Facial expression recognition has been an active research area over the pastfew decades, and it is still challenging due to the high intra-class variation. Traditional approaches for this problem rely on hand-crafted features such asSIFT, HOG and LBP, followed by a classifier trained on a database of images orvideos. Most of these works perform reasonably well on datasets of images captured ina controlled condition, but fail to perform as good on more challengingdatasets with more image variation and partial faces. In recent years, several works proposed an end-to-end framework for facialexpression recognition, using deep learning models. Despite the better performance of these works, there still seems to be agreat room for improvement. In this work, we propose a deep learning approach based on attentionalconvolutional network, which is able to focus on important parts of the face,and achieves significant improvement over previous models on multiple datasets,including FER-2013, CK+, FERG, and JAFFE. We also use a visualization technique which is able to find important faceregions for detecting different emotions, based on the classifier's output. Through experimental results, we show that different emotions seems to besensitive to different parts of the face.