Most of the existing 3D engines are overwhelmingly complex and do not integrate support for virtual characters. We have developed a teaching oriented 3D engine with support for su...
We present an algorithm for jointly learning a consistent bidirectional generative-recognition model that combines top-down and bottom-up processing for monocular 3d human motion ...
Cristian Sminchisescu, Atul Kanaujia, Dimitris N. ...
We propose an Isometric Self-Organizing Map (ISOSOM) method for nonlinear dimensionality reduction, which integrates a Self-Organizing Map model and an ISOMAP dimension reduction ...
We describe a part-based object-recognition framework, specialized to mining complex 3D objects from detailed 3D images. Objects are modeled as a collection of parts together with...
In this paper, temporal segmentation of 3D video based on motion analysis is presented. 3D video is a sequence of 3D models made for a real-world dynamic object. A modified shape ...