Dual Temporal Scale Convolutional Neural Network for Micro-Expression Recognition

Dual Temporal Scale Convolutional Neural Network for Micro-Expression Recognition

Blog Article

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 Eye Shadow 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 Side Rails some state-of-the-art method can achieve.