We present a Dynamic Data Driven Application System (DDDAS) to track 2D shapes across large pose variations by learning non-linear shape manifold as overlapping, piecewise linear s...
We present in this paper a novel approach for shape description based on kernel principal component analysis (KPCA). The strength of this method resides in the similarity (rotatio...
An active contour model for parametric curve and surface approximation is presented. The active curve or surface adapts to the model shape to be approximated in an optimization al...
Helmut Pottmann, Stefan Leopoldseder, Michael Hofe...
Abstract. In this work, we find meaningful parameterizations of cortical surfaces utilizing prior anatomical information in the form of anatomical landmarks (sulci curves) on the s...
Lok Ming Lui, Sheshadri Thiruvenkadam, Yalin Wan...
Abstract. We propose a novel method for action detection based on a new action descriptor called a shape flow that represents both the shape and movement of an object in a holistic...