We present an unsupervised algorithm for aligning a pair of shapes in the presence of significant articulated motion and missing data, while assuming no knowledge of a template, u...
: Fast and accurate 3D object reconstruction and partial 3D component retrieval from 2D image slices represent a difficult and challenging problem. To group related objects on diff...
This paper shows (i) improvements over state-of-the-art local feature recognition systems, (ii) how to formulate principled models for automatic local feature selection in object c...
Determining the position of breaks in a sentence is a key task for a text-to-speech (TTS) system. We describe some methods for phrase break prediction in which the whole sentence ...
In this paper we introduce Active Monte Carlo Recognition (AMCR), a new approach for object recognition. The method is based on seeding and propagating "relational" part...