Facial micro-expression is a brief involuntary facial Vacuum PowerBrush™ Kit 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 Magnetic Playboard 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.