Search

Neural style transfer (NST) is a deep learning technique that produces an unprecedentedly rich style transfer from a style image to a content image. It is particularly impressive when it comes to transferring style from a painting to an image. NST was originally achieved by solving an optimization problem to match the global statistics of the style image while preserving the local geometric features of the content image. The two main drawbacks of this original approach is that it is computationally expensive and that the resolution of the output images is limited by high GPU memory requirements. Many solutions have been proposed to both accelerate NST and produce images with larger size. However, our investigation shows that these accelerated methods all compromise the quality of the produced images in the context of painting style transfer. Indeed, transferring the style of a painting is a complex task involving features at different scales, from the color palette and compositional style to the fine brushstrokes and texture of the canvas. This paper provides a solution to solve the original global optimization for ultra‐high resolution (UHR) images, enabling multiscale NST at unprecedented image sizes. This is achieved by spatially localizing the computation of each forward and backward passes through the VGG network. Extensive qualitative and quantitative comparisons, as well as a perceptual study, show that our method produces style transfer of unmatched quality for such high‐resolution painting styles. By a careful comparison, we show that state‐of‐the‐art fast methods are still prone to artifacts, thus suggesting that fast painting style transfer remains an open problem. [ABSTRACT FROM AUTHOR]

Copyright of Gazette de la Société Mathématique de France is the property of Societe Mathematique de France and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The most common reported epidemic time series in epidemiological surveillance are the daily or weekly incidence of new cases, the hospital admission count, the ICU admission count, and the death toll, which played such a prominent role in the struggle to monitor the Covid-19 pandemic. We show that pairs of such curves are related to each other by a generalized renewal equation depending on a smooth time varying delay and a smooth ratio generalizing the reproduction number. Such a functional relation is also explored for pairs of simultaneous curves measuring the same indicator in two neighboring countries. Given two such simultaneous time series, we develop, based on a signal processing approach, an efficient numerical method for computing their time varying delay and ratio curves, and we verify that its results are consistent. Indeed, they experimentally verify symmetry and transitivity requirements and we also show, using realistic simulated data, that the method faithfully recovers time delays and ratios. We discuss several real examples where the method seems to display interpretable time delays and ratios. The proposed method generalizes and unifies many recent related attempts to take advantage of the plurality of these health data across regions or countries and time, providing a better understanding of the relationship between them. An implementation of the method is publicly available at the EpiInvert CRAN package. Author summary: To monitor an epidemic, it is crucial to understand the relationship between the incidence of new cases, the hospital admission count, the ICU admission count, and the death toll time series. The relationship between any pair of such indicators can be formulated in terms of temporal delays and ratios which evolve across time. Given two such time series, we develop, based on a signal processing approach, an efficient numerical method for computing their time varying delay and ratio curves. Using realistic simulated data, we show that the method faithfully recovers time delays and ratios. In addition, we discuss several applications to real epidemic data where the method seems to output interpretable time delays and ratios. The obtained relationship between these epidemic time series is a key issue in epidemiological surveillance. The proposed technique provides a new tool to visualize, compare, and understand the evolution of key epidemiological time series. An implementation of the method is publicly available at the EpiInvert CRAN package. [ABSTRACT FROM AUTHOR]

The COVID-19 pandemy has created a radically new situation where most countries provide raw measurements of their daily incidence and disclose them in real time. This enables new machine learning forecast strategies where the prediction might no longer be based just on the past values of the current incidence curve, but could take advantage of observations in many countries. We present such a simple global machine learning procedure using all past daily incidence trend curves. Each of the 27,418 COVID-19 incidence trend curves in our database contains the values of 56 consecutive days extracted from observed incidence curves across 61 world regions and countries. Given a current incidence trend curve observed over the past four weeks, its forecast in the next four weeks is computed by matching it with the first four weeks of all samples, and ranking them by their similarity to the query curve. Then the 28 days forecast is obtained by a statistical estimation combining the values of the 28 last observed days in those similar samples. Using comparison performed by the European Covid-19 Forecast Hub with the current state of the art forecast methods, we verify that the proposed global learning method, EpiLearn, compares favorably to methods forecasting from a single past curve. Author summary: Forecasting the short time evolution of the COVID-19 daily incidence is a key issue in the epidemic decision making policy. We propose a machine learning method which forecasts the future values of the daily incidence trend based on the evolution of other incidence trend curves that were similar to the current one in the past. Using comparison performed by the European Covid-19 Forecast Hub with the current state of the art forecast methods, we verify that the proposed global learning method, EpiLearn compares favorably to methods that forecast from a single past curve. [ABSTRACT FROM AUTHOR]

The staircase effect created by neighborhood filters is explained by finding subjacent partial differential equation (PDEs) of the filters, also demonstrates a simple alternative of the filter to solve the problem and work out a subjacent stable PDE of the variant. The results show that the ill-posed PDE is a variant to another famous image processing model, the Perona-Malik equation, which suffers the same articrafts.

