用图神经网络建模面部特征点关系，提升情绪识别准确率与可解释性。
GLaRE: A Graph-based Landmark Region Embedding Network for Emotion Recognition
- 基于3D对齐的面部关键点构建分层粗化图，保留空间结构
- 在AffectNet上达64.89%准确率，FERG上达94.24%
- 区域嵌入机制增强模型可解释性，适合需要透明决策的场景
面部表情识别（FER）是计算机视觉中的关键任务，广泛应用于人机交互、监控和辅助技术。然而，遮挡、表情差异以及缺乏可解释性等问题制约了传统方法的性能。图神经网络（GNN）通过建模面部关键点间的关联关系，提供了结构化且可解释的学习方式。本文提出GLaRE——一种基于图的面部地标区域嵌入网络用于情绪识别。采用3D面部对齐提取关键点，并通过分层粗化构建商图以保持空间结构的同时降低复杂度。实验表明，该方法在AffectNet上达到64.89%准确率，在FERG上达到94.24%，优于多个现有基线。消融实验进一步证明，商图生成的区域级嵌入显著提升了预测性能。
原文摘要 · Abstract (English)
Facial expression recognition (FER) is a crucial task in computer vision with wide range of applications including human computer interaction, surveillance, and assistive technologies. However, challenges such as occlusion, expression variability, and lack of interpretability hinder the performance of traditional FER systems. Graph Neural Networks (GNNs) offer a powerful alternative by modeling relational dependencies between facial landmarks, enabling structured and interpretable learning. In this paper, we propose GLaRE, a novel Graph-based Landmark Region Embedding network for emotion recognition. Facial landmarks are extracted using 3D facial alignment, and a quotient graph is constructed via hierarchical coarsening to preserve spatial structure while reducing complexity. Our method achieves 64.89 percentage accuracy on AffectNet and 94.24 percentage on FERG, outperforming several existing baselines. Additionally, ablation studies have demonstrated that region-level embeddings from quotient graphs have contributed to improved prediction performance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。