no code implementations • 21 Apr 2017 • Sebastien C. Wong, Victor Stamatescu, Adam Gatt, David Kearney, Ivan Lee, Mark D. McDonnell
We argue that by transferring the use of prior knowledge from the detection and tracking stages to the classification stage we can design a robust, general purpose object recognition system with the ability to detect and track a variety of object types.
no code implementations • 28 Sep 2016 • Sebastien C. Wong, Adam Gatt, Victor Stamatescu, Mark D. McDonnell
In this paper we investigate the benefit of augmenting data with synthetically created samples when training a machine learning classifier.