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...
We present a novel approach to estimating depth from single omnidirectional camera images by learning the relationship between visual features and range measurements available dur...
Pairwise constraints specify whether or not two samples should be in one cluster. Although it has been successful to incorporate them into traditional clustering methods, such as ...
In this paper we present a visual education tool for efficient and effective learning. The toolkit is based on a simple premise: simple concepts should be learned before advanced ...
We propose an unsupervised, probabilistic method for learning visual feature hierarchies. Starting from local, low-level features computed at interest point locations, the method c...