—In this work, we address the problem of performing class-specific unsupervised object segmentation, i.e., automatic segmentation without annotated training images. Object segmen...
Many unsupervised learning algorithms make use of kernels that rely on the Euclidean distance between two samples. However, the Euclidean distance is optimal for Gaussian distribut...
Karim T. Abou-Moustafa, Mohak Shah, Fernando De la...
Adaptor grammars (Johnson et al., 2007b) are a non-parametric Bayesian extension of Probabilistic Context-Free Grammars (PCFGs) which in effect learn the probabilities of entire s...
Probabilistic grammars offer great flexibility in modeling discrete sequential data like natural language text. Their symbolic component is amenable to inspection by humans, while...
Abstract. Humans demonstrate a remarkable ability to parse complicated motion sequences into their constituent structures and motions. We investigate this problem, attempting to le...