(DOM). With D3, designers selectively bind input data to arbitrary document elements, applying dynamic transforms to both generate and modify content. We show how representational transparency improves expressive-ness and better integrates with developer tools than prior approaches, while offering

of unlabeled images (or audio samples, or text documents) randomly downloaded from the Internet to improve performance on a given image (or audio, or text) classification task. Such unlabeled data is significantly easier to obtain than in typical semi-supervised or transfer learning settings, making selftaught

In this paper, we compare learning techniques based on statistical classification to traditional methods of relevance feedback for the document routing problem. We consider three classification techniques which have decision rules that are derived via explicit error minimization: linear

Neural networks are a powerful technology for classification of visual inputs arising from documents. However, there is a confusing plethora of different neural network methods that are used in the literature and in industry. This paper describes a set of concrete best practices that document

Joint Video Team (JVT) of ISO/IEC MPEG & ITU-T VCEG

. (JEL E24, E32) It has been well documented that the cyclical adjustment of labor input chiefly represents move-ment of workers into and out of employment, rather than adjustment of hours at given jobs. Thus, in understanding business cycles, it is cen-trally important to understand the formation

is an adaptive approach to the recognition of the hundreds of font styles and sizes that can occur on printed documents. A preclassifier is constructed during the input process and used to speed up a well-known pattern-matching method for clustering characters from an arbitrary print source into a small sample

is asserted, MEME obtains increased robustness from a method for determining motif widths automatically, and from probabilistic models that allow motifs to be absent in some input sequences. On the other hand, MEME can exploit prior knowledgeabout a motif being present in all input sequences, about the length

interesting regions and then describing their semantics. This task is expedited by a mining component that attempts to infer the grammar of the file from the information the user has input so far. Once the format of a document has been determined, its data can be extracted into a number of useful forms

, based on a notion of projection for XML, which can be used to drastically reduce memory requirements in XQuery processors. The main contribution of the paper is a static analysis technique that can identify at compile time which parts of the input document are needed to answer an arbitrary XQuery. We