Scene labeling research has mostly focused on outdoor scenes, leaving the harder case of indoor scenes poorly understood. Microsoft Kinect dramatically changed the landscape, show...
Active learning aims to reduce the amount of labels required for classification. The main difficulty is to find a good trade-off between exploration and exploitation of the lab...
Modeling representations of image patches that are quasi-invariant to spatial deformations is an important problem in computer vision. In this paper, we propose a novel concept, t...
Jan Ernst, Maneesh Kumar Singh, Visvanathan Ramesh
Consumer digital cameras use tone-mapping to produce compact, narrow-gamut images that are nonetheless visually pleasing. In doing so, they discard or distort substantial radiomet...
Ying Xiong, Kate Saenko, Trevor Darrell, Todd Zick...
Programming with dependent types is a blessing and a curse. It is a blessing to be able to bake invariants into the definition of datatypes: we can finally write correct-by-cons...