Structure and Intensity Unbiased Translation for 2D Medical Image Segmentation.

Data distribution gaps often pose significant challenges to the use of deep segmentation models. However, retraining models for each distribution is expensive and time-consuming. In clinical contexts, device-embedded algorithms and networks, typically unretrainable and unaccessable post-manufacture, exacerbate this issue.

Weakly-Supervised RGBD Video Object Segmentation.

Depth information opens up new opportunities for video object segmentation (VOS) to be more accurate and robust in complex scenes. However, the RGBD VOS task is largely unexplored due to the expensive collection of RGBD data and time-consuming annotation of segmentation. In this work, we first introduce a new benchmark for RGBD VOS, named DepthVOS, which contains 350 videos (over 55k frames in total) annotated with masks and bounding boxes.

Characterization, Sensory and Oxidative Stability Analysis of Vegetable Mayonnaise Formulated with Olive Leaf Vinegar as an Active Ingredient.

Development of novel food products represents a basic meeting point for health and business requirements. Mayonnaise sauce is well-suited to be a healthy and tasty dressing. In this study, mayonnaise was formulated by using unconventional ingredients, such as olive leaf vinegar (OLV), soybean/high oleic sunflower oil blend, and soymilk (as an egg substitute).

FlexHDR: Modeling Alignment and Exposure Uncertainties for Flexible HDR Imaging.

High dynamic range (HDR) imaging is of fundamental importance in modern digital photography pipelines and used to produce a high-quality photograph with well exposed regions despite varying illumination across the image. This is typically achieved by merging multiple low dynamic range (LDR) images taken at different exposures. However, over-exposed regions and misalignment errors due to poorly compensated motion result in artefacts such as ghosting.

Deep neural networks and image classification in biological vision.

In this paper we consider recent advances in the use of deep convolutional neural networks to understanding biological vision. We focus on claims about the plausibility of feedforward deep convolutional neural networks (fDCNNs) as models of image classification in the biological system. Despite the putative similarity of these networks to some properties of the biological vision system, and the remarkable levels of performance accuracy of some fDCNNs, we argue that their plausibility as a framework for understanding image classification remains unclear.

Diagnosing and Preventing Instabilities in Recurrent Video Processing.

Recurrent models are a popular choice for video enhancement tasks such as video denoising or super-resolution. In this work, we focus on their stability as dynamical systems and show that they tend to fail catastrophically at inference time on long video sequences. To address this issue, we (1) introduce a diagnostic tool which produces input sequences optimized to trigger instabilities and that can be interpreted as visualizations of temporal receptive fields, and (2) propose two approaches to enforce the stability of a model during training: constraining the spectral norm or constraining the stable rank of its convolutional layers.

Progress in Colloid Delivery Systems for Protection and Delivery of Phenolic Bioactive Compounds: Two Study Cases-Hydroxytyrosol and Curcumin.

Insufficient intake of beneficial food components into the human body is a major issue for many people. Among the strategies proposed to overcome this complication, colloid systems have been proven to offer successful solutions in many cases. The scientific community agrees that the production of colloid delivery systems is a good way to adequately protect and deliver nutritional components.

Learning Frequency Domain Priors for Image Demoireing.

Image demoireing is a multi-faceted image restoration task involving both moire pattern removal and color restoration. In this paper, we raise a general degradation model to describe an image contaminated by moire patterns, and propose a novel multi-scale bandpass convolutional neural network (MBCNN) for single image demoireing. For moire pattern removal, we propose a multi-block-size learnable bandpass filters (M-LBFs), based on a block-wise frequency domain transform, to learn the frequency domain priors of moire patterns.

Learning a Model-Driven Variational Network for Deformable Image Registration.

Data-driven deep learning approaches to image registration can be less accurate than conventional iterative approaches, especially when training data is limited. To address this issue and meanwhile retain the fast inference speed of deep learning, we propose VR-Net, a novel cascaded variational network for unsupervised deformable image registration. Using a variable splitting optimization scheme, we first convert the image registration problem, established in a generic variational framework, into two sub-problems, one with a point-wise, closed-form solution and the other one being a denoising problem.

A Continual Learning Survey: Defying Forgetting in Classification Tasks.

Artificial neural networks thrive in solving the classification problem for a particular rigid task, acquiring knowledge through generalized learning behaviour from a distinct training phase. The resulting network resembles a static entity of knowledge, with endeavours to extend this knowledge without targeting the original task resulting in a catastrophic forgetting. Continual learning shifts this paradigm towards networks that can continually accumulate knowledge over different tasks without the need to retrain from scratch.

Cognitive Relevance Transform for Population Re-Targeting.

This work examines the differences between a human and a machine in object recognition tasks. The machine is useful as much as the output classification labels are correct and match the dataset-provided labels. However, very often a discrepancy occurs because the dataset label is different than the one expected by a human.

