Robust semantic labeling of image regions is a basic problem in representing and retrieving image/video content. We propose an SVM-MRF framework to model features and their spatia...
Automatic image tagging is important yet challenging due to the semantic gap and the lack of learning examples to model a tag’s visual diversity. Meanwhile, social user tagging ...
For handwritten character recognition, a new elastic image matching (EM) technique based on a class-dependent deformation model is proposed. In the deformation model, any deformat...
Summarizing the contents of a video containing human activities is an important problem in computer vision and has important applications in automated surveillance systems. Summar...
We present a face recognition system able to identify people from a single non-frontal image in an arbitrary pose. The key component of the system is a novel pose correction techni...
Jean-Yves Guillemaut, Josef Kittler, Mohammad Sade...