英文论文
-
文献类型
-
Journal article (JA)
-
题名
-
Micro-Expression Recognition Based on Optical Flow and PCANet
-
作者
-
Wang, Shiqi; Guan, Suen; Lin, Hui; Huang, Jianming; Long, Fei; Yao, Junfeng
-
作者单位
-
[Wang, Shiqi; Guan, Suen; Lin, Hui; Long, Fei; Yao, Junfeng] Xiamen Univ, Sch Informat, Xiamen 361005, Peoples R China. [Huang, Jianming; Long, Fei; Yao, Junfeng] Xiamen Univ, Ctr Digital Media Comp & Software Engn, Xiamen 361005, Peoples R China.
-
通讯作者地址
-
Xiamen Univ, Sch Informat, Xiamen 361005, Peoples R China.; Xiamen Univ, Ctr Digital Media Comp & Software Engn, Xiamen 361005, Peoples R China.
-
Email
-
wangshiqi@stu.xmu.edu.cn; gse2020XMU@foxmail.com; 24320182203231@stu.xmu.edu.cn; 24320142202428@stu.xmu.edu.cn; flong@xmu.edu.cn; yao0010@xmu.edu.cn
-
ResearchID
-
-
ORCID
-
-
期刊名称
-
Sensors
-
出版社
-
MDPI
-
ISSN
-
1424-8220
-
出版信息
-
2022-06-01, 22 (11)
-
JCR
-
3
-
影响因子
-
-
ISBN
-
-
基金
-
Natural Science Foundation of Fujian Province of China [2019J01001]; Industry-University-Research Project of Xiamen City [3502Z20203002]
-
会议名称
-
-
会议地点
-
-
会议开始日期
-
-
会议结束日期
-
-
关键词
-
Deep neural networks
-
摘要
-
Micro-expressions are rapid and subtle facial movements. Different from ordinary facial expressions in our daily life, micro-expressions are very difficult to detect and recognize. In recent years, due to a wide range of potential applications in many domains, micro-expression recognition has aroused extensive attention from computer vision. Because available micro-expression datasets are very small, deep neural network models with a huge number of parameters are prone to over-fitting. In this article, we propose an OF-PCANet+ method for micro-expression recognition, in which we design a spatiotemporal feature learning strategy based on shallow PCANet+ model, and we incorporate optical flow sequence stacking with the PCANet+ network to learn discriminative spatiotemporal features. We conduct comprehensive experiments on publicly available SMIC and CASME2 datasets. The results show that our lightweight model obviously outperforms popular hand-crafted methods and also achieves comparable performances with deep learning based methods, such as 3D-FCNN and ELRCN.
-
一级学科
-
Chemistry, Analytical; Engineering, Electrical & Electronic; Instruments & Instrumentation
-
WOS入藏号
-
WOS:000808840300001
-
EI收录号
-
20222312199778
-
DOI
-
10.3390/s22114296
-
ESI
-
-
收录于
-
SCIE, EI
-
返回