Graph matching techniques are widely used in pattern recognition problems such as scene description, finger print identification, or face recognition. In this paper, we put forwar...
We extend the "Sparse LDA" algorithm of [7] with new sparsity bounds on 2-class separability and efficient partitioned matrix inverse techniques leading to 1000-fold spe...
We present the first method to compute depth cues from images taken solely under uncalibrated near point lighting. A stationary scene is illuminated by a point source that is move...
We formulate multi-view 3D shape reconstruction as the computation of a minimum cut on the dual graph of a semiregular, multi-resolution, tetrahedral mesh. Our method does not ass...
Sudipta N. Sinha, Philippos Mordohai, Marc Pollefe...
Numerous applications processing 3D point data will gain from the ability to estimate reliably normals and differential geometric properties. Normal estimates are notoriously nois...
Local spatiotemporal features or interest points provide compact but descriptive representations for efficient video analysis and motion recognition. Current local feature extract...
The paper deals with grouping of edges to contours of shapes using only local symmetry and continuity. Shape skeletons are used to generate the search space for a version of the M...
In this paper we study face recognition across ages within a real passport photo verification task. First, we propose using the gradient orientation pyramid for this task. Discard...
In this paper, we describe a method for segmenting fiber bundles from diffusion-weighted magnetic resonance images using a locally-constrained region based approach. From a pre-co...
John Melonakos, Marc Niethammer, Vandana Mohan, Ma...