The description of the object shape is an important characteristic of the image. In image processing and pattern recognition, several different shape descriptors are used. In huma...
Recently, a novel and structural representation of speech was proposed [1, 2], where the inevitable acoustic variations caused by nonlinguistic factors are effectively removed fro...
Situated, spontaneous speech may be ambiguous along acoustic, lexical, grammatical and semantic dimensions. To understand such a seemingly difficult signal, we propose to model th...
We present a method to represent unstructured scalar fields at multiple levels of detail. Using a parallelizable classification algorithm to build a cluster hierarchy, we generate...
A multitask learning framework is developed for discriminative classification and regression where multiple large-margin linear classifiers are estimated for different predictio...