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...
Rather recently object-oriented modeling languages, tools, and methods attract the interest of embedded (realtime) system developers. This is especially true if embedded (real-tim...
TalkMiner is a search engine for lecture webcasts. Lecture videos are processed to recover a set of distinct slide images and OCR is used to generate a list of indexable terms fro...
John Adcock, Matthew Cooper, Laurent Denoue, Hamed...
We participate in all the sub tracks of the Blog track 2007. For the Opinionated Task, we use an excerpt list of the SentiWordNet to determine the opinionated nature of returned b...
We investigate the use of recently proposed character and word sequence kernels for the task of authorship attribution and compare their performance with two probabilistic approac...