Search results

In this paper, we present a system for extracting tabular information from loosely structured handwritten documents. The system consists of three parts, (i) a u-net like CNN-based method for text detection and segmentation, (ii) a new attention-based method for simultaneous text recognition and classification of word-parts, and (iii) a method for matching the word parts into a tabular structure fo

Background and purpose: Neoadjuvant chemoradiotherapy (nCRT) is used in locally recurrent rectal cancer (LRRC) to increase chances of a radical surgical resection. Delineation in LRRC is hampered by complex disease presentation and limited clinical exposure. Within the PelvEx II trial, evaluating the benefit of chemotherapy preceding nCRT for LRRC, a delineation guideline was developed by an exper

BACKGROUND: Magnetic resonance imaging (MRI) carries prognostic importance after traumatic brain injury (TBI), especially when computed tomography (CT) fails to fully explain the level of unconsciousness. However, in critically ill patients, the risk of deterioration during transfer needs to be balanced against the benefit of detecting prognostically relevant information on MRI. We therefore aimed

In this paper we address absolute camera pose estimation. An efficient (and standard) way to solve this problem, is to use sparse keypoint correspondences. In many cases point features are not available, or are unstable over time and viewing conditions. We propose a framework based on silhouettes of quadric surfaces, with special emphasis on cylinders. We provide mathematical analysis of the probl

Social media are increasingly important tools in diplomacy. Diplomats are expected to use social media platforms such as Twitter, Facebook and Instagram to communicate with each other and with both domestic and international publics. This form of communication involves displaying positive emotions to generate attention in a competitive information environment. Emotions are essential to managing pe

Results from the application of a new seismic technique for non-destructive testing of pavement layer moduli are presented. The method is based on the multichannel analysis of surface waves (MASW) method and multichannel simulation with one receiver (MSOR). The MSOR method uses one accelerometer (receiver), a light hammer (source), and a single-channel recording device to generate a simulated mult

The honeybee gut microbiome is thought to be important for bee health, but the role of the individual members is poorly understood. Here, we present closed genomes and associated mobilomes of 102 Apilactobacillus kunkeei isolates obtained from the honey crop (foregut) of honeybees sampled from beehives in Helsingborg in the south of Sweden and from the islands Gotland and Åland in the Baltic Sea.

The article presents a semantic theory suggesting that equivalence and polyvalence are closely connected phenomena. The connection between them is utilised by making equivalence the basis of an argument for polyvalence within semantics, or in other terms, for a stratified semantics encompassing two levels of description. This argument from equivalence lends new support to frameworks assuming a str

Antinuclei found in cosmic rays could provide a smoking gun signal for dark matter as this signal is virtually background free. The study of 3He cosmic rays requires the knowledge of their production, propagation in the galaxy and annihilation cross-section. While the former two have been already estimated with data-driven methods, there were no experimental data available for the 3He inelastic cr

Several types of Galactic sources, like magnetars, microquasars, novae or pulsar wind nebulae flares, display transient emission in the X-ray band. Some of these sources have also shown emission at MeV-GeV energies. However, none of these Galactic transients have ever been detected in the very-high-energy (VHE; E>100 GeV) regime by any Imaging Air Cherenkov Telescope (IACT). The Galactic Transient

The various existing measures to quantify upper limb use from wrist-worn inertial measurement units can be grouped into three categories: 1) Thresholded activity counting, 2) Gross movement score and 3) machine learning. However, there is currently no direct comparison of all these measures on a single dataset. While machine learning is a promising approach to detecting upper limb use, there is cu

This paper investigates an integrated traffic environment modeling and model predictive control (MPC) system to realize interaction-aware dynamic motion planning of an autonomous vehicle with multiple surrounding vehicles. The interaction-aware interacting multiple model Kalman filter (IAIMM-KF) from the literature is used to hierarchically predict maneuvers and trajectories of surrounding vehicle

Classical molecular dynamics simulations are a common component of multi-modal analyses of scattering measurements, such as small-angle scattering and diffraction. Users of these experimental techniques often have no formal training in the theory and practice of molecular dynamics simulation, leading to the possibility of these simulations being treated as a `black box' analysis technique. This ar

Sulfur-doped titania thin films with cubic mesostructures were prepared by dip coating via the evaporation induced self-assembly route. The effect of sulfur doping on structure, morphology, porosity, optical properties, and photocatalytic activity of the mesoporous films was studied. Compared to undoped titania films, the S-doped films showed better long-range ordering, bigger pore size, higher po

The hierarchical pattern exploitation (HPE) method is proposed for the efficient electromagnetic analysis of finite periodic arrays. Instead of taking advantage of the Toeplitz symmetry by discretizing integral equations, HPE partitions the array hierarchically to form considerably larger geometrical repetitions, which result in identical interaction blocks inside the system matrix. These interact