Current multimodal registration methods almost always rely on local gradient-descent type optimization strategies. Such registration methods often converge to an incorrect local o...
In this work we propose an approach to combine audio and video modalities for person tracking using graphical models. We demonstrate a principled and intuitive framework for combi...
Akash Kushal, Mandar Rahurkar, Fei-Fei Li 0002, Je...
A desirable property for any system dealing with unrestricted natural language text is robustness, the ability to analyze any input regardless of its grammaticality. In this paper ...
We propose a new data structure to search in metric spaces. A metric space is formed by a collection of objects and a distance function de ned among them, which satis es the trian...
Dynamic software visualization is designed to provide programmers with insights as to what the program is doing. Most current visualizations either use program traces to show info...