Sampling Equivariant Self-Attention Networks for Object Detection in Aerial Images.

Objects in aerial images show greater variations in scale and orientation than in other images, making them harder to detect using vanilla deep convolutional neural networks. Networks with sampling equivariance can adapt sampling from input feature maps to object transformation, allowing a convolutional kernel to extract effective object features under different transformations. However, methods such as deformable convolutional networks can only provide sampling equivariance under certain circumstances, as they sample by location. We propose sampling equivariant self-attention networks, which treat self-attention restricted to a local image patch as convolution sampling by masks instead of locations, and a transformation embedding module to improve the equivariant sampling further. We further propose a novel randomized normalization module to enhance network generalization and a quantitative evaluation metric to fairly evaluate the ability of sampling equivariance of different models. Experiments show that our model provides significantly better sampling equivariance than existing methods without additional supervision and can thus extract more effective image features. Our model achieves state-of-the-art results on the DOTA-v1.0, DOTA-v1.5, and HRSC2016 datasets without additional computations or parameters.

Mesh Neural Networks Based on Dual Graph Pyramids.

Deep neural networks (DNNs) have been widely used for mesh processing in recent years. However, current DNNs can not process arbitrary meshes efficiently. On the one hand, most DNNs expect 2-manifold, watertight meshes, but many meshes, whether manually designed or automatically generated, may have gaps, non-manifold geometry, or other defects. On the other hand, the irregular structure of meshes also brings challenges to building hierarchical structures and aggregating local geometric information, which is critical to conduct DNNs. In this paper, we present DGNet, an efficient, effective and generic deep neural mesh processing network based on dual graph pyramids; it can handle arbitrary meshes. Firstly, we construct dual graph pyramids for meshes to guide feature propagation between hierarchical levels for both downsampling and upsampling. Secondly, we propose a novel convolution to aggregate local features on the proposed hierarchical graphs. By utilizing both geodesic neighbors and Euclidean neighbors, the network enables feature aggregation both within local surface patches and between isolated mesh components. Experimental results demonstrate that DGNet can be applied to both shape analysis and large-scale scene understanding. Furthermore, it achieves superior performance on various benchmarks, including ShapeNetCore, HumanBody, ScanNet and Matterport3D. Code and models will be available at https://github.com/li-xl/DGNet.

Cover Crops Modulate the Response of Arbuscular Mycorrhizal Fungi to Water Supply: A Field Study in Corn.

Cover crops (CCs) were found to improve soil health by increasing plant diversity and ground cover. They may also improve water supply for cash crops by reducing evaporation and increasing soil water storage capacity. However, their influence on plant-associated microbial communities, including symbiotic arbuscular mycorrhizal fungi (AMF), is less well understood. In a corn field trial, we studied the response of AMF to a four-species winter CC, relative to a no-CC control, as well as to two contrasting water supply levels (i.e., drought and irrigated). We measured AMF colonization of corn roots and used Illumina MiSeq sequencing to study the composition and diversity of soil AMF communities at two depths (i.e., 0-10 and 10-20 cm). In this trial, AMF colonization was high (61-97%), and soil AMF communities were represented by 249 amplicon sequence variants (ASVs) belonging to 5 genera and 33 virtual taxa. Glomus, followed by Claroideoglomus and Diversispora (class Glomeromycetes), were the dominant genera. Our results showed interacting effects between CC treatments and water supply levels for most of the measured variables. The percentage of AMF colonization, arbuscules, and vesicles tended to be lower in irrigated than drought sites, with significant differences detected only under no-CC. Similarly, soil AMF phylogenetic composition was affected by water supply only in the no-CC treatment. Changes in the abundance of individual virtual taxa also showed strong interacting effects between CCs, irrigation, and sometimes soil depth, although CC effects were clearer than irrigation effects. An exception to these interactions was soil AMF evenness, which was higher in CC than no-CC, and higher under drought than irrigation. Soil AMF richness was not affected by the applied treatments. Our results suggest that CCs can affect the structure of soil AMF communities and modulate their response to water availability levels, although soil heterogeneity could influence the final outcome.

Accurate Dynamic SLAM Using CRF-Based Long-Term Consistency.