Wertheimer's theory suggests a general perception law according to which objects having a quality in common get perceptually grouped. The Helmholtz principle is a quantitative version of this general grouping law. It states that a grouping is perceptually "meaningful" if its number of occurrences would be very small in a random situation: Geometric structures are then characterized as large deviations from randomness. In two previous works, we have applied this principle to the detection of orientation alignments and boundaries in a digital image. In this paper, we show that the method is fully general and can be extended to a grouping by any quality. We treat as an illustration the alignments of objects, their grouping by color and by size, and the vicinity gestalt (clusters). Collaboration of the gestalt grouping laws and their pyramidal structure are illustrated in a case study. Index Terms--Gestalt grouping laws, a contrario probabilistic model, binomial law, number of false alarms, histogram modes, clusters, alignments.

Phytonutrients comprise many different chemicals, including carotenoids, indoles, glucosinolates, organosulfur compounds, phytosterols, polyphenols, and saponins. This review focuses on the human healthcare benefits of seven phytochemical families and highlights the significant potential contribution of phytonutrients in the prevention and management of pathologies and symptoms in the field of family health. The structure and function of these phytochemical families and their dietary sources are presented, along with an overview of their potential activities across different health and therapeutic targets. This evaluation has enabled complementary effects of the different families of phytonutrients in the same area of health to be recognized. [ABSTRACT FROM AUTHOR]

Simple Summary: In the past two years, the COVID-19 incidence curves and reproduction number R t have been the main metrics used by policy makers and journalists to monitor the spread of this global pandemic. However, these metrics are not always reliable in the short term, because of a combination of delay in detection, administrative delays and random noise. In this article, we present a complete model of COVID-19 incidence, faithfully reconstructing the incidence curve and reproduction number from the renewal equation of the disease and precisely estimating the biases associated with periodic weekly bias, festive day bias and residual noise. The sanitary crisis of the past two years has focused the public's attention on quantitative indicators of the spread of the COVID-19 pandemic. The daily reproduction number R t , defined by the average number of new infections caused by a single infected individual at time t, is one of the best metrics for estimating the epidemic trend. In this paper, we provide a complete observation model for sampled epidemiological incidence signals obtained through periodic administrative measurements. The model is governed by the classic renewal equation using an empirical reproduction kernel, and subject to two perturbations: a time-varying gain with a weekly period and a white observation noise. We estimate this noise model and its parameters by extending a variational inversion of the model recovering its main driving variable R t . Using R t , a restored incidence curve, corrected of the weekly and festive day bias, can be deduced through the renewal equation. We verify experimentally on many countries that, once the weekly and festive days bias have been corrected, the difference between the incidence curve and its expected value is well approximated by an exponential distributed white noise multiplied by a power of the magnitude of the restored incidence curve. [ABSTRACT FROM AUTHOR]

The problem of computing a local orientation map in a digital image is investigated.

Possible algorithms for interpolating scalar data given on a set of curves or points in the plane are presented. The model is based on the concept of 'raw primal sketch' and is assumed to consist mainly of areas of smooth or constantly varying intensity separated by discontinuities symbolized by strong edges. Waveform coding techniques such as pyramidal or transform coding are used to separately code residual texture information at higher bit rates.

Weathering steels are structural steels mainly used in civil engineering structures like bridges, building and in some electrical network structures. These steels that are slightly alloyed with copper and chromium have the advantage of not requiring a protective coating because of their good atmospheric corrosion resistance compared to conventional steels. This protection prevents repainting of structures which is the main maintenance operation of them with large drawbacks from a sustainable development point of view (economy, ecological, social). Besides a lack of understanding of how the distribution of chemical alloying elements act to reduce the corrosion rate, an important limit of their use remains in the ability to predict their corrosion behavior in a coupled environment/steel grade context. Furthermore, the two main atmospheric pollutants known to have a major influence on corrosion of structural steels are SO2 and chlorides. In recent decades, SO2 levels have drastically decreased in the atmosphere. During this same period the sulfur content in steels, which is the most harmful chemical element from the point of view of atmospheric corrosion, decreased sharply. The evolution of these both parameters could have an influence on the prediction models for the long‐term durability of steels. We are carrying out an experimental campaing aiming to characterize and model formation of patinas on different grades of steels exposed on several atmopsheric sites. Exposure times range from short term (a few weeks to several years on 6 different grades in 6 sites of different environments) to long term (samples taken from structures erected since few decades). These different samples were characterized according to a multi‐scale approach by metallographic techniques (macros‐copy, microscopy and fractography) and, microstructural (Raman and XRD), electrochemical and gravimetric techniques. The results after 1 year of exposure show very close corrosion rates whatever the non‐marine environments considered and there are no significant differences between the different grades of steel. From the point of view of their structures, the patinas present a double‐layer appearance, including for conventional steels. [ABSTRACT FROM AUTHOR]