As standard volume rendering is based on an integral in physical space (or “coordinate space”), it is inherently dependent on the scaling of this space. Although this dependen...
Background modeling plays an important role in video surveillance, yet in complex scenes it is still a challenging problem. Among many difficulties, problems caused by illuminatio...
We investigate a method for learning object categories in a weakly supervised manner. Given a set of images known to contain the target category from a similar viewpoint, learning...
This paper addresses the problem of content-based synchronization for robust watermarking. Synchronization is a process of extracting the location to embed and detect the signature...
Hae-Yeoun Lee, Jong-Tae Kim, Heung-Kyu Lee, Young-...
Current feature-based object recognition methods use information derived from local image patches. For robustness, features are engineered for invariance to various transformation...