In this paper we present a general, flexible framework for learning mappings from images to actions by interacting with the environment. The basic idea is to introduce a feature-...
Pose estimation involves reconstructing the configuration of a moving body from images sequences. In this paper we present a general framework for pose estimation of unknown obje...
In this paper, we propose a sequential approach to hallucinate/synthesize high-resolution images of multiple facial expressions. We propose an idea of multi-resolution tensor for ...
Abstract This paper presents an approach to designing and implementing extensible computational models for perceiving systems based on a knowledge-driven joint inference approach. ...
An interpretation system finds the likely mappings from portions of an image to real-world objects. An interpretation policy specifies when to apply which imaging operator, to whi...