Effective assay for olive vinegar production from olive oil mill wastewaters.

In this work, an effective and simple approach for vinegar production from olive oil press-mill wastewaters (OMW) is presented. Effects of sterilization and yeast presence on the acetic acid production were investigated. Sugar addition and inoculum of selected yeast starter have been crucial for a satisfactory acidification.

Robust Fusion of Color and Depth Data for RGB-D Target Tracking Using Adaptive Range-Invariant Depth Models and Spatio-Temporal Consistency Constraints.

This paper presents a novel robust method for single target tracking in RGB-D images, and also contributes a substantial new benchmark dataset for evaluating RGB-D trackers. While a target object's color distribution is reasonably motion-invariant, this is not true for the target's depth distribution, which continually varies as the target moves relative to the camera. It is therefore nontrivial to design target models which can fully exploit (potentially very rich) depth information for target tracking.

Robust Real-Time Music Transcription with a Compositional Hierarchical Model.

The paper presents a new compositional hierarchical model for robust music transcription. Its main features are unsupervised learning of a hierarchical representation of input data, transparency, which enables insights into the learned representation, as well as robustness and speed which make it suitable for real-world and real-time use. The model consists of multiple layers, each composed of a number of parts.

microRNAs differentially modulated in response to heat and drought stress in durum wheat cultivars with contrasting water use efficiency.

Plant stress response is a complex molecular process based on transcriptional and posttranscriptional regulation of many stress-related genes. microRNAs are the best-studied class of small RNAs known to play key regulatory roles in plant response to stress, besides being involved in plant development and organogenesis. We analyzed the leaf miRNAome of two durum wheat cultivars (Cappelli and Ofanto) characterized by a contrasting water use efficiency, exposed to heat stress, and mild and severe drought stress.

Technological Potential of Lactobacillus Strains Isolated from Fermented Green Olives: In Vitro Studies with Emphasis on Oleuropein-Degrading Capability.

Technological properties of two strains of Lactobacillus plantarum (B3 and B11) and one of Lactobacillus pentosus (B4), previously isolated from natural fermented green olives, have been studied in vitro. Acidifying ability, salt, temperature, and pH tolerances of all strains were found in the range reported for similar strains produced in Italy and optimal growth conditions were found to be 6.0-8.

Yeast Autolysis in Sparkling Wine Aging: Use of Killer and Sensitive Saccharomyces cerevisiae Strains in Co-Culture.

Background: Sparkling wines produced by traditional method owe their characteristics to secondary fermentation and maturation that occur during a slow ageing in bottles. Yeast autolysis plays an important role during the sparkling wine aging. Using a combination of killer and sensitive yeasts is possible to accelerate yeast autolysis and reduce maturing time.

Use of purple durum wheat to produce naturally functional fresh and dry pasta.

In this study, the effects of different milling procedures (roller-milling vs. stone-milling) and pasta processing (fresh vs. dried spaghetti), and cooking on the antioxidant components and sensory properties of purple durum wheat were investigated.

Visual Object Tracking Performance Measures Revisited.

The problem of visual tracking evaluation is sporting a large variety of performance measures, and largely suffers from lack of consensus about which measures should be used in experiments. This makes the cross-paper tracker comparison difficult. Furthermore, as some measures may be less effective than others, the tracking results may be skewed or biased toward particular tracking aspects.

A Novel Performance Evaluation Methodology for Single-Target Trackers.

This paper addresses the problem of single-target tracker performance evaluation. We consider the performance measures, the dataset and the evaluation system to be the most important components of tracker evaluation and propose requirements for each of them. The requirements are the basis of a new evaluation methodology that aims at a simple and easily interpretable tracker comparison.

Effects of Heat Stress on Metabolite Accumulation and Composition, and Nutritional Properties of Durum Wheat Grain.

Durum wheat (Triticum turgidum (L.) subsp. turgidum (L.

Conservation of AtTZF1, AtTZF2, and AtTZF3 homolog gene regulation by salt stress in evolutionarily distant plant species.

Arginine-rich tandem zinc-finger proteins (RR-TZF) participate in a wide range of plant developmental processes and adaptive responses to abiotic stress, such as cold, salt, and drought. This study investigates the conservation of the genes AtTZF1-5 at the level of their sequences and expression across plant species. The genomic sequences of the two RR-TZF genes TdTZF1-A and TdTZF1-B were isolated in durum wheat and assigned to chromosomes 3A and 3B, respectively.

Evidence of oleuropein degradation by olive leaf protein extract.

The enzymatic activity of raw protein olive leaf extract has been investigated in vivo, on olive leaf homogenate and, in vitro with pure oleuropein and other phenolic substrates. At least two types of enzymes were found to be involved in the degradation of endogenous oleuropein in olive leaves. As for the in vitro experiments, the presence of active polyphenoloxidase and β-glucosidase was determined by HPLC and UV-Visible spectroscopy.