This paper presents a calibration-free line-based tracking method to augment virtual objects into a video sequence. The presented method uses a cube on the first image to calibrat...
Our goal is to circumvent one of the roadblocks to using existing approaches for single-view recognition for achieving multi-view recognition, namely, the need for sufficient trai...
In this paper we present a framework for semantic scene parsing and object recognition based on dense depth maps. Five viewindependent 3D features that vary with object class are e...
We consider the problem of grasping novel objects, specifically ones that are being seen for the first time through vision. Grasping a previously unknown object, one for which a 3...
3D human pose recovery is considered as a fundamental step in view-invariant human action recognition. However, inferring 3D poses from a single view usually is slow due to the la...