Development of a Lightweight Temporal Convolutional Network for Microexpression Recognition

• Author(s): Adeyemi, Ifeoluwa Olamiji; Falohun, Adeleye Samuel; Oguntoye Jonathan Ponmile; Ayinla, Michael Oluwaseun
• Paper ID: 1719374
• Page: 1644-1655
• Published Date: 18-07-2026
• Published In: Iconic Research And Engineering Journals
• Publisher: IRE Journals
• e-ISSN: 2456-8880
• Volume/Issue: Volume 10 Issue 1 July-2026

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

Citations

IRE Journals:
Adeyemi, Ifeoluwa Olamiji, Falohun, Adeleye Samuel, Oguntoye Jonathan Ponmile, Ayinla, Michael Oluwaseun "Development of a Lightweight Temporal Convolutional Network for Microexpression Recognition" Iconic Research And Engineering Journals Volume 10 Issue 1 2026 Page 1644-1655

IEEE:
Adeyemi, Ifeoluwa Olamiji, Falohun, Adeleye Samuel, Oguntoye Jonathan Ponmile, Ayinla, Michael Oluwaseun "Development of a Lightweight Temporal Convolutional Network for Microexpression Recognition" Iconic Research And Engineering Journals, vol. 10, no. 1, Jul. 2026

APA:
Adeyemi, Ifeoluwa Olamiji, Falohun, Adeleye Samuel, Oguntoye Jonathan Ponmile, Ayinla, Michael Oluwaseun (2026). Development of a Lightweight Temporal Convolutional Network for Microexpression Recognition. Iconic Research And Engineering Journals, 10(1).

MLA:
Adeyemi, Ifeoluwa Olamiji, Falohun, Adeleye Samuel, Oguntoye Jonathan Ponmile, Ayinla, Michael Oluwaseun "Development of a Lightweight Temporal Convolutional Network for Microexpression Recognition" Iconic Research And Engineering Journals, vol. 10, no. 1, Jul. 2026.

BibTeX

@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}
}