Gaze tracking is widely used in fatigue driving detection, eye disease diagnosis, mental illness diagnosis, website or advertising design, virtual reality, gaze-control devices and human-computer interaction. However, the influence of light, specular reflection and occlusion, the change of head pose, especially the ever-changing human pose in natural scenes, have brought great challenges to the accurate gaze tracking. In this paper, gaze tracking in natural scenes is studied, and a method based on Convolutional Neural Network (CNN) with residual blocks is proposed, in which attention mechanism is integrated into the network to improve the accuracy of gaze tracking. Furthermore, it is tested on the GazeFollow database which contains six kinds of databases. The results show that the performance of proposed method outperforms that of other state-of-the-art methods in natural scenes. Moreover, the proposed method has better real-time performance and is more suitable for practical applications.