Abstract
The task of video facial expression recognition is widely applied in human-computer, psychology interaction and other fields. Existing methods are generally based on LSTM or CNN, but these frameworks are under-developed for the following two reasons. 1) Some own small memory capacity, and their memory storage encoded by hidden states cannot precisely remember past changes; 2) Others only focus on the local appearance of faces. Therefore, how to exploit longer dynamic facial changes and refine local information in video is a non-trivial work.
To solve the above problems, a two-stream interactive memory network based on channel/spatial attention(TM-CSA) is proposed in this paper. Specifically, a channel attention module attempts to extract more distinctive features among different channels, and a spatial attention module encodes the pixel-level context of the entire image. In this way, a interactive memory module of TM-CSA mines the interaction and correlation within and between images. Correspondingly, the TM-CSA has ability to remember enough past facts and reduce information redundancy. The experimental results tested on the three public datasets, JAFFE, CK+ and ImaSeDS show our TM-CSA has better performance.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
An, F., Liu, Z.: Facial expression recognition algorithm based on parameter adaptive initialization of cnn and lstm. The Visual Computer (2019)
Chen, L., Ouyang, y., Zeng, Y., Li, Y.: Dynamic facial expression recognition model based on bilstm-attention. In: ICCSE (2020)
Cugu, I., Sener, E., Akbas, E.: Microexpnet: An extremely small and fast model for expression recognition from face images. In: IPTA (2019)
Deng, L., Wang, Q., Yuan, D.: Dynamic facial expression recognition based on deep learning. In: 14th International Conference on Computer Science & Education, ICCSE 2019, Toronto, ON, Canada, 19–21 August 2019, pp. 32–37. IEEE (2019)
Ekman, P., Friesen, W.V.: A new pan-cultural facial expression of emotion. Motiv. Emot. 10(2), 159–168 (1986)
Eskil, M.T., Benli, K.S.: Facial expression recognition based on anatomy. Comput. Vis. Image Underst. 119, 1–14 (2014). https://doi.org/10.1016/j.cviu.2013.11.002
Benitez-Quiroz, C.F., Srinivasan, R., Martinez, A.M.: Discriminant functional learning of color features for the recognition of facial action units and their intensities. IEEE Trans. Pattern Anal. Mach. Intell. 41, 2835–2845 (2018)
Fan, X.: Tjahjadi, Tardi: a spatial-temporal framework based on histogram of gradients and optical flow for facial expression recognition in video sequences. Pattern Recogn. J. Pattern Recogn. Soc. 48(11), 3407–3416 (2015)
Goyani, M., Patel, N.: Template matching and machine learning-based robust facial expression recognition system using multi-level haar wavelet. Int. J. Comput. Appli. 42, 1–12 (2017)
Hu, M., Wang, H., Wang, X., Yang, J., Wang, R.: Video facial emotion recognition based on local enhanced motion history image and CNN-CTSLSTM networks. J. Vis. Commun. Image Represent. 59, 176–185 (2019)
Jain, S., Hu, C., Aggarwal, J.K.: Facial expression recognition with temporal modeling of shapes. In: ICCV (2011)
Jie, H., Li, S., Gang, S., Albanie, S.: Squeeze-and-excitation networks. IEEE Trans. Pattern Anal. Mach. Intell. 42, PP(99) (2017)
Lei, J., Liu, Z., Zou, Z., Li, T., Xu, J., Feng, Z., Liang, R.: Facial expression recognition by expression-specific representation swapping (2021)
Li, T.S., Kuo, P., Tsai, T., Luan, P.: CNN and LSTM based facial expression analysis model for a humanoid robot. IEEE Access 7, 93998–94011 (2019)
Li, Z., Wu, S., Xiao, G.: Facial expression recognition by multi-scale cnn with regularized center loss. In: ICPR (2018)
Liu, C., Hirota, K., Ma, J., Jia, Z., Dai, Y.: Facial expression recognition using hybrid features of pixel and geometry. IEEE Access PP(99), 1–1 (2021)
Lucey, P., Cohn, J.F., Kanade, T., Saragih, J., Matthews, I.: The extended cohn-kanade dataset (ck+): A complete dataset for action unit and emotion-specified expression. In: CVPR Workshops (2010)
Lyons, M.J., Kamachi, M., Gyoba, J.: Coding facial expressions with gabor wavelets (ivc special issue) (2020)