Accurate camera pose estimation is essential and challenging for real world dynamic 3D reconstruction and augmented reality applications. In this article, we present a novel RGB-D SLAM approach for accurate camera pose tracking in dynamic environments. Previous methods detect dynamic components only across a short time-span of consecutive frames. Instead, we provide a more accurate dynamic 3D landmark detection method, followed by the use of long-term consistency via conditional random fields, which leverages long-term observations from multiple frames. Specifically, we first introduce an efficient initial camera pose estimation method based on distinguishing dynamic from static points using graph-cut RANSAC. These static/dynamic labels are used as priors for the unary potential in the conditional random fields, which further improves the accuracy of dynamic 3D landmark detection. Evaluation using the TUM and Bonn RGB-D dynamic datasets shows that our approach significantly outperforms state-of-the-art methods, providing much more accurate camera trajectory estimation in a variety of highly dynamic environments. We also show that dynamic 3D reconstruction can benefit from the camera poses estimated by our RGB-D SLAM approach.

Directly observing household food waste generation using composition audits in a Canadian municipality.

This study complements a previous study that combined household survey data with weights of curbside separated organics in the residential sector (Parizeau et al., 2015). Our findings reinforce the need for the collection of detailed observational data in household food waste audits. We revisited some households from the original study and a new set of households in order to conduct compositional audits on all three streams of waste, and to combine these results with survey data. In the compositional audits, we observed an average food waste per capita of 1.64 kg per week, and avoidable food waste per capita of 1.05 kg per week. Overall, 64% of wasted food was avoidable. The highest proportions of total and avoidable food waste came from fruits and vegetables (63%; 59%), followed by bread products (14%; 22%). Combining the compositional audits with survey data, we confirmed some of the behavioural and attitudinal patterns assessed in our previous study, including that household composition, food awareness, waste awareness, and convenience lifestyles may impact household food waste generation rates. Individual household audits provide greater insight into food waste generation than do curbside weights.

Two-Layer QR Codes.

A quick-response code (QR code) is a two-dimensional code akin to a barcode that encodes a message of limited length. In this paper, we present a variant of QR code, a two-layer QR code. Its two-layer structure can display two alternative messages when scanned from two different directions. We propose a method to generate such two-layer QR codes encoding two given messages in a few seconds. We also demonstrate the robustness of our method on both synthetic and fabricated examples. All source code will be made publicly available (https://github.com/yuantailing/two-layer-qrcode).

Effect of variety, soil fertility status and agronomic treatments on carrot mineral and phytochemical composition and consumer liking of flavor traits.

BACKGROUND: The aim of this study was to investigate the effects of variety (Nantes and Imperator), soil fertility status (high and low) and agronomic treatments on yield and quality traits of carrot composition and sensory factors. The treatments compared synthetic nitrogen at conventionally recommended amounts with compost-sourced nitrogen (high and low rates) and a range of amendments (compost, compost tea, micronutrients and foliar treatments). Additionally, we intended to identify factors affecting polyacetylene accumulation in carrots, owing to the growing interest in their health effects and paucity of agronomic information on their bioaccumulation in carrots. RESULTS: Imperator accumulated more minerals, produced more phytochemicals and had higher antioxidant capacity than Nantes, which had more carotenoids. However, consumers preferred the flavor of Nantes over Imperator. High-fertility soil produced carrots of superior nutritional quality than did low-fertility soil, regardless of year-of-application amendments, the effects of which were often variety-dependent. High soil biological activity was able to overcome low fertility status and stimulate greater yield. Carrot phosphorus was correlated with falcarindiol biosynthesis. Chlorogenic acid and falcarindiol were correlated with antioxidant capacity, but not falcarinol or total phenolic compounds. CONCLUSION: Carrots were not strongly affected by agronomic treatments in terms of yield or phytochemical status; however, soil biological activity overcame a soil nutrient deficit in terms of yield. Phenolic compounds and antioxidant status were generally higher in the high-fertility site, whereas polyacetylenes were variety-dependent. Chlorogenic acid and falcarindiol were associated with antioxidant capacity, but not total phenolic compounds and carotenoids. © 2019 Society of Chemical Industry.

A Comparative Study of Algorithms for Realtime Panoramic Video Blending.

