My major areas of research have been in computer vision. As humans, we effortlessly use vision for most of our daily interactions with the world. While computer vision systems are already useful for many tasks, such as recognition of specific objects, augmented reality, and computational photography, there remain important future challenges, such as self-driving cars, that will require far better capabilities. My research is aimed at improving the capabilites of object recognition and large-scale image matching to enable a wide range of new applications.