Abstract

In the field of facial expression recognition (FER), two main trends point to the data-driven FER and feature-driven FER exist. The former focused on the data problems (e.g., sample imbalance and multimodal fusion), while the latter explored the facial expression features. As the feature-driven FER is more important than the data-driven FER, for deeper mining of facial features, we propose an expression recognition model based on Local–Global information Reasoning and Landmark Spatial Distributions. Particularly to reason local–global information, multiple attention mechanisms with the modified residual module are designed for the Res18-LG module. In addition, taking the spatial topology of facial landmarks into account, a topological relationship graph of landmarks and a two-layer graph neural network are introduced to extract spatial distribution features. Finally, the experiment results on FERPlus and RAF-DB datasets demonstrate that our model outperforms the state-of-the-art methods.

中文翻译：

---

基于局部-全局信息推理和地标特征空间分布的面部表情识别

摘要

在面部表情识别（FER）领域，存在数据驱动的 FER 和特征驱动的 FER 两个主要趋势。前者关注数据问题（例如样本不平衡和多模态融合），而后者则探索面部表情特征。由于特征驱动的 FER 比数据驱动的 FER 更重要，为了更深入地挖掘面部特征，我们提出了一种基于局部-全局信息推理和地标空间分布的表情识别模型。特别是为了推理局部-全局信息，为 Res18-LG 模块设计了带有修改后的残差模块的多种注意机制。此外，考虑到面部特征点的空间拓扑，引入特征点拓扑关系图和两层图神经网络来提取空间分布特征。最后，在 FERPlus 和 RAF-DB 数据集上的实验结果表明，我们的模型优于最先进的方法。