This paper proposes a novel approach to motion capture
from multiple, synchronized video streams, specifically
aimed at recording dense and accurate models of the structure
and ...
Yasutaka Furukawa (University of Washington), Jean...
We present a novel approach, clustering on local image profiles, for statistically characterizing image intensity in object boundary regions. In deformable model segmentation, a d...
Joshua Stough, Stephen M. Pizer, Edward L. Chaney,...
This paper describes the implementation of a demo that will be shown at the conference site. The demo of “softfinger grasping of physically based quasi-rigid objects” will pr...
Maurizio de Pascale, Gabriele Sarcuni, Domenico Pr...
Abstract. We propose a novel model-based approach to activity recognition using high-level primitives that are derived from a human body model estimated from sensor data. Using sho...
Although human action recognition has been the subject of much research in the past, the issue of viewpoint invariance has received scarce attention. In this paper, we present an ...