Abstract— Given an unstructured collection of captioned images of cluttered scenes featuring a variety of objects, our goal is to simultaneously learn the names and appearances o...
Michael Jamieson, Afsaneh Fazly, Suzanne Stevenson...
Sparse representation theory has been increasingly used in the fields of signal processing and machine learning. The standard sparse models are not invariant to spatial transform...
Supervised methods for learning an embedding aim to map high-dimensional images to a space in which perceptually similar observations have high measurable similarity. Most approac...
Graham Taylor, Ian Spiro, Rob Fergus, Christoph Br...
In this paper we present a novel boosting algorithm for supervised learning that incorporates invariance to data transformations and has high generalization capabilities. While on...