Facial microexpressions offer useful insights into subtle human emotions. This unpremeditated emotional leakage exhibits the true emotions of a person. However, the minute temporal changes in the video sequences are very difficult to model for accurate classification. In this article, we propose a novel spatiotemporal architecture search algorithm, AutoMER for microexpression recognition (MER). Our main contribution is a new parallelogram design-based search space for efficient architecture search. We introduce a spatiotemporal feature module named 3-D singleton convolution for cell-level analysis. Furthermore, we present four such candidate operators and two 3-D dilated convolution operators to encode the raw video sequences in an end-to-end manner. To the best of our knowledge, this is the first attempt to discover 3-D convolutional neural network (CNN) architectures with a network-level search for MER. The searched models using the proposed AutoMER algorithm are evaluated over five microexpression data sets: CASME-I, SMIC, CASME-II, CAS(ME) 2^\hat{2} , and SAMM. The proposed generated models quantitatively outperform the existing state-of-the-art approaches. The AutoMER is further validated with different configurations, such as downsampling rate factor, multiscale singleton 3-D convolution, parallelogram, and multiscale kernels. Overall, five ablation experiments were conducted to analyze the operational insights of the proposed AutoMER.

中文翻译：

---

AutoMER：用于微表情识别的时空神经架构搜索


面部微表情提供了对人类微妙情感的有用见解。这种无意识的情绪泄露，展现了一个人的真实情绪。然而，视频序列中微小的时间变化很难建模以进行准确分类。在本文中，我们提出了一种新颖的时空架构搜索算法，即用于微表情识别（MER）的 AutoMER。我们的主要贡献是一个新的基于平行四边形设计的搜索空间，用于高效的架构搜索。我们引入了一种名为 3-D 单例卷积的时空特征模块，用于细胞级分析。此外，我们提出了四个这样的候选算子和两个 3D 扩张卷积算子，以端到端的方式对原始视频序列进行编码。据我们所知，这是通过网络级 MER 搜索来发现 3D 卷积神经网络 (CNN) 架构的首次尝试。使用所提出的 AutoMER 算法搜索的模型在五个微表情数据集上进行评估：CASME-I、SMIC、CASME-II、CAS(ME) 2^\hat{2} 和 SAMM。所提出的生成模型在数量上优于现有的最先进方法。 AutoMER 通过不同的配置进行了进一步验证，例如下采样率因子、多尺度单例 3-D 卷积、平行四边形和多尺度内核。总的来说，进行了五次消融实验来分析所提出的 AutoMER 的操作见解。