A growing body of research is investigating the use of tabletop displays, in particular to support collaborative work. People often interact directly with these displays, typicall...
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...
We present a novel approach to controlling a virtual 3D camera with a 2D mouse or stylus input device that is based on gestural interaction. Our approach to 3D camera manipulation...
In this paper, we present a system to detect passenger cars in aerial images where car appears small. We post the detection as a 3D object recognition problem to account for the v...
1 We propose a novel video-based rendering algorithm with a single moving camera. We reconstruct a dynamic 3D model of the scene with a feature point set that "evolves" o...