Foreground map evaluation is crucial for gauging the progress of object segmentation algorithms, in particular in the field of salient object detection where the purpose is to accurately detect and ...segment the most salient object in a scene. Several measures (e.g., area-under-the-curve, F1-measure, average precision, etc.) have been used to evaluate the similarity between a foreground map and a ground-truth map. The existing measures are based on pixel-wise errors and often ignore the structural similarities. Behavioral vision studies, however, have shown that the human visual system is highly sensitive to structures in scenes. Here, we propose a novel, efficient (0.005 s per image), and easy to calculate measure known as
S-measure
(structural measure) to evaluate foreground maps. Our new measure simultaneously evaluates region-aware and object-aware structural similarity between a foreground map and a ground-truth map. We demonstrate superiority of our measure over existing ones using 4 meta-measures on 5 widely-used benchmark datasets. Furthermore, we conduct a behavioral judgment study over a new database. Data from 45 subjects shows that on average they preferred the saliency maps chosen by our measure over the saliency maps chosen by the state-of-the-art measures. Our experimental results offer new insights into foreground map evaluation where current measures fail to truly examine the strengths and weaknesses of models. Code:
https://github.com/DengPingFan/S-measure
.
Although the fates of microplastics (0.1-5 mm in size) and nanoplastics (<100 nm) in marine environments are being increasingly well studied
, little is known about the behaviour of nanoplastics in ...terrestrial environments
, especially agricultural soils
. Previous studies have evaluated the consequences of nanoplastic accumulation in aquatic plants, but there is no direct evidence for the internalization of nanoplastics in terrestrial plants. Here, we show that both positively and negatively charged nanoplastics can accumulate in Arabidopsis thaliana. The aggregation promoted by the growth medium and root exudates limited the uptake of amino-modified polystyrene nanoplastics with positive surface charges. Thus, positively charged nanoplastics accumulated at relatively low levels in the root tips, but these nanoplastics induced a higher accumulation of reactive oxygen species and inhibited plant growth and seedling development more strongly than negatively charged sulfonic-acid-modified nanoplastics. By contrast, the negatively charged nanoplastics were observed frequently in the apoplast and xylem. Our findings provide direct evidence that nanoplastics can accumulate in plants, depending on their surface charge. Plant accumulation of nanoplastics can have both direct ecological effects and implications for agricultural sustainability and food safety.
COVID-19 is associated with 5.1% mortality. Although the virological, epidemiological, clinical, and management outcome features of COVID-19 patients have been defined rapidly, the inflammatory and ...immune profiles require definition as they influence pathogenesis and clinical expression of COVID-19. Here we show lymphopenia, selective loss of CD4+ T cells, CD8+ T cells and NK cells, excessive T-cell activation and high expression of T-cell inhibitory molecules are more prominent in severe cases than in those with mild disease. CD8+ T cells in patients with severe disease express high levels of cytotoxic molecules. Histochemical studies of lung tissue from one fatality show sub-anatomical distributions of SARS-CoV-2 RNA and massive infiltration of T cells and macrophages. Thus, aberrant activation and dysregulation of CD8+ T cells occur in patients with severe COVID-19 disease, an effect that might be for pathogenesis of SARS-CoV-2 infection and indicate that immune-based targets for therapeutic interventions constitute a promising treatment for severe COVID-19 patients.
RGB-D salient object detection (SOD) aims to segment the most attractive objects in a pair of cross-modal RGB and depth images. Currently, most existing RGB-D SOD methods focus on the foreground ...region when utilizing the depth images. However, the background also provides important information in traditional SOD methods for promising performance. To better explore salient information in both foreground and background regions, this paper proposes a Bilateral Attention Network (BiANet) for the RGB-D SOD task. Specifically, we introduce a Bilateral Attention Module (BAM) with a complementary attention mechanism: foreground-first (FF) attention and background-first (BF) attention. The FF attention focuses on the foreground region with a gradual refinement style, while the BF one recovers potentially useful salient information in the background region. Benefited from the proposed BAM module, our BiANet can capture more meaningful foreground and background cues, and shift more attention to refining the uncertain details between foreground and background regions. Additionally, we extend our BAM by leveraging the multi-scale techniques for better SOD performance. Extensive experiments on six benchmark datasets demonstrate that our BiANet outperforms other state-of-the-art RGB-D SOD methods in terms of objective metrics and subjective visual comparison. Our BiANet can run up to 80 fps on <inline-formula> <tex-math notation="LaTeX">224\times 224 </tex-math></inline-formula> RGB-D images, with an NVIDIA GeForce RTX 2080Ti GPU. Comprehensive ablation studies also validate our contributions.
Smart polymeric materials with dynamically tunable physico‐chemical characteristics in response to changes of environmental stimuli, have received considerable attention in myriad fields. The diverse ...combination of their micro‐/nano‐structural and molecular designs creates promising and exciting opportunities for exploiting advanced smart polymeric materials. Engineering micro‐/nano‐structures into smart polymeric materials with elaborate molecular design enables intricate coordination between their structures and molecular‐level response to cooperatively realize smart functions for practical applications. In this review, recent progresses of smart polymeric materials that combine micro‐/nano‐structures and molecular design to achieve designed advanced functions are highlighted. Smart hydrogels, gating membranes, gratings, milli‐particles, micro‐particles and microvalves are employed as typical examples to introduce their design and fabrication strategies. Meanwhile, the key roles of interplay between their micro‐/nano‐structures and responsive properties to realize the desired functions for their applications are emphasized. Finally, perspectives on the current challenges and opportunities of micro‐/nano‐structured smart polymeric materials for their future development are presented.
