Learn More
Acknowledgements During the last three years, my work has beneeted greatly from discussions with where I learnt the nal tools needed for this research. I hope that the ideas in this dissertation will only be used towards peaceful ends. This is the second edition of my thesis. Some typographical errors have been corrected, and a small number of clariications(More)
To illustrate the potential of multilayer neural networks for adaptive interfaces, a VPL Data-Glove connected to a DECtalk speech synthesizer via five neural networks was used to implement a hand-gesture to speech system. Using minor variations of the standard backpropagation learning procedure, the complex mapping of hand movements to speech is learned(More)
People have aesthetic experiences when they manipulate objects skillfully. Highly skilled performance with an object requires forming a highly intimate relationship with it. Aesthetics flow from this intimacy. This paper discusses three works which bring together technology and art to illustrate the issues of intimacy and embodiment. The three works are:(More)
We propose a linear programming relaxation scheme for the class of multiple object tracking problems where the inter-object interaction metric is convex and the intra-object term quantifying object state continuity may use any metric. The proposed scheme models object tracking as a multi-path searching problem. It explicitly models track interaction , such(More)
We define a two-axis transparency framework that can be used as a predictor of the expressivity of a musical device. One axis is the player's transparency scale, while the other is the audience's transparency scale. Through consideration of both traditional instrumentation and new technology-driven interfaces, we explore the role that metaphor plays in(More)
In this paper, we propose a multi-camera video surveillance system with automatic camera selection. A new confidence measure, Quality-Of-View (QOV), is defined to automatically evaluate the camera's view performance for each time instant. This measure takes into account view angle and distance from subjects. By comparing each camera's QOVs, the system can(More)