the IEEE"},{"key":"2258_CR54","unstructured":"Yue, Z., Zhang, H., Sun, Q., Hua, X.S. (2020). Interventional few-shot learning. In: Advances in Neural Information Processing Systems, Curran Associates, Inc., pp 2734\u20132746."},{"key":"2258_CR55","unstructured":"Zhang, D., Zhang, H., Tang, J., Hua, X. S., & Sun, Q. (2020). Causal intervention for weakly-supervised semantic segmentation. Advances in Neural Information Processing Systems, 33, 655\u2013666."},{"key":"2258_CR56","unstructured":"Zhang, J., He, T., Sra, S., Jadbabaie, A. (2019). Why gradient clipping accelerates training: A theoretical justification for adaptivity. In: International Conference on Learning Representations."},{"key":"2258_CR57","unstructured":"Zhang, Q., Yang, Y.B. (2021). Rest: An efficient transformer for visual recognition. In: Advances in Neural Information Processing Systems, Curran Associates, Inc., pp 15475\u201315485."},{"key":"2258_CR58","unstructured":"Zhang, Q., Yang, Y.B. (2022). Rest v2: simpler, faster and stronger. In: Advances in Neural Information Processing Systems, Curran Associates, Inc., pp 36440\u201336452."},{"key":"2258_CR59","doi-asserted-by":"crossref","unstructured":"Zhang, W., Guo, Z., Chen, K., Li, L., Zhang, Z., Ding, Y., Wu, R., Lv, T., Fan, C. (2021). Prior aided streaming network for multi-task affective analysis. In: IEEE International Conference on Computer Vision Workshops, IEEE, pp 3539\u20133549.","DOI":"10.1109\/ICCVW54120.2021.00394"},{"issue":"10","key":"2258_CR60","doi-asserted-by":"crossref","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. (2014). Bp4d-spontaneous: A high-resolution spontaneous 3d dynamic facial expression database. Image and Vision Computing, 32(10), 692\u2013706.","journal-title":"Image and Vision Computing"},{"key":"2258_CR61","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Girard, J.M., Wu, Y., Zhang, X., Liu, P., Ciftci, U., Canavan, S., Reale, M., Horowitz, A., Yang, H., Cohn, J.F., Ji, Q., Yin, L. (2016). Multimodal spontaneous emotion corpus for human behavior analysis. In: IEEE Conference on Computer Vision and Pattern Recognition, IEEE, pp 3438\u20133446.","DOI":"10.1109\/CVPR.2016.374"},{"issue":"8","key":"2258_CR62","doi-asserted-by":"crossref","first-page":"3931","DOI":"10.1109\/TIP.2016.2570550","volume":"25","author":"K Zhao","year":"2016","unstructured":"Zhao, K., Chu, W. S., De la Torre, F., Cohn, J. F., & Zhang, H. (2016). Joint patch and multi-label learning for facial action unit and holistic expression recognition. IEEE Transactions on Image Processing, 25(8), 3931\u20133946.","journal-title":"IEEE Transactions on Image Processing"},{"key":"2258_CR63","doi-asserted-by":"crossref","unstructured":"Zhao, K., Chu, W.S., Zhang, H. (2016b). Deep region and multi-label learning for facial action unit detection. In: IEEE Conference on Computer Vision and Pattern Recognition, IEEE, pp 3391\u20133399.","DOI":"10.1109\/CVPR.2016.369"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02258-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-02258-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02258-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,30]],"date-time":"2025-03-30T21:59:43Z","timestamp":1743371983000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-02258-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,17]]},"references-count":63,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,4]]}},"alternative-id":["2258"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-02258-6","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,17]]},"assertion":[{"value":"26 December 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 September 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 October 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}