In this paper, we address the problem of visual tracking by proposing a novel feature learning technique. Recently, correlation filter based methods have dominated the visual tracking community due to various reasons such as efficient dense matching in frequency domain and simple update strategy. Nevertheless, the studies of correlation filters utilize hand-crafted or pre-trained deep features of classification task without considering the correlation filter cost function. Thus, we attempt to learn deep convolutional features for correlation filter based object tracking. In our experiments on benchmark sequences, we observe a significant improvement over the hand-crafted features while decreasing the number of features utilized in the recent correlation filter based trackers.