We address the problem of multiclass object detection. Our aims are to enable models for new categories to benefit from the detectors built previously for other categories, and fo...
The goal of text categorization is to classify documents into a certain number of pre-defined categories. The previous works in this area have used a large number of labeled train...
We investigate the problem of learning action effects in partially observable STRIPS planning domains. Our approach is based on a voted kernel perceptron learning model, where act...
See a PPT file with videos at www.research.microsoft.com/users/jojic/FlexiblesSprites.htm We propose a technique for automatically learning layers of "flexible sprites" ...
Inverse halftoning is the process to retrieve a (gray) continuous-tone image from a halftone. Recently, machinelearning-based inverse halftoning techniques have been proposed. Dec...