We combine detection and tracking techniques to achieve robust 3?D motion recovery of people seen from arbitrary viewpoints by a single and potentially moving camera. We rely on d...
Andrea Fossati, Miodrag Dimitrijevic, Vincent Lepe...
This paper presents a learning-based method for combining the shape and appearance feature types for 3D human pose estimation from single-view images. Our method is based on clust...
In this paper, we propose a novel technique for video shot segmentation and classification based on the Singular Value Decomposition (SVD). For the input video sequence, we create...
Abstract. This paper presents a novel approach to the problem of determining head pose estimation and face 3D orientation of several people in low resolution sequences from multipl...
Cristian Canton-Ferrer, Josep R. Casas, Montse Par...
The IRIS Network of Excellence (NoE) started its work in January 2009. In this paper we highlight some new research directions developing within the network: one is revisiting narr...