In recent work we have presented a formal framework for linguistic annotation based on labeled acyclic digraphs. These `annotation graphs' oer a simple yet powerful method fo...
Two fast illumination invariant image retrieval methods for scenes comprising textured objects with variable illumination are introduced. Both methods are based on texture gradien...
One important issue in designing state-of-the-art LVCSR systems is the choice of acoustic units. Context dependent (CD) phones remain the dominant form of acoustic units. They can...
Xunying Liu, Mark John Francis Gales, Jim L. Hiero...
Background: Recent approaches for predicting the three-dimensional (3D) structure of proteins such as de novo or fold recognition methods mostly rely on simplified energy potentia...
A prototype-based approach is introduced for action
recognition. The approach represents an action as a se-
quence of prototypes for efficient and flexible action match-
ing in ...