We introduce novel discriminative learning algorithms for dynamical systems. Models such as Conditional Random Fields or Maximum Entropy Markov Models outperform the generative Hi...
This paper describes a user interface for video chat that is capable of panning, tilting, and zooming (PTZ) operation using head tracking. The approach is to map a captured 3D pos...
Kota Yamaguchi, Takashi Komuro, Masatoshi Ishikawa
Abstract— Fire brigades and special agencies are often demanded to operate for search and aid of human lives in extremely dangerous scenarios. It is very important to first veri...
We present a method to simultaneously estimate 3d body pose and action categories from monocular video sequences. Our approach learns a lowdimensional embedding of the pose manifol...
Tobias Jaeggli, Esther Koller-Meier, Luc J. Van Go...