In this paper we propose a method for matching articulated shapes represented as large sets of 3D points by aligning the corresponding embedded clouds generated by locally linear ...
Diana Mateus, Fabio Cuzzolin, Radu Horaud, Edmond ...
In this paper we present a new method for categorizing
video sequences capturing different scene classes. This can
be seen as a generalization of previous work on scene classific...
Paritosh Gupta, Sai Sankalp Arrabolu, Mathew Brown...
Abstract. Motion capture, a currently active research area, needs estimation of the pose of the subject. This requires a match between a model and the 3D shape, constructed using a...
Recently, Dementhon 0 Davis [2] proposed a method for determining the pose of a 3-0 object with respect to a camera from 3-D to 2-0 point correspondences. The method consists of i...
This paper describes a non-intrusive method to estimate the gaze direction of a person by using stereo cameras. First, facial features are tracked with an adapted particle filter...