4.6 Article

Micro-expression action unit detection with spatial and channel attention

期刊

NEUROCOMPUTING
卷 436, 期 -, 页码 221-231

出版社

ELSEVIER
DOI: 10.1016/j.neucom.2021.01.032

关键词

Micro-expression analysis; AU detection; Deep learning; Second-order statistics; Covariance matrix

资金

  1. Infotech Oulu, National Natural Science Foundation of China [61772419, 62076122]
  2. Academy of Finland [316765]
  3. ICT 2023 project [328115]
  4. Jiangsu SpeciallyAppointed Professor Program
  5. Talent Startup project of NJIT [YKJ201982]
  6. Jiangsu joint research project of sinoforeign cooperative education platform and Technology Innovation Project of Nanjing for Oversea Scientist

向作者/读者索取更多资源

This paper focuses on AU detection in micro-expressions, proposing a novel method that utilizes self high-order statistics of spatio-wise and channel-wise features as spatial and channel attentions. By leveraging rich relationship information of facial regions through a spatial attention module, the method aims to increase AU detection robustness on limited micro-expression samples. Additionally, exploring high-order statistics for capturing subtle regional changes on face to obtain more discriminative AU features contributes to the improved performance of the proposed approach on CASME II, CASME, and SAMM datasets.
Action Unit (AU) detection plays an important role in facial behaviour analysis. In the literature, AU detection has extensive researches in macro-expressions. However, to the best of our knowledge, there is limited research about AU analysis for micro-expressions. In this paper, we focus on AU detection in micro-expressions. Due to the small quantity and low intensity of micro-expression databases, micro expression AU detection becomes challenging. To alleviate these problems, in this work, we propose a novel micro-expression AU detection method by utilizing self high-order statistics of spatio-wise and channel-wise features which can be considered as spatial and channel attentions, respectively. Through such spatial attention module, we expect to utilize rich relationship information of facial regions to increase the AU detection robustness on limited micro-expression samples. In addition, considering the low intensity of micro-expression AUs, we further propose to explore high-order statistics for better capturing subtle regional changes on face to obtain more discriminative AU features. Intensive experiments show that our proposed approach outperforms the basic framework by 0.0859 on CASME II, 0.0485 on CASME, and 0.0644 on SAMM in terms of the average F1-score. (c) 2021 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.6
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据