Multi-label learning is useful in visual object recognition when several objects are present in an image. Conventional approaches implement multi-label learning as a set of binary...
Abstract. A handwritten digit recognition system was used in a demonstration project to visualize artificial neural networks, in particular Kohonen’s self-organizing feature map...
Abstract-- This paper introduces Evolutionary Pursuit (EP) as a novel and adaptive representation method for image encoding and classification. In analogy to projection pursuit met...
The Ambient Kitchen is a high fidelity prototype for exploring the design of pervasive computing algorithms and applications for everyday environments. The environment integrates ...
Patrick Olivier, Guangyou Xu, Andrew Monk, Jesse H...
Many vision tasks are posed as either graph partitioning (coloring) or graph matching (correspondence) problems. The former include segmentation and grouping, and the latter inclu...