The problem of human activity recognition via visual stimuli can be approached using manifold learning, since the silhouette (binary) images of a person undergoing a smooth motion...
Tat-Jun Chin, Liang Wang, Konrad Schindler, David ...
Intrinsic curvature flows can be used to design Riemannian metrics by prescribed curvatures. This chapter presents three discrete curvature flow methods that are recently introduce...
Xiaotian Yin, Miao Jin, Feng Luo 0002, Xianfeng Da...
Manifold learning can discover the structure of high dimensional data and provides understanding of multidimensional patterns by preserving the local geometric characteristics. Ho...
We apply the concept of natural gradients to deformable registration. The motivation stems from the lack of physical interpretation for gradients of image-based difference measure...
We present a generalization of thin-plate splines for interpolation and approximation of manifold-valued data, and demonstrate its usefulness in computer graphics with several app...
Florian Steinke, Matthias Hein, Jan Peters, Bernha...