Abstract. This paper proposes a quasi-dense reconstruction from uncalibrated sequence. The main innovation is that all geometry is computed based on re-sampled quasi-dense correspo...
In a massive stream of sequential events such as stock feeds, sensor readings, or IP traffic measurements, tuples pertaining to recent events are typically more important than olde...
Many computer vision algorithms make use of local features, and rely on a systematic comparison of these features. The chosen dissimilarity measure is of crucial importance for th...
Two major challenges in collaborative filtering are the efficiency of the algorithms and the quality of the recommendations. A variety of machine learning methods have been applie...
In this paper, we propose a novel method for automatic, feature-based alignment of transmission electron microscope images that is needed for computing 3D reconstructions in elect...