I am lucky enough to be this year’s Program Chair of KONVENS 2012, the 11th Conference on Natural Language Processing. The history of KONVENS goes back to 1992, and it is held in a two-year rotation, organized by
- the Austrian Society for Artificial Intelligence (ÖGAI),
- the German Society for Language Technology and Computational Linguistic (GSCL), and
- the German Society for Linguistics, Section Computational Linguistics (DGfS-CL).
KONVENS 2012 will be held from September 19-21, 2012 in Vienna and I strongly encourage everyone with an interest in natural language processing to visit the conference. This year, we have a very strong technical program, including
Please visit the conference website for further details. I should also add that the adjacent weekend is a great opportunity to extend your stay and get to know the city.
I am looking forward to seeing you in Vienna!
J. Jancsary, S. Nowozin and C. Rother
After a decade of rapid progress in image denoising, recent methods seem to have reached a performance limit. Nonetheless, we find that state-of-the-art denoising methods are visually clearly distinguishable and possess complementary strengths and failure modes. Motivated by this observation, we introduce a powerful non-parametric image restoration framework based on Regression Tree Fields (RTF). Our restoration model is a densely-connected tractable conditional random field that leverages existing methods to produce an image-dependent, globally consistent prediction. We estimate the conditional structure and parameters of our model from training data so as to directly optimize for popular performance measures. In terms of peak signal-to-noise-ratio (PSNR), our model improves on the best published denoising method by at least 0.26dB across a range of noise levels. Our most practical variant still yields statistically significant improvements, yet is over 20x faster than the strongest competitor. Our approach is well-suited for many more image restoration and low-level vision problems, as evidenced by substantial gains in tasks such as removal of JPEG blocking artefacts.