High-level generative models provide elegant descriptions of videos and are commonly used as the inference framework in many unsupervised motion segmentation schemes. However, app...
In this study we propose an integrated approach to the problem of 3D pose estimation. The main difference to the majority of known methods is the usage of complementary image info...
We present a robust, noise-resistant criterion characterizing planelike skeletons in binary voxel objects. It is based on a distance map and the geodesic distance along the object...
We present a multispectral photometric stereo method for capturing geometry of deforming surfaces. A novel photometric calibration technique allows calibration of scenes containin...
In this paper, we present a novel approach for human activities recognition in the video. We analyze human activities in the sequential frames because human activities can be cons...