Development of a Lightweight Temporal Convolutional Network for Microexpression Recognition

References

[1] Aouayeb, M., Hamidouche, W., Soladié, C., Kpalma, K., & Séguier, R. (2021). Micro-expression recognition from local facial regions. Signal Processing: Image Communication, 99, 116457.

[2] Cai, X., Tang, H., & Chai, L. (2023). Micro expression recognition based on graph convolutional networks with LSTM. In 2023 35th Chinese Control and Decision Conference (CCDC) (pp. 5449-5453). IEEE.

[3] Gan, Y. S., Liong, S. T., Yau, W. C., Huang, Y. C., & Tan, L. K. (2019). OFF-ApexNet on micro-expression recognition system. Signal Processing: Image Communication, 74, 129-139.

[4] Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., & Adam, H. (2017). MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv:1704.04861.

[5] Jin, H., He, N., Li, Z., & Yang, P. (2024). Micro-expression recognition based on multi-scale 3D residual convolutional neural network. Mathematical Biosciences and Engineering, 21(4), 5007-5031.

[6] Khor, H. Q., See, J., Liong, S. T., Phan, R. C. W., & Lin, W. (2019). Dual-stream shallow networks for facial micro-expression recognition. In IEEE International Conference on Image Processing (pp. 36-40). IEEE.

[7] Kim, D. H., Baddar, W. J., & Ro, Y. M. (2016). Micro-expression recognition with expression-state constrained spatio-temporal feature representations. In ACM International Conference on Multimedia (pp. 382-386).

[8] Li, J., Wang, Y., See, J., & Liu, W. (2018). Micro-expression recognition based on 3D flow convolutional neural network. Pattern Analysis and Applications, 22, 1331-1339.

[9] Peng, W., Hong, X., Xu, Y., & Zhao, G. (2019). A boost in revealing subtle facial expressions: A consolidated Eulerian framework. In IEEE FG 2019 (pp. 1-5).

[10] Verma, M., Satish, M., Reddy, K., Meedimale, Y., & Kumar, S. (2021). AutoMER: Spatiotemporal neural architecture search for microexpression recognition. IEEE Transactions on Affective Computing.

[11] Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004). Image quality assessment: From error visibility to structural similarity. IEEE Transactions on Image Processing, 13(4), 600-612.

[12] Wu, H.-Y., Rubinstein, M., Shih, E., Guttag, J., Durand, F., & Freeman, W. (2012). Eulerian video magnification for revealing subtle changes in the world. ACM Transactions on Graphics, 31(4), 1-8.

[13] Xue, F., Zhang, Y., Shao, Z., Cui, W., & Yuan, Z. (2025). HIM-PyraNet: Hierarchical attention and region-focused lightweight network for micro-expression recognition. Concurrency and Computation: Practice and Experience.

[14] Yu, Z., Chen, X., & Qu, C. (2024). SDGSA: A lightweight shallow dual-group symmetric attention network for micro-expression recognition. Complex & Intelligent Systems, 10, 8143-8162.

[15] Zhang, F., Huang, Z., Zhang, X., & Jin, Q. (2024). Adaptive temporal motion guided graph convolution network for micro-expression recognition. In IEEE International Conference on Multimedia and Expo.

[16] Zhang, L., & Arandjelović, O. (2021). Review of automatic microexpression recognition in the past decade. Machine Learning and Knowledge Extraction, 3(2), 414-434.

[17] Zong, Y., Zhang, M., & Zhao, G. (2020). Toward bridging microexpressions from different domains via domain adaptation methods. IEEE Transactions on Affective Computing, 13, 1117-1127.

@article{1719374,
      author = {Adeyemi, Ifeoluwa Olamiji, Falohun, Adeleye Samuel, Oguntoye Jonathan Ponmile, Ayinla, Michael Oluwaseun},
      title = {Development of a Lightweight Temporal Convolutional Network for Microexpression Recognition},
      journal = {Iconic Research And Engineering Journals},
      year = {2026},
      volume = {10},
      number = {1},
      pages = {1644-1655},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1719374.pdf},
      abstract = {Microexpression recognition (MER) remains challenging because facial movements are short, subtle, and usually require computationally expensive temporal models. This paper presents a lightweight depthwise-separable Temporal Convolutional Network (DS-TCN) for MER on the CASME II dataset. The model uses a dual-stream design that combines grayscale facial-frame features with optical-flow motion features after face cropping, Eulerian video magnification, resizing, and SSIM-based key-frame selection. Standard temporal convolutions are replaced with depthwise separable temporal convolutions to reduce parameter count and floating-point operations while preserving sequence learning. Three-fold cross-validation produced a validation accuracy of 72.6% and a macro-F1 score of 67.58%. Compared with the standard TCN baseline, the proposed DS-TCN reduced parameters from 1.57 M to 0.219 M, FLOPs from 10.33 G to 1.50 G, and CPU inference time from 580 ms to 210 ms. The results show that lightweight temporal modeling can provide competitive MER performance with substantially lower computational cost.},
      keywords = {CASME II, Depthwise Separable Convolution, Microexpression Recognition, Optical Flow, Temporal Convolutional Network},
      month = {July},
      doi = {https://doi.org/10.64388/IREV10I1-1719374}
  }