Smart polymeric materials with elaborate micro‐/nano‐structural and molecular designs to achieve designed functions for myriad applications are summarized. The smart materials, including responsive hydrogels, gating membranes, gratings, milli‐particles, micro‐particles and microvalves, can achieve intricate coordination between their micro‐/nano‐structures and responsive properties to cooperatively achieve desired functions.
Plastic products are widely used around the world, but waste plastic is not reasonably managed and causes serious plastic pollution. Biodegradable plastics (BPs) provide an alternative to ...conventional plastics, but not all BPs can be completely degraded under natural conditions. Instead, they may break down into microplastics (MPs) faster than conventional plastics, posing an additional threat to soil environment. In this paper, the definition, applications, and degradation behaviors of BPs, including biodegradable microplastics (BMPs), are reviewed, and we comprehensively summarized the eco-toxicological effects of BMPs in soil ecosystems, in terms of physical and chemical properties of soil, soil nutrient cycling, soil bacterial and fungal communities, soil flora and fauna. The compound effects of BMPs and other pollutants were also addressed. The results revealed that BMPs made different or more severely effects compared to conventional MPs. Overall, this review aims to address gaps in knowledge, shed light on the ecological effects of BPs and BMPs in soil. BPs are not a perfect substitute to solve plastic pollution, and further exploration should focus on their generation, environmental behavior, ecological impact and whether BMPs cause more harm than conventional MPs.
This paper investigates the strategies for adopting blockchain technology in the fresh product supply chain (FPSC) consisting of a supplier, a third-party logistics service provider (3PL) and an ...e-tailer. We analyse the optimal strategies of FPSC members under the benchmark scenario where the FPSC does not adopt blockchain technology and those under the three scenarios where the supplier, 3PL and e-tailer lead the construction of the blockchain-based traceability system (BTS), respectively. We find that adopting blockchain technology is not always the optimal decision for the FPSC, which is related to the consumers' acceptance degree for the product without blockchain technology, the deterioration rate of the fresh product and the allocation proportion of traceability cost of FPSC members when adopting blockchain technology. Regardless of the power and status of each member in the FPSC, it can lead the construction of the BTS. From the perspective of whole FPSC's profit maximisation, the leader of the FPSC should lead the construction of the BTS under the coordination of a two-part tariff contract. This study provides valuable insights for FPSCs to adopt blockchain technology.
Blockchain technology is an emerging technology developed in recent years. It has powerful information traceability function. The blockchain technology plays an important role in monitoring product ...quality and responding to product safety problems. Under considering the traceability awareness of consumers and the cost of using the blockchain technology, should the supply chain adopt the blockchain technology? The research on this issue deserves great attentions. In this paper, for a three-stage supply chain consisting of a supplier, a manufacturer and a retailer, we study the optimal pricing strategies of the supply chain considering the traceability awareness of consumers in two scenarios. These two scenarios are: scenario N (i.e., the supply chain does not adopt the blockchain technology) and scenario B (i.e., the supply chain adopts the blockchain technology). On this basis, we discuss the conditions that the supply chain adopts the blockchain technology by comparing the optimal profits of the supply chain and its members in two scenarios. Further, we discuss the problem of supply chain coordination when adopting the blockchain technology. The results show that it is conditional for the supply chain to adopt the blockchain technology, and the condition is related to the traceability awareness of consumers, the production costs of the supplier and manufacturer, and the cost of using the blockchain technology. We also find that under a certain condition, the revenue sharing contract can realize a Pareto improvement for the supply chain that adopts the blockchain technology.
Salient object detection, which simulates human visual perception in locating the most significant object(s) in a scene, has been widely applied to various computer vision tasks. Now, the advent of ...depth sensors means that depth maps can easily be captured; this additional spatial information can boost the performance of salient object detection. Although various RGB-D based salient object detection models with promising performance have been proposed over the past several years, an in-depth understanding of these models and the challenges in this field remains lacking. In this paper, we provide a comprehensive survey of RGB-D based salient object detection models from various perspectives, and review related benchmark datasets in detail. Further, as light fields can also provide depth maps, we review salient object detection models and popular benchmark datasets from this domain too. Moreover, to investigate the ability of existing models to detect salient objects, we have carried out a comprehensive attribute-based evaluation of several representative RGB-D based salient object detection models. Finally, we discuss several challenges and open directions of RGB-D based salient object detection for future research. All collected models, benchmark datasets, datasets constructed for attribute-based evaluation, and related code are publicly available at
https://github.com/taozh2017/RGBD-SODsurvey
.
Long delivery lead times and costly transportation postage are significant characteristics of B2C cross-border e-commerce and logistics. They engender preference inconsistencies and reversals in ...customers, which can lead to product returns. The aim of this study is to enable retailers to select the optimal cross-border logistics mode that fulfils their marketing strategies while taking product returns into consideration. We propose a novel way to describe customer utility by incorporating customer time preferences, and construct three cross-border logistics models. The theoretical and numerical analyses indicate that, if retailers want to eliminate or reduce their product return rates, they can adjust their delivery lead times in each logistics mode under various product procurement and sales prices, commodity tariffs, international and domestic postage and operating costs. In particular, the O2O mode is always a better option for retailers than the O2D mode, and under certain conditions, the D2D mode is better for retailers than the O2O mode. To increase market demand, the O2O mode is optimal for retailers selling high-priced products, while the O2D mode is optimal for retailers selling low-priced products. This study also provides suggestions for overseas manufacturers. These findings are applicable to B2C cross-border e-commerce, cross-border logistics, and overseas production.
PDF
