The maximum flow algorithm for minimizing energy functions of binary variables has become a standard tool in computer vision. In many cases, unary costs of the energy depend linea...
Tree-structured probabilistic models admit simple, fast inference. However, they are not well suited to phenomena such as occlusion, where multiple components of an object may dis...
Abstract. We formulate a robust method using Expectation Maximization (EM) to address the problem of dense photometric stereo. Previous approaches using Markov Random Fields (MRF) ...
Linear techniques are widely used to reduce the dimension of image representation spaces in applications such as image indexing and object recognition. Optimal Component Analysis ...
Yiming Wu, Xiuwen Liu, Washington Mio, Kyle A. Gal...
In this work we present a new string similarity feature, the sparse spatial sample (SSS). An SSS is a set of short substrings at specific spatial displacements contained in the or...