We present an unsupervised algorithm for aligning a pair of shapes in the presence of significant articulated motion and missing data, while assuming no knowledge of a template, u...
We present a new approach to model visual scenes in image collections, based on local invariant features and probabilistic latent space models. Our formulation provides answers to...
Pedro Quelhas, Florent Monay, Jean-Marc Odobez, Da...
Abstract—Vision-based prop-free pointing detection is challenging both from an algorithmic and a systems standpoint. From a computer vision perspective, accurately determining wh...
Pyry Matikainen, Padmanabhan Pillai, Lily B. Mumme...
This paper presents an automatic algorithm which reconstructs building models from airborne LiDAR (light detection and ranging) data of urban areas. While our algorithm inherits t...
MIME (Mime Is Manual Expression) is a computationally efficient computer vision system for recognizing hand gestures. The system is intended to replace the mouse interface on a st...