We consider the problem of learning classifiers in structured domains, where some objects have a subset of features that are inherently absent due to complex relationships between...
Gal Chechik, Geremy Heitz, Gal Elidan, Pieter Abbe...
In this paper, we propose a tone mapping operator based on a multiscale representation pattern and on thresholds of detection contrast computed for local adaptation luminances. Th...
See a PPT file with videos at www.research.microsoft.com/users/jojic/FlexiblesSprites.htm We propose a technique for automatically learning layers of "flexible sprites" ...
In this paper we perform 3D face tracking on corrupted video sequences. We use a deformable model, combined with a predictive filter, to recover both the rigid transformations and...
Siome Goldenstein, Christian Vogler, Dimitris N. M...
Abstract. Volume datasets have been a primary representation for scientific visualization with the advent of rendering algorithms such as marching cubes and ray casting. Nonethele...