综述图神经网络在面部表情识别中的应用方法与前景
A survey on Graph Deep Representation Learning for Facial Expression Recognition
- 用图结构建模面部关键点关系，捕捉表情动态变化
- 整合时空图与多流架构，提升复杂表情识别性能
- 适合关注图学习在视觉任务中应用的研究者
本文系统综述了图表示学习（GRL）在面部表情识别（FER）中的应用。首先介绍FER任务及图表示、GRL的基本概念，随后梳理常用数据集。重点探讨图扩散、时空图与多流架构等代表性方法。最后指出未来研究方向并总结进展，为该领域提供清晰技术脉络。
原文摘要 · Abstract (English)
This comprehensive review delves deeply into the various methodologies applied to facial expression recognition (FER) through the lens of graph representation learning (GRL). Initially, we introduce the task of FER and the concepts of graph representation and GRL. Afterward, we discuss some of the most prevalent and valuable databases for this task. We explore promising approaches for graph representation in FER, including graph diffusion, spatio-temporal graphs, and multi-stream architectures. Finally, we identify future research opportunities and provide concluding remarks.
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。