We consider the problem of dimensionality reduction, where given high-dimensional data we want to estimate two mappings: from high to low dimension (dimensionality reduction) and f...
The problem of choosing fast implementations for a class of recursive algorithms such as the fast Fourier transforms can be formulated as an optimization problem over the language...
It is an interesting challenge to design input devices that are easy to learn and use and that allow a wide range of differentiated input. We have developed a novel joystick-like ...
Many modern visual recognition algorithms incorporate a step of spatial `pooling', where the outputs of several nearby feature detectors are combined into a local or global `...
Pictorial structure (PS) models are extensively used for part-based recognition of scenes, people, animals and multi-part objects. To achieve tractability, the structure and param...