Research at the Computer Vision Laboratory at the University of Maryland has focussed on developing algorithms and systems that can look at humans and recognize their activities i...
Larry S. Davis, Vasanth Philomin, Ramani Duraiswam...
In this paper, we propose a novel method for solving single-image super-resolution problems. Given a low-resolution image as input, we recover its highresolution counterpart using...
As the consequence of semantic gap, visual similarity does not guarantee semantic similarity, which in general is conflicting with the inherent assumption of many generativebased ...
This paper presents a new method for computing optimal L1
solutions for vision geometry problems, particularly for those
problems of fixed-dimension and of large-scale. Our strat...
This paper introduces a new formulation for discrete image labeling tasks, the Decision Tree Field (DTF), that combines and generalizes random forests and conditional random fiel...
Sebastian Nowozin, Carsten Rother, Shai Bagon, Ban...