In this paper we present a system for mobile augmented reality (AR) based on visual recognition. We split the tasks of recognizing an object and tracking it on the user's screen into a server-side and a client-side task, respectively. The capabilities of this hybrid client-server approach are demonstrated with a prototype application on the Android platform, which is able to augment both stationary (landmarks) and non stationary (media covers) objects. The database on the server side consists of hundreds of thousands of landmarks, which is crawled using a state of the art mining method for community photo collections. In addition to the landmark images, we also integrate a database of media covers with millions of items. Retrieval from these databases is done using vocabularies of local visual features. In order to fulfill the real-time constraints for AR applications, we introduce a method to speed-up geometric verification of feature matches. The client-side tracking of recognized objects builds on a multi-modal combination of visual features and sensor measurements. Here, we also introduce a motion estimation method, which is more efficient and precise than similar approaches. To the best of our knowledge this is the first system, which demonstrates a complete pipeline for augmented reality on mobile devices with visual object recognition scaled to millions of objects combined with real-time object tracking.