Active Appearance Models (AAMs) are generative parametric models that have been successfully used in the past to track faces in video. A variety of video applications are possible, including dynamic pose estimation for real-time user interfaces, lip-reading, and expression recognition. To construct an AAM, a number of training images of faces with a mesh of canonical feature points (usually hand-marked) are needed. All feature points have to be visible in all training images. However, in many scenarios parts of the face may be occluded. Perhaps the most common cause of occlusion is 3D pose variation, which can cause self-occlusion of the face. Furthermore, tracking using standard AAM fitting algorithms often fails in the presence of even small occlusions. In this paper we propose algorithms to construct AAMs from occluded training images and to efficiently track faces in videos containing occlusion. We evaluate our algorithms both quantitatively and qualitatively and show successful real-time face tracking on a number of image sequences containing varying degrees of occlusions.