In this paper, we present an approach to interpret handwritten digit strings by employing a two-stage segmentation and recognition scheme. The first stage processing is to deal wi...
Gyeonghwan Kim, Seon-Hwa Jeong, Sungwon Park, Yunh...
We present a novel framework for motion segmentation that combines the concepts of layer-based methods and feature-based motion estimation. We estimate the initial correspondences...
The automatic annotation of images presents a particularly complex problem for machine learning researchers. In this work we experiment with semantic models and multi-class learnin...
This study is a part of a global project on urban scenes interpretation using high resolution satellite images. Actually, the research is focused on buildings and roads are used to...
Nesrine Chehata, Franck Jung, Marc Pierrot Deseill...
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...