Open Access

ARTICLE

Robust Facial Landmark Detection via Transformer-Conv Attention

Zhi Zhang^1,2, Bingyu Sun^1,*

1 Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei, China
2 Science Island Branch, Graduate School of University of Science and Technology of China, Hefei, China

* Corresponding Author: Bingyu Sun. Email:

(This article belongs to the Special Issue: Bridging the Gap: AutoML and Explainable AI for Industrial and Healthcare Innovations)

Computers, Materials & Continua 2026, 87(3), 13 https://doi.org/10.32604/cmc.2026.076236

Received 17 November 2025; Accepted 12 January 2026; Issue published 09 April 2026

Abstract

In facial landmark detection, shape deviations induced by large poses and exaggerated expressions often prevent existing algorithms from simultaneously achieving fine-grained local accuracy and holistic global shape constraints. To address this, we propose a Transformer-Conv Attention-based Method (TCAM). Built upon a hybrid coordinate-heatmap regression backbone, TCAM integrates the long-range dependency modeling of Transformers with the local feature extraction advantages of Depthwise Convolution (DWConv). Specifically, by partitioning feature maps into sub-regions and applying Transformer modeling, the module enforces sparse linear constraints on global information, effectively mitigating the issues caused by discontinuous landmark distributions. Experimental results on the WFLW, COFW, and 300W datasets demonstrate that TCAM significantly outperforms current state-of-the-art methods. Notably, the Normalized Mean Error (NME) is reduced by 0.24% and 0.21% on the large pose and exaggerated expression subsets, respectively, validating the superior robustness of the proposed model.

---

Keywords

---