Unlike image blending algorithms, video blending algorithms have been little studied. In this paper, we investigate 6 popular blending algorithms-feather blending, multi-band blending, modified Poisson blending, mean value coordinate blending, multi-spline blending and convolution pyramid blending. We consider their application to blending realtime panoramic videos, a key problem in various virtual reality tasks. To evaluate the performances and suitabilities of the 6 algorithms for this problem, we have created a video benchmark with several videos captured under various conditions. We analyze the time and memory needed by the above 6 algorithms, for both CPU and GPU implementations (where readily parallelizable). The visual quality provided by these algorithms is also evaluated both objectively and subjectively. The video benchmark and algorithm implementations are publicly available1.

Pairwise Force SPH Model for Real-Time Multi-Interaction Applications.

In this paper, we present a novel pairwise-force smoothed particle hydrodynamics (PF-SPH) model to enable simulation of various interactions at interfaces in real time. Realistic capture of interactions at interfaces is a challenging problem for SPH-based simulations, especially for scenarios involving multiple interactions at different interfaces. Our PF-SPH model can readily handle multiple types of interactions simultaneously in a single simulation; its basis is to use a larger support radius than that used in standard SPH. We adopt a novel anisotropic filtering term to further improve the performance of interaction forces. The proposed model is stable; furthermore, it avoids the particle clustering problem which commonly occurs at the free surface. We show how our model can be used to capture various interactions. We also consider the close connection between droplets and bubbles, and show how to animate bubbles rising in liquid as well as bubbles in air. Our method is versatile, physically plausible and easy-to-implement. Examples are provided to demonstrate the capabilities and effectiveness of our approach.

Variability of Serum Thyroglobulin Levels in Post- Thyroidectomy Patients with Well-Differentiated Thyroid Cancer: the ATA Guidelines.

OBJECTIVE: Evaluate the variability of stimulated serum thyroglobulin (Tg) levels in post-thyroidectomy patients with well-differentiated thyroid cancer (WDTC) and determine the frequency of undetectable Tg in patients with evidence of functional thyroid tissue after a 131-I whole-body scan (WBS). METHODS: A retrospective record review of patients with WDTC referred to our clinic from 1990 to 2010. Demographic data, histology, staging, imaging studies, stimulated Tg values, and the presence if applicable of Tg antibodies (TgAb) were documented. The images of whole-body radioiodine scans were reviewed to assess the extent of functional thyroid tissue. RESULTS: A total of 142 cases were evaluated with 417 studies. There were 112 women and 30 men; the median age was 47 years. The tumor histologies included 97 papillary (4 had the Hurthle cell variant), 33 papillary-follicular tumor, and 12 follicular tumors; 7 were multifocal. ATA classification was used; groups were divided into low (55%) and intermediate-high risk (45%). The final analysis comprised 84 patients, having among them 170 studies that included Tg values in their records. The cut-off value for Tg was 2.0 ng/ml, and for TgAb, it was 20 IU/ml or more. Residual functional tissue was present in 105 (62%) cases. Discordant Tg results were found in 55% of the low-risk patients; of those, only 3 had TgAb. In the intermediate- and high-risk group, 47% had discordant results; 2 cases had TgAb. CONCLUSION: The variability of the Tg levels and the high frequency of discordant results (positive WBSs with undectable Tg levels) bring into question the standard recommendation of conservative management for low-risk patients. Follow-ups should include a Tg assay and imaging studies.

Efficient, Edge-Aware, Combined Color Quantization and Dithering.

In this paper, we present a novel algorithm to simultaneously accomplish color quantization and dithering of images. This is achieved by minimizing a perception-based cost function, which considers pixel-wise differences between filtered versions of the quantized image and the input image. We use edge aware filters in defining the cost function to avoid mixing colors on the opposite sides of an edge. The importance of each pixel is weighted according to its saliency. To rapidly minimize the cost function, we use a modified multi-scale iterative conditional mode (ICM) algorithm, which updates one pixel a time while keeping other pixels unchanged. As ICM is a local method, careful initialization is required to prevent termination at a local minimum far from the global one. To address this problem, we initialize ICM with a palette generated by a modified median-cut method. Compared with previous approaches, our method can produce high-quality results with a fewer visual artifacts but also requires significantly less computational effort.

Realtime Reconstruction of an Animating Human Body from a Single Depth Camera.

