We propose a region-based method to extract semantic foreground regions from color video sequences with static backgrounds. First, we introduce a new distance measure for backgrou...
We develop nonparametric Bayesian models for multiscale representations of images depicting natural scene categories. Individual features or wavelet coefficients are marginally de...
Jyri J. Kivinen, Erik B. Sudderth, Michael I. Jord...
Recognition of object categories from their images is extremely challenging due to the large intra-class variations, and variations in pose, illumination and scale, in addition to...
Dynamic programming on a scanline is one of the oldest and still popular methods for stereo correspondence. While efficient, its performance is far from the state of the art becau...
We introduce a new texture representation that combines standard sampling, to be bilinearly interpolated in smoothly varying regions, with customizable discontinuities, to model s...