**2. Related works**

Deep learning has exhibited powerful automatic feature extraction capability in computer vision tasks such as image classification, object detection, and so on. Visual object tracking is one of the important research contents in the field of computer vision. The performance of the tracker can be greatly improved due to the applications of the deep learning. Currently, two kinds of deep learning models including convolution neural network and deep auto-encoder are mainly used in the visual object tracking to perform automatic feature extraction.
