Abstract. We describe a new method for unsupervised structure learning of a hierarchical compositional model (HCM) for deformable objects. The learning is unsupervised in the sense...
Long Zhu, Chenxi Lin, Haoda Huang, Yuanhao Chen, A...
A fundamental issue in differential motion analysis is the compromise between the flexibility of the matching criterion for image regions and the ability of recovering the motion....
We present techniques for automatically creating and animating models obtained from human whole body scanned data. A layered model is developed in which the underlying skeleton, s...
—In this paper, we propose a circular blurred shape model descriptor to deal with the problem of symbol detection and classification as a particular case of object recognition. ...
In this paper we propose a weakly supervised learning algorithm for appearance models based on the minimum description length (MDL) principle. From a set of training images or volu...
Georg Langs, Rene Donner, Philipp Peloschek, Horst...