We present an approach to teach incrementally human gestures to a humanoid robot. The learning process consists of first projecting the movement data in a latent space and encodin...
In this paper, we want to exploit the knowledge obtained from those detected objects which are incorporated into the background model since they cease their movement. These motionl...
Ivan Huerta Casado, Daniel Rowe, Jordi Gonzà...
Modeling and describing temporal structure in multimedia signals, which are captured simultaneously by multiple sensors, is important for realizing human machine interaction and mo...
We address the problem of classifying scenes from feature films into semantic categories and propose a robust framework for this problem. We propose that the Finite State Machines ...
Abstract. We present a method for mining frequently occurring objects and scenes from videos. Object candidates are detected by finding recurring spatial arrangements of affine cov...