We present an integrated model for visual object localization and continuous state estimation in a discriminative structured prediction framework. While existing discriminative `p...
Abstract Three-dimensional (3D) representations of complex geometric shapes, especially when they are reconstructed from magnetic resonance imaging (MRI) and computed tomography (C...
We present an adaptive parametrization scheme for dynamic mesh refinement in the application of parametric image registration. The scheme is based on a refinement measure ensuring...
Michael Sass Hansen, Rasmus Larsen, Ben Glocker, N...
High-level, or holistic, scene understanding involves
reasoning about objects, regions, and the 3D relationships
between them. This requires a representation above the
level of ...
Many methods for object recognition, segmentation, etc., rely on tessellation of an image into "superpixels". A superpixel is an image patch which is better aligned with ...