Abstract. In this paper, we address the problem of computing a canonical representation of an n-dimensional combinatorial map. To do so, we define two combinatorial map signatures...
Multiple Instance Learning (MIL) provides a framework for training a discriminative classifier from data with ambiguous labels. This framework is well suited for the task of learni...
Carolina Galleguillos, Boris Babenko, Andrew Rabin...
Blendshapes (linear shape interpolation models) are perhaps the most commonly employed technique in facial animation practice. A major problem in creating blendshape animation is ...
John P. Lewis, Jonathan Mooser, Zhigang Deng, Ulri...
* This paper presents a new, classification-based spatial error concealment algorithm for images. The proposed scheme takes advantage of two state-of-the-art concealment schemes an...
In context photography, sensors gather real-time context information, which visually affects a photograph as it is taken. We have implemented a prototype running on standard camer...