Tomas Wilkinson

Learn More
This paper has described the DIVA system, an architecture incorporating PIM devices as smart memories to one or more external host processors. Other distinguishing features of DIVA include its PIM-to-PIM interconnect and explicit support for in-memory operations on irregular data structures. In this paper, we presented system level requirements for(More)
We describe an operating system design for multiprocessor systems called Angel, based on a single, coherent, uniform virtual address space. This unies naming and interprocess communication in both shared and distributed memory multiprocessors by using distributed shared memory techniques when shared memory is not already provided by the hardware. The design(More)
—Deep learning has thus far not been used for dating of pre-modern handwritten documents. In this paper, we propose ways of using deep convolutional neural networks (CNNs) to estimate production dates for such manuscripts. In our approach, a CNN can either be used directly for estimating the production date or as a feature learning framework for other(More)
—In the last few years, deep convolutional neural networks have become ubiquitous in computer vision, achieving state-of-the-art results on problems like object detection, semantic segmentation, and image captioning. However, they have not yet been widely investigated in the document analysis community. In this paper, we present a word spotting system based(More)
—In this paper, we introduce image-based word clouds as a novel tool for a quick and aesthetic overviews of common words in collections of digitized text manuscripts. While OCR can be used to enable summaries and search functionality to printed modern text, historical and handwritten documents remains a challenge. By segmenting and counting word images,(More)
  • 1