A number of recent systems for unsupervised featurebased learning of object models take advantage of cooccurrence: broadly, they search for clusters of discriminative features tha...
This paper proposes a novel solution to the problem of pose estimation of three-dimensional objects using feature maps. Our approach relies on quaternions as the mathematical repre...
We propose a simple framework that utilizes online appearance models for 3D face and facial feature tracking with a deformable model. Adapting the geometrical parameters for each ...
This paper presents a software-based parameter-free method for the demultiplexing of a video stream [7] that is missing camera labeling information. The method is based on the obs...
Jose Luis Lisani, Lenny Rudin, Pascal Monasse, Jea...
In this paper, a new tracking algorithm, based on local minimum energy, is proposed for matching between a projected model and corresponding image features in real-time. The algor...