We describe a method for learning classes of facial motion patterns from video of a human interacting with a computerized embodied agent. The method also learns correlations between the uncovered motion classes and the current interaction context. Our work is motivated by two hypotheses. First, a computer user’s facial displays will be context dependent, especially in the presence of an embodie...

Clustering is a key component in any data analysis toolbox. Despite its importance, scalable algorithms often eschew rich statistical models in favor of simpler descriptions such as k-means clustering. In this paper we present a sampler, capable of estimating mixtures of exponential families. At its heart lies a novel proposal distribution using random projections to achieve high throughput in ...

We investigate a novel cluster-of-bandit algorithm CAB for collaborative recommendation tasks that implements the underlying feedback sharing mechanism by estimating the neighborhood of users in a context-dependent manner. CAB makes sharp departures from the state of the art by incorporating collaborative effects into inference as well as learning processes in a manner that seamlessly interleav...

This paper introduces an architecture for rhythm recognition and comparative analysis. A fuzzy system is used to rate segmentation and structural assignment produced by combinatorial pattern-matching. The fuzzy system can be trained by examples. It provides fault tolerant, context sensitive and adaptive recognition of musical rhythm with a description of temporal and structural deviations.

Training of continuous density hidden Markov models (CDHMMs) is usually time-consuming and tedious due to the large number of model parameters involved. Recently we proposed a new derivative of CDHMM, the subspace distribution clustering hidden Markov model (SDCHMM) which tie CDHMMs at the ner level of subspace distributions, resulting in many fewer model parameters. An SDCHMM training algorith...

We investigate an efficient context-dependent clustering technique for recommender systems based on exploration-exploitation strategies through multi-armed bandits over multiple users. Our algorithm dynamically groups users based on their observed behavioral similarity during a sequence of logged activities. In doing so, the algorithm reacts to the currently served user by shaping clusters arou...

This work describes the CASE tool that provides support for CSRML (Collaborative Systems Requirements Modeling Language), an i* extension for specifying CSCW systems requirements. The tool has been implemented as a Visual Studio 2012 extension by using the Visualization and Modeling SDK. It supports all the CSRML characteristics, such as the specification of collaborative tasks with Workspace A...

We propose to create and study a new model for the micro-typography part of automated multilingual typesetting. This new model will support quality typesetting for a number of modern and ancient scripts. The major innovations in the proposal are: the process is refined into four phases, each dependent on a multidimensional tree-structured context summarizing the current linguistic and cultural ...

We present two new transformation techniques for proving termination of context-sensitive rewriting. Our rst method is simple, sound, and more powerful than previously suggested transformations. However, it is not complete, i.e., there are terminating context-sensitive rewrite systems that are transformed into non-terminating term rewrite systems. The second method that we present in this paper...

Several procedures are considered for testing numerically the performances of some two-dimensional position sensitive gas detectors (PSD) . The response of a PSD to a homogeneous flux of scattered neutrons is modelled by a two-dimensional Poisson process and specific statistical tests and techniques are developed in order to determine the PSD's characteristics. Two approaches are used: the firs...