In this paper, we propose a prior for hand pose estimation that integrates the direct relation between a manipulating hand and a 3d object. This is of particular interest for a va...
How can knowing about some categories help us to discover new ones in unlabeled images? Unsupervised visual category discovery is useful to mine for recurring objects without huma...
We present a method which enables rapid and dense reconstruction of scenes browsed by a single live camera. We take point-based real-time structure from motion (SFM) as our starti...
Pictorial structure (PS) models are extensively used for part-based recognition of scenes, people, animals and multi-part objects. To achieve tractability, the structure and param...
StitchRV is a fiducial and touch-tracking engine based on the popular reacTIVision fiducial tracking system. StitchRV combines video input from multiple cameras in real time, and ...