This paper presents a Bayesian framework for multi-cue 3D object tracking of deformable objects. The proposed spatio-temporal object representation involves a set of distinct linea...
Abstract. Multiple-instance learning (MIL) allows for training classifiers from ambiguously labeled data. In computer vision, this learning paradigm has been recently used in many ...
Abstract. This paper is concerned with arti cial evolution of neurocontrollers with adaptive synapses for autonomous mobile robots. The method consists of encoding on the genotype ...
Wireless Sensor Networks (WSNs) are challenging types of networks where resources can be scarce. In particular, battery is often a very limited resource and the radio interface is...
We propose an active vision system for object acquisition. The core of our approach is a reinforcement learning module which learns a strategy to scan an object. The agent moves a...
Gabriele Peters, Claus-Peter Alberts, Markus Bries...