We propose a new method for human action recognition from video sequences using latent topic models. Video sequences are represented by a novel “bag-of-words” representation, w...
Modeling the performance behavior of parallel applications to predict the execution times of the applications for larger problem sizes and number of processors has been an active ...
The goal of automatic image annotation is to automatically generate annotations for images to describe their content. In the past, statistical machine translation models have been...
Abstract. We propose a generative approach to the problem of labeling images containing configurations of objects from multiple classes. The main building blocks are dense statisti...
We consider the problem of compressing graphs of the link structure of the World Wide Web. We provide efficient algorithms for such compression that are motivated by recently prop...