We present a method for realtime reconstruction of an animating human body,which produces a sequence of deforming meshes representing a given performance captured by a single commodity depth camera. We achieve realtime single-view mesh completion by enhancing the parameterized SCAPE model.Our method, which we call Realtime SCAPE, performs full-body reconstruction without the use of markers.In Realtime SCAPE, estimations of body shape parameters and pose parameters, needed for reconstruction, are decoupled. Intrinsic body shape is first precomputed for a given subject, by determining shape parameters with the aid of a body shape database. Subsequently, per-frame pose parameter estimation is performed by means of linear blending skinning (LBS); the problem is decomposed into separately finding skinning weights and transformations. The skinning weights are also determined offline from the body shape database,reducing online reconstruction to simply finding the transformations in LBS. Doing so is formulated as a linear variational problem;carefully designed constraints are used to impose temporal coherence and alleviate artifacts. Experiments demonstrate that our method can produce full-body mesh sequences with high fidelity.

Simultaneous Camera Path Optimization and Distraction Removal for Improving Amateur Video.

A major difference between amateur and professional video lies in the quality of camera paths. Previous work on video stabilization has considered how to improve amateur video by smoothing the camera path. In this paper, we show that additional changes to the camera path can further improve video aesthetics. Our new optimization method achieves multiple simultaneous goals: 1) stabilizing video content over short time scales; 2) ensuring simple and consistent camera paths over longer time scales; and 3) improving scene composition by automatically removing distractions, a common occurrence in amateur video. Our approach uses an L(1) camera path optimization framework, extended to handle multiple constraints. Two passes of optimization are used to address both low-level and high-level constraints on the camera path. The experimental and user study results show that our approach outputs video that is perceptually better than the input, or the results of using stabilization only.

Regularization Based Iterative Point Match Weighting for Accurate Rigid Transformation Estimation.

Feature extraction and matching (FEM) for 3D shapes finds numerous applications in computer graphics and vision for object modeling, retrieval, morphing, and recognition. However, unavoidable incorrect matches lead to inaccurate estimation of the transformation relating different datasets. Inspired by AdaBoost, this paper proposes a novel iterative re-weighting method to tackle the challenging problem of evaluating point matches established by typical FEM methods. Weights are used to indicate the degree of belief that each point match is correct. Our method has three key steps: (i) estimation of the underlying transformation using weighted least squares, (ii) penalty parameter estimation via minimization of the weighted variance of the matching errors, and (iii) weight re-estimation taking into account both matching errors and information learnt in previous iterations. A comparative study, based on real shapes captured by two laser scanners, shows that the proposed method outperforms four other state-of-the-art methods in terms of evaluating point matches between overlapping shapes established by two typical FEM methods, resulting in more accurate estimates of the underlying transformation. This improved transformation can be used to better initialize the iterative closest point algorithm and its variants, making 3D shape registration more likely to succeed.

Left Ventricular Function Parameters in a Hispanic Population: Comparison of Planar & Tomographic Radionuclide Ventriculography (MUGA).

OBJECTIVE: Left ventricular (LV) function parameters have major diagnostic and prognostic importance in heart disease. Measurement of ventricular function with tomographic (SPECT) radionuclide ventriculography (MUGA) decreases camera time, improves contrast resolution, accuracy of interpretation and the overall reliability of the study as compared to planar MUGA. The relationship between these techniques is well established particularly with LV ejection fraction (LVEF), while there is limited data comparing the diastolic function parameters. Our goal was to validate the LV function parameters in our Hispanic population. METHODS: Studies from 44 patients, available from 2009-2010, were retrospectively evaluated. RESULTS: LVEF showed a good correlation between the techniques (r=0.94) with an average difference of 3.8%. In terms of categorizing the results as normal or abnormal, this remained unchanged in 95% of the cases (p=0.035). For the peak filling rate, there was a moderate correlation between the techniques (r=0.71), whereas the diagnosis remained unchanged in 89% of cases (p=0.0004). Time to peak filling values only demonstrated a weak correlation (r=0.22). Nevertheless, the diagnosis remained the same in 68% of the cases (p=0.089). CONCLUSION: Systolic function results in our study were well below the 7-10% difference reported in the literature. Only a weak to moderate correlation was observed with the diastolic function parameters. Comparison with echocardiogram (not available) may be of benefit to evaluate which of these techniques results in more accurate diastolic function parameters.

Increasing crop diversity mitigates weather variations and improves yield stability.

