A Hilbert space embedding of a distribution—in short, a kernel mean embedding—has
recently emerged as a powerful tool for machine learning and statistical inference. The basic …

Many questions of fundamental interest in today's science can be formulated as inference
problems: some partial, or noisy, observations are performed over a set of variables and the …

A general framework for constructing and using probabilistic models of complex systems that
would enable a computer to use available information for making decisions. Most tasks …

Traditional views of visual processing suggest that early visual neurons in areas V1 and V2
are static spatiotemporal filters that extract local features from a visual scene. The extracted …

Articulated hand-tracking systems have been widely used in virtual reality but are rarely
deployed in consumer applications due to their price and complexity. In this paper, we …

Causal discovery methods typically extract causal relations between multiple nodes
(variables) based on univariate observations of each node. However, one frequently …

In this paper, we propose the Deep Structured self-Driving Network (DSDNet), which
performs object detection, motion prediction, and motion planning with a single neural …

In this work, we address the problem of 3D pose estimation of multiple humans from multiple
views. This is a more challenging problem than single human 3D pose estimation due to the …

Automatic self-calibration of ad-hoc sensor networks is a critical need for their use in military
or civilian applications. In general, self-calibration involves the combination of absolute …

State-of-the-art research on MRFs, successful MRF applications, and advanced topics for
future study. This volume demonstrates the power of the Markov random field (MRF) in …