Segmenting the signal of a 3D-sensor represents a core problem in computer vision. Describing segments at the object level is a common requirement for higher-level tasks like action recognition. Non-parametric techniques can provide segmentation without prior model information. However, they are also prone to overand under-segmentation, especially in case of high occluded scenes. In this paper ...

The objective of this paper is to analyze the estimation quality of a staged methodology, that allows the estimation of signal timing information like cycle length, green and red time intervals for timedependent fixed-time controlled and actuated intersections based on low-frequency and sparse floating car data (FCD). The paper exemplifies, based on simulated dataset, the estimation approach, w...

In this paper, we propose epitomic variational autoencoder (eVAE), a probabilistic generative model of high dimensional data. eVAE is composed of a number of sparse variational autoencoders called ‘epitome’ such that each epitome partially shares its encoder-decoder architecture with other epitomes in the composition. We show that the proposed model greatly overcomes the common problem in varia...

This paper presents an efficient compilation algorithm that is several orders of magnitude faster than a standard method for context restriction rules. The new algorithm combines even hundreds of thousands of rules in parallel when the alphabet is large but the resulting automaton is sparse. The method opens new possibilities for representation of contextdependent lexical entries and the relate...

This paper discusses several lessons learned from the SpamTREC 2006 challenge. We discuss issues related to decoding, preprocessing, and tokenization of email messages. Using the Winnow algorithm with orthogonal sparse bigram features, we construct an efficient, highly scalable incremental classifier, trained to maximize a discriminative optimization criterion. The algorithm easily scales to mi...

Many decision problems exhibit structural properties in the sense that the objective function is a composition of different component functions that can be identified using empirical data. We consider the approximation of such objective functions, subject to general monotonicity constraints on the component functions. Using a constrained B-spline approximation, we provide a data-driven robust o...