We present MI-Winnow, a new multiple-instance learning (MIL) algorithm that provides a new technique to convert MIL data into standard supervised data. In MIL each example is a co...
Sharath R. Cholleti, Sally A. Goldman, Rouhollah R...
We propose a new model for the probabilistic estimation of continuous state variables from a sequence of observations, such as tracking the position of an object in video. This ma...
This paper presents work on vision based robotic grasping. The proposed method adopts a learning framework where prototypical grasping points are learnt from several examples and ...
Abstract— We present a learning-based approach for longrange vision that is able to accurately classify complex terrain at distances up to the horizon, thus allowing high-level s...
Raia Hadsell, Ayse Erkan, Pierre Sermanet, Marco S...
A novel approach to scene categorization is proposed. Similar to previous works of [11, 15, 3, 12], we introduce an intermediate space, based on a low dimensional semantic "t...