Cropping sequence diversification provides a systems approach to reduce yield variations and improve resilience to multiple environmental stresses. Yield advantages of more diverse crop rotations and their synergistic effects with reduced tillage are well documented, but few studies have quantified the impact of these management practices on yields and their stability when soil moisture is limiting or in excess. Using yield and weather data obtained from a 31-year long term rotation and tillage trial in Ontario, we tested whether crop rotation diversity is associated with greater yield stability when abnormal weather conditions occur. We used parametric and non-parametric approaches to quantify the impact of rotation diversity (monocrop, 2-crops, 3-crops without or with one or two legume cover crops) and tillage (conventional or reduced tillage) on yield probabilities and the benefits of crop diversity under different soil moisture and temperature scenarios. Although the magnitude of rotation benefits varied with crops, weather patterns and tillage, yield stability significantly increased when corn and soybean were integrated into more diverse rotations. Introducing small grains into short corn-soybean rotation was enough to provide substantial benefits on long-term soybean yields and their stability while the effects on corn were mostly associated with the temporal niche provided by small grains for underseeded red clover or alfalfa. Crop diversification strategies increased the probability of harnessing favorable growing conditions while decreasing the risk of crop failure. In hot and dry years, diversification of corn-soybean rotations and reduced tillage increased yield by 7% and 22% for corn and soybean respectively. Given the additional advantages associated with cropping system diversification, such a strategy provides a more comprehensive approach to lowering yield variability and improving the resilience of cropping systems to multiple environmental stresses. This could help to sustain future yield levels in challenging production environments.

Changing the Graduate Medical Education Funding Path to Reduce the Price of Health Care Services.

An analysis of the current Graduate Medical Education (GME) funding stream reveals undesired aspects that limit the number of graduates and may tend to raise the price of health care services. The author shows that a different model of GME funding changes the economic dynamics and takes advantage of economic forces to increase the supply of graduates, while potentially reducing the price of health care services.

Household-level dynamics of food waste production and related beliefs, attitudes, and behaviours in Guelph, Ontario.

It has been estimated that Canadians waste $27 billion of food annually, and that half of that waste occurs at the household level (Gooch et al., 2010). There are social, environmental, and economic implications for this scale of food waste, and source separation of organic waste is an increasingly common municipal intervention. There is relatively little research that assesses the dynamics of household food waste (particularly in Canada). The purpose of this study is to combine observations of organic, recyclable, and garbage waste production rates to survey results of food waste-related beliefs, attitudes, and behaviours at the household level in the mid-sized municipality of Guelph, Ontario. Waste weights and surveys were obtained from 68 households in the summer of 2013. The results of this study indicate multiple relationships between food waste production and household shopping practices, food preparation behaviours, household waste management practices, and food-related attitudes, beliefs, and lifestyles. Notably, we observed that food awareness, waste awareness, family lifestyles, and convenience lifestyles were related to food waste production. We conclude that it is important to understand the diversity of factors that can influence food wasting behaviours at the household level in order to design waste management systems and policies to reduce food waste.

THE ROLE OF NUCLEAR IMAGING IN TRAUMATIC HEPATOPLEURAL FISTULA: A CASE REPORT.

Penetrating injuries are a major cause of mortality and morbidity. The most common diagnostic tool used in this setting is CT scan. We present a case of a traumatic hepatopleural fistula demonstrated by hepatobiliary scintigraphy. Traumatic abdominal injuries to the liver and diaphragm can result in complications, whose detection by CT scan is not always straightforward. Hepatobiliary scintigraphy is very useful in the search of bilious pleural effusions.

SuperMatching: feature matching using supersymmetric geometric constraints.

Feature matching is a challenging problem at the heart of numerous computer graphics and computer vision applications. We present the SuperMatching algorithm for finding correspondences between two sets of features. It does so by considering triples or higher order tuples of points, going beyond the pointwise and pairwise approaches typically used. SuperMatching is formulated using a supersymmetric tensor representing an affinity metric that takes into account feature similarity and geometric constraints between features: Feature matching is cast as a higher order graph matching problem. SuperMatching takes advantage of supersymmetry to devise an efficient sampling strategy to estimate the affinity tensor, as well as to store the estimated tensor compactly. Matching is performed by an efficient higher order power iteration approach that takes advantage of this compact representation. Experiments on both synthetic and real data show that SuperMatching provides more accurate feature matching than other state-of-the-art approaches for a wide range of 2D and 3D features, with competitive computational cost.