Subspace learning techniques are widespread in pattern recognition research. They include PCA, ICA, LPP, etc. These techniques are generally linear and unsupervised. The problem o...
Annotating paper documents with a pen is a familiar and indispensable activity across a wide variety of work and educational settings. Recent developments in pen-based computing p...
We present a novel image classification technique for detecting multiple objects (called subobjects) in a single image. In addition to image classifiers, we apply spatial relati...
The objective of this paper is to parse object trajectories in surveillance video against occlusion, interruption, and background clutter. We present a spatio-temporal graph (ST-G...
Image retargeting is the problem of adapting images for display on devices different than originally intended. This paper presents a method for adapting large images, such as thos...