Ensemble learning is an intensively studied technique in machine learning and pattern
recognition. Recent work in computational biology has seen an increasing use of ensemble …

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 …

Interactive image segmentation is characterized by multimodality. When the user clicks on a
door, do they intend to select the door or the whole house? We present an end-to-end …

Learning patterns of human behavior from sensor data is extremely important for high-level
activity inference. This paper describes how to extract a person's activities and significant …

The paper addresses the problem of generating multiple hypotheses for prediction tasks that
involve interaction with users or successive components in a cascade. Given a set of …

Much effort has been directed at algorithms for obtaining the highest probability (MAP)
configuration in probabilistic (random field) models. In many situations, one could benefit …

Structured prediction requires searching over a combinatorial number of structures. To
tackle it, we introduce SparseMAP, a new method for sparse structured inference, together …

Many dialog state tracking algorithms have been limited to generative modeling due to the
influence of the Partially Observable Markov Decision Process framework. Recent analyses …

We describe a method for generating N-best configurations from part-based models,
ensuring that they do not overlap according to some user-provided definition of overlap. We …

The goal of this work is to detect hand and arm positions over continuous sign language
video sequences of more than one hour in length. We cast the problem as inference in a …