Research performed in the field of computer vision has steadily ignored recent advances in programming tools and techniques, relying on well-established traditional methods, such ...
We have designed and tested a single-chip analog VLSI sensor that detects imminent collisions by measuring radially expansive optic flow. The design of the chip is based on a mode...
Sample selection bias is a common problem in many real world applications, where training data are obtained under realistic constraints that make them follow a different distribut...
We present an approach to low-level vision that combines two main ideas: the use of convolutional networks as an image processing architecture and an unsupervised learning procedu...
We describe a technique for comparing distributions without the need for density estimation as an intermediate step. Our approach relies on mapping the distributions into a reprodu...
Alexander J. Smola, Arthur Gretton, Le Song, Bernh...