We describe a neurally-inspired, unsupervised learning algorithm that builds a non-linear generative model for pairs of face images from the same individual. Individuals are then ...
Abstract-- A main difficulty that arises in the context of probabilistic localization is the design of an appropriate observation model, i.e., determining the likelihood of a senso...
Maren Bennewitz, Cyrill Stachniss, Sven Behnke, Wo...
Low-dimensional topic models have been proven very useful for modeling a large corpus of documents that share a relatively small number of topics. Dimensionality reduction tools s...
This paper presents an approach to visualize and analyze 3D building information models within virtual 3D city models. Building information models (BIMs) formalize and represent d...
Metric Labeling problems have been introduced as a model for understanding noisy data with pair-wise relations between the data points. One application of labeling problems with pa...