Given a set of images of scenes containing multiple object categories (e.g. grass, roads, buildings) our objective is to discover these objects in each image in an unsupervised man...
— Recent advances in the field of humanoid robotics increase the complexity of the tasks that such robots can perform. This makes it increasingly difficult and inconvenient to ...
The prediction of the native structures of proteins, the socalled protein folding problem, is a NP hard multi-minima optimization problem for which to date no routine solutions ex...
— In this paper we present a novel method for robot path planning based on learning motion patterns. A motion pattern is defined as the path that results from applying a set of ...
We describe a learning-based method for low-level vision problems--estimating scenes from images. We generate a synthetic world of scenes and their corresponding rendered images, m...