- Full text PDF available (7)
Data Set Used
The OCRopus system is an open source OCR system developed for book capture and digital library applications. It is designed to be a multilingual system in which all components are easily pluggable and replaceable. In this paper, I describe recent progress, on-going work, and preliminary results in the development of the OCRopus system, including the new… (More)
State-of-the-art results of semantic segmentation are established by Fully Convolutional neural Networks (FCNs). FCNs rely on cascaded convolutional and pooling layers to gradually enlarge the receptive fields of neurons, resulting in an indirect way of modeling the distant con-textual dependence. In this work, we advocate the use of spatially recurrent… (More)
Gesture typing is an efficient input method for phones and tablets using continuous traces created by a pointed object (e.g., finger or stylus). Translating such continuous gestures into textual input is a challenging task as gesture inputs exhibit many features found in speech and handwriting such as high variability, co-articulation and elision. In this… (More)
Most of the existing image-to-image translation frameworks—mapping an image in one domain to a corresponding image in another—are based on supervised learning, i.e., pairs of corresponding images in two domains are required for learning the translation function. This largely limits their applications, because capturing corresponding images in two different… (More)
Transliteration is a key component of machine translation systems and software internation-alization. This paper demonstrates that neural sequence-to-sequence models obtain state of the art or close to state of the art results on existing datasets. In an effort to make machine transliteration accessible, we open source a new Arabic to English… (More)
Estimation of the probability of finite percolation in porous microstructures from tomographic images, Int.