In this paper, we present a novel approach for human action recognition with histograms of 3D joint locations (HOJ3D) as a compact representation of postures. We extract the 3D sk...
Gaze-contingent variable resolution display techniques allocate computational resources for image generation preferentially to the area around the center of gaze where visual sens...
Derrick Parkhurst, Eugenio Culurciello, Ernst Nieb...
Spatial awareness is crucial for human performance efficiency of any task that entails perception of space. Memory of spaces is an imperfect reflection of the cognitive activity (...
This paper addresses the problem of camera selfcalibration, bundle adjustment and 3D reconstruction from line segments in two images of poorly-textured indoor scenes. First, we ge...
Herbert Bay, Andreas Ess, Alexander Neubeck, Luc J...
In this work we propose a method for the polygonization of octree-based reconstructions by dual contouring. Dual contouring is an adaptive method for determining contiguous polygo...
Anselmo Antunes Montenegro, Luiz Velho, Paulo Ceza...