Dual Temporal Scale Convolutional Neural Network for Micro-Expression Recognition
Clicks: 242
ID: 71456
2017
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 overfitting 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.
| Reference Key |
peng2017dualfrontiers
Use this key to autocite in the manuscript while using
SciMatic Manuscript Manager or Thesis Manager
|
|---|---|
| Authors | Peng, Min;Peng, Min;Wang, Chongyang;Wang, Chongyang;Chen, Tong;Chen, Tong;Chen, Tong;Liu, Guangyuan;Liu, Guangyuan;Fu, Xiaolan; |
| Journal | Frontiers in psychology |
| Year | 2017 |
| DOI | DOI not found |
| URL | |
| Keywords |
Citations
No citations found. To add a citation, contact the admin at info@scimatic.org
Comments
No comments yet. Be the first to comment on this article.