The goal of the study described in this paper was to gain an improved understanding of the social context of UK online centres and issues around the creation and exchange of knowl...
We propose a hybrid body representation that represents each typical pose by both template-like view information and part-based structural information. Specifically, each body par...
Purpose Knowledge management for space exploration is part of a multi-generational effort. Each mission builds on knowledge from prior missions, and learning is the first step in ...
In this work, we present an approach to jointly segment a rigid object in a 2D image and estimate its 3D pose, using the knowledge of a 3D model. We naturally couple the two proces...
Samuel Dambreville, Romeil Sandhu, Anthony J. Yezz...
One of the very interesting properties of Reinforcement Learning algorithms is that they allow learning without prior knowledge of the environment. However, when the agents use al...