We propose a novel MRF-based model for deformable image matching (also known as registration). The deformation is described by a field of discrete variables, representing displace...
Abstract. We present the newly developed core concept for the Multidimensional Knapsack Problem (MKP) which is an extension of the classical concept for the one-dimensional case. T...
We propose a novel scheme to detect human actions in active video. Active videos such as movies or sports broadcasting are taken purposively by “clever” photographers. They ar...
Mining discrete patterns in binary data is important for subsampling, compression, and clustering. We consider rankone binary matrix approximations that identify the dominant patt...
Traditional feature selection methods assume that the data are independent and identically distributed (i.i.d.). In real world, tremendous amounts of data are distributed in a net...