Many of the recently popular shape based category recognition methods require stable, connected and labeled edges as input. This paper introduces a novel method to find the most st...
Michael Donoser, Hayko Riemenschneider and Horst B...
This paper describes an experimental study about a robust contour feature (shape-context) for using in action recognition based on continuous hidden Markov models (HMM). We ran dif...
We present a Modular Bilinear Disciminant Analysis (MBDA) approach for face recognition. A set of classifiers are trained independently on specific face regions, and different c...
In this paper, we introduce the concept of SelfQuotient Image (SQI) for robust face recognition under varying lighting conditions. It is based on the Quotient Image method [4][5] ...
A new direction in improving modern dialogue systems is to make a human-machine dialogue more similar to a human-human dialogue. This can be done by adding more input modalities, e...