Case-based problem-solving systems rely on similarity assessment to select stored cases whose solutions are easily adaptable to t current problems. However, widely-used similarity...
Exponentially growing photo collections motivate the needs for automatic image annotation for effective manipulations (e.g., search, browsing). Most of the prior works rely on sup...
This paper presents a method for improving any object tracking algorithm based on machine learning. During the training phase, important trajectory features are extracted which are...
We develop a new component analysis framework, the Noisy-Or Component Analyzer (NOCA), that targets high-dimensional binary data. NOCA is a probabilistic latent variable model tha...
Typographic and visual information is an integral part of textual documents. Most information extraction systems ignore most of this visual information, processing the text as a l...