Research Publications
All 2009 | |
| Narrow your search | 713 result(s) |
By Type
By Year By Research Group
| Large-margin structured estimation methods work by minimizing a convex upper bound of loss functions. While they allow for efficient optimization algorithms, these convex formulations are not tight and sacrifice the ability to accurately model the true... Tree walking transducers are an expressive formalism for reasoning about XSLT-like document transformations. One of the useful properties of tree transducers is decidability of type checking: given a transducer and input and output types, it can be ... Images captured in foggy weather conditions exhibit losses in quality which are dependent on distance. If the depth and atmospheric conditions are known, one can enhance the images (to some degree) by compensating for the effects of the fog. Recently, ... Approximate solutions to labelling problems can be found using binary graph cuts and the alpha-beta swap algorithm. In some specific cases, an exact solution can be computed by constructing a multilabel graph. However, in many practical applications ... This paper presents a novel discriminative approach for pave-ment scene understanding and obstacle detection in real-world images. It overcomes the heavy constraints in previous systems such as a simple background, a speci c obstacle, etc. The approach ... Large displays are now more widely used than ever before, yet the computer mouse remains the most common input tool for large displays users. The main drawback of the mouse is that it is only a tool for mapping hand movements to on-screen cursor movements... It is typically thought that the interaction between transcription factor (TF) and DNA is mediated by the ability of the TF to recognise a canonical DNA sequence, and the chromatin structure that renders the DNA accessible to the TF. As the DNA ... Humans frequently produce emergent properties or associates when com- bining concepts in new ways. This presentation will examine the manner in which concept combination can generate emergent properties suggest- ing that the process is abductive in ... Many applications in the field of scientific computing - such as computational biology, computational linguistics, and others - depend on Machine Learning algorithms to provide important core functionality to support solutions in the particular ... Systemic Lupus Erythematosus (SLE) is a complex autoimmune disease that has heterogeneous clinical manifestation with diverse patterns of organ involvement, autoantibody profiles and varying degrees of severity of disease. Research and clinical ... This paper investigates combining opportunistic routing techniques with multipath routing for achieving reliability and timeliness in fast-changing network conditions. We present two approaches, WIMOP and DOMR, based on source routing and distributed ... There is growing interest in applying agile practices in Global Software Development (GSD) projects. But project stakeholder distribution in GSD creates a number of challenges that make it difficult to use some agile practices. Moreover, little is known ... This paper explores the use of machine learning techniques to restore punctuation and case in English text, as part of which it investigates the co-dependence of case information and punctuation. We achieve an overall F-score of .619 for the task using a ... |