Image keypoints and descriptors play a crucial role in many visual measurement tasks. In recent years, deep neural networks have been widely used to improve the performance of keypoint descriptor extraction. However, conventional convolution operations do not provide geometric invariance required for descriptor. To address this issue, we propose Sparse Deformable Descriptor Head (SDDH), which l...

One widespread procedure to render the attractor of Kleinian groups, appearing in the renown book [8], wantshuge memory resources to compute and store the results. We present a new faster and lighter version that drops the original array and pulls out group elements from integers.

This paper describes the SENSE machine translation system participation in the Third Workshop for Asian Translation (WAT2016). We share our best practices to build a fast and light phrasebased machine translation (PBMT) models that have comparable results to the baseline systems provided by the organizers. As Neural Machine Translation (NMT) overtakes PBMT as the state-of-the-art, deep learning...

Matrix-parametrized models (MPMs) are widely used in machine learning (ML) applications. In large-scale ML problems, the parameter matrix of a MPM can grow at an unexpected rate, resulting in high communication and parameter synchronization costs. To address this issue, we offer two contributions: first, we develop a computation model for a large family of MPMs, which share the following proper...

BACKGROUND We tried to explain why a marked decrease in birthweight of 122 g occurred over a 15-year period in Ribeirão Preto, Brazil. METHODS Factors reflecting biological, social, and health care characteristics (infant gender, parity, maternal age, marital status, type of hospital, maternal smoking, preterm birth, small for gestational age [SGA], and prenatal care) were assessed on 6711 ne...

We discuss the three-body decays t̃1 → W+ b χ̃1, t̃1 → H+ b χ̃1, t̃1 → b l̃ i νl, and t̃1 → b ν̃l l+ (l = e, μ, τ) of the lighter top squark t̃1 within the minimal supersymmetric standard model. We give the complete analytical formulas for the decay widths and present a numerical study in view of an upgraded Tevatron, the CERN LHC, and a future lepton collider demonstrating the importance of these decay...

The study presented in this paper concerns the development of an algorithm, based on finite element analysis, for the dynamic simulation of a tethered lighter-than-air balloon when subjected to operational conditions. The main features of the algorithm are described, highlighting the advantages of this approach when performing dynamic analysis. The input parameters considered in the method are ...