In this work we address the problem of modeling varying time duration sequences for large-scale human routine discovery from cellphone sensor data using a multi-level approach to p...
Color is of interest to those working in computer vision largely because it is assumed to be helpful for recognition. This assumption has driven much work in color based image ind...
In our previous work we presented a new 2D-3D mixed face recognition scheme called Partial Principal Component Analysis (P2 CA) [1]. The main contribution of P2 CA is that it uses...
This paper extends our previous work on feature transformationbased support vector machines for speaker recognition by proposing a joint MAP adaptation of feature transformation (...
The automatic analysis of social interactions is attracting significant interest in the multimedia community. This work addresses one of the most important aspects of the problem...
Sarah Favre, Alfred Dielmann, Alessandro Vinciarel...