Meng, Z., Ping, L., Jie, C., Han, S., Yan, T.: Identity-aware convolutional neural network for facial expression recognition. In: IEEE International Conference on Automatic Face and Gesture Recognition (2017)
Miyoshi, R., Nagata, N., Hashimoto, M.: Facial-expression recognition from video using enhanced convolutional lstm. In: 2019 Digital Image Computing: Techniques and Applications (DICTA) (2019)
Munasinghe, M.I.N.P.: Facial expression recognition using facial landmarks and random forest classifier. In: 17th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2018, Singapore, 6–8 June 2018, pp. 423–427. IEEE Computer Society (2018)
Nigam, S., Singh, R., Misra, A.K.: Efficient facial expression recognition using histogram of oriented gradients in wavelet domain. Multimedia Tools Appli. 77(21), 28725–28747 (2018). https://doi.org/10.1007/s11042-018-6040-3
Scovanner, P., Ali, S., Shah, M.: A 3-dimensional sift descriptor and its application to action recognition. In: MM, pp. 357–360 (2007)
Sun, W., Zhao, H., Jin, Z.: A visual attention based roi detection method for facial expression recognition. Neurocomputing 296, 12–22 (2018)
Sun, X., Xia, P., Ren, F.: Multi-attention based deep neural network with hybrid features for dynamic sequential facial expression recognition. Neurocomputing 444, 378–389 (2020)
Sun, Z., Hu, Z.P., Chiong, R., Wang, M., He, W.: Combining the kernel collaboration representation and deep subspace learning for facial expression recognition. J. Circuits Syst. Comput. 27(8), 1850121.1-1850121.16 (2018)
Tang, D., Qin, B., Liu, T.: Aspect level sentiment classification with deep memory network (2016)
Wang, S., Zheng, Z., Yin, S., Yang, J., Ji, Q.: A novel dynamic model capturing spatial and temporal patterns for facial expression analysis. IEEE Trans. Pattern Anal. Mach. Intell. 42, 2082–2095 (2019)
Wang, Y., Hui, Y., Stevens, B., Liu, H.: Dynamic facial expression recognition using local patch and lbp-top. In: International Conference on Human System Interactions (2015)
Weston, J., Chopra, S., Bordes, A.: Memory networks. Eprint Arxiv (2014)
Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: CBAM: Convolutional block attention module. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 3–19. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01234-2_1
Xu, N., Mao, W., Chen, G.: Multi-interactive memory network for aspect based multimodal sentiment analysis. In: AAAI (2019)
Yu, J., Bhanu, B.: Evolutionary feature synthesis for facial expression recognition. Pattern Recognit. Lett. 27(11), 1289–1298 (2006)
Zagoruyko, S., Komodakis, N.: Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer (2016)
Zeng, Y., Cao, D., Lu, S., Zhang, H., Xu, J., Zheng, Q.: Moment is important: language-based video moment retrieval via adversarial learning. ACM Trans. Multim. Comput. Commun. Appl. 18, 56:1–56:21 (2022)
Zeng, Y., Cao, D., Wei, X., Liu, M., Zhao, Z., Qin, Z.: Multi-modal relational graph for cross-modal video moment retrieval. In: CVPR, pp. 2215–2224. IEEE (2021)
Zhao, G., Pietikainen, M.: Dynamic texture recognition using local binary patterns with an application to facial expressions. IEEE Trans. Pattern Anal. Mach. Intell. 29, 915–928 (2007)
Zhi, R., Wan, M.: Dynamic facial expression feature learning based on sparse rnn. In: ITAIC (2019)
Acknowledgements
This paper is supported by National College Student Innovation and Entrepreneurship Training Program (S202010500049).
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Chen, L., Ouyang, Y., Xu, R., Sun, S., Zeng, Y. (2022). Two-Stream Interactive Memory Network for Video Facial Expression Recognition. In: Pimenidis, E., Angelov, P., Jayne, C., Papaleonidas, A., Aydin, M. (eds) Artificial Neural Networks and Machine Learning – ICANN 2022. ICANN 2022. Lecture Notes in Computer Science, vol 13531. Springer, Cham. https://doi.org/10.1007/978-3-031-15934-3_25
Download citation
DOI: https://doi.org/10.1007/978-3-031-15934-3_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-15933-6
Online ISBN: 978-3-031-15934-3
eBook Packages: Computer ScienceComputer Science (R0)