Abstract--In this paper we introduce a probabilistic approach of building extraction in remotely sensed images. To cope with data heterogeneity we construct a flexible hierarchical...
We introduce a new concept of co-recognition for object-level image matching between an arbitrary image pair. Our method augments putative local regionmatches to reliable object-...
Minsu Cho (Seoul National University), Young Min S...
Dynamic textures (DT) are videos of non-rigid dynamical objects, such as fire and waves, which constantly change their shape and appearance over time. Most of the prior work on DT ...
We introduce Hidden Process Models (HPMs), a class of probabilistic models for multivariate time series data. The design of HPMs has been motivated by the challenges of modeling h...
Rebecca Hutchinson, Tom M. Mitchell, Indrayana Rus...
We present a unified framework for separating specular and diffuse reflection components in images and videos of textured scenes. This can be used for specularity removal and for i...
Satya P. Mallick, Todd Zickler, Peter N. Belhumeur...