In this paper we examine the effect of receptive field designs on classification accuracy in the commonly adopted pipeline of image classification. While existing algorithms us...
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
This paper proposes contour-based features for articulated pose estimation. Most of recent methods are designed using tree-structured models with appearance evaluation only within...
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...