Most pose robust face verification algorithms, which employ 2D appearance, rely heavily on statistics gathered from offline databases containing ample facial appearance variation ...
A good distance metric is crucial for unsupervised learning from high-dimensional data. To learn a metric without any constraint or class label information, most unsupervised metr...
This paper presents a new methodology for evaluating the quality of motion estimation and stereo correspondence algorithms. Motivated by applications such as novel view generation...
Abstract. Traditional stereo algorithms implicitly use the frontal parallel plane assumption when exploiting contextual information, since the smoothness prior biases towards const...
While symmetry reduction has been established to be an important technique for reducing the search space in model checking, its application in concurrent software verification is ...