Journal
FRONTIERS IN PSYCHOLOGY
Volume 8, Issue -, Pages -Publisher
FRONTIERS MEDIA SA
DOI: 10.3389/fpsyg.2017.01745
Keywords
micro-expression recognition; deep learning; optical flow; convolutional neural network; feature fusion
Categories
Funding
- National Natural Science Foundation of China [61301297]
- National Natural Science Foundation of China (NSFC)
- German Research Foundation (DFG) in project Cross Modal Learning [NSFC 6162113608/DFG TRR-169]
- Southwest University Doctoral Foundation [SWU115093]
Ask authors/readers for more resources
Facial micro-expression is a brief involuntary facial movement and can reveal the genuine emotion that people try to conceal. Traditional methods of spontaneous micro-expression recognition rely excessively on sophisticated hand-crafted feature design and the recognition rate is not high enough for its practical application. In this paper, we proposed a Dual Temporal Scale Convolutional Neural Network (DTSCNN) for spontaneous micro-expressions recognition. The DTSCNN is a two-stream network. Different of stream of DTSCNN is used to adapt to different frame rate of micro-expression video clips. Each stream of DSTCNN consists of independent shallow network for avoiding the over fitting problem. Meanwhile, we fed the networks with optical-flow sequences to ensure that the shallow networks can further acquire higher-level features. Experimental results on spontaneous micro-expression databases (CASME I/II) showed that our method can achieve a recognition rate almost 10% higher than what some state-of-the-art method can achieve.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available