[3] Gao H, Ma B. A robust improved network for facial expression recognition［J］. Frontiers in Signal Processing, 2020, 4(4): 4.
[4] Zhao Z, Liu Q, Wang S. Learning deep global multi-scale and local attention features for facial expression recognition in the wild［J］. IEEE Trans. on Image Processing, 2021, 30: 4973-4984.
[5] Hasani B, Mahoor M H. Facial expression recognition using enhanced deep 3D convolutional neural networks［C］// Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition Workshops, 2017: 30-40.
[6] Li D, Zhao X, Yuan G, et al. Robustness comparison between the capsule network and the convolutional network for facial expression recognition［J］. Appl. Intelligence, 2021, 51(4): 2269-2278.
[7] Ayidzoe M A, Yu Y, Mensah P K, et al. Gabor capsule network with preprocessing blocks for the recognition of complex images［J］. Machine Vision and Applications, 2021, 32(4): 1-16.
[8] Mensah P K, Weyori B A, Ayidzoe M A. Evaluating shallow capsule networks on complex images［J］. Inter. J. of Information Technol., 2021, 13(3): 1047-1057.
[9] Li Wei, Abtahi F, Zhu Z, et al. EAC-Net: Deep nets with enhancing and cropping for facial action unit detection［J］. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2018, 40(11): 2583-2596.
[10] Cao Shan, Yao Yuqian, An Gaoyun. E2-capsule neural networks for facial expression recognition using AU-aware attention［J］. IET Image Processing, 2020, 14(11): 2417-2424.
[13] Stergiou A, Poppe R, Kalliatakis G. Refining activation downsampling with Softpool［J］. arXiv preprint: 2101.00440.
[14] Li S, Deng W. Reliable crowdsourcing and deep locality-preserving learning for unconstrained facial expression recognition［J］. IEEE Trans. on Image Processing, 2018, 28(1): 356-370.
[15] Vielzeuf V, Kervadec C, Pateux S , et al. An Occams Razor view on learning audiovisual emotion recognition with small training sets［C］// Proc. of the 20th ACM Inter. Conf. on Multimodal Interaction, 2018: 589-593.
[16] Li Y, Zeng J, Shan S, et al. Occlusion aware facial expression recognition using CNN with attention mechanism［J］. IEEE Trans. on Image Processing, 2018, 28(5): 2439-2450.
[17] Zhou Jiancan, Jia Xi, Shen Linlin, et al. Improved softmax loss for deep learning-based face and expression recognition［J］. Cognitive Computation and Systems, 2019, 1(4): 97-102.
[18] Tian Yi, Wen Zhiwei, Xie Weicheng, et al. Outlier-suppressed triplet loss with adaptive class-aware margins for facial expression recognition［C］// 2019 IEEE Inter. Conf. on Image Processing (ICIP), 2019: 46-50.
