Presentation attack detection based on two-stream vision transformers with self-attention fusion

Aiming at the performance degradation of the existing presentation attack detection methods due to the illumination variation, a two-stream vision transformers framework (TSViT) based on transfer learning in two complementary spaces is proposed in this paper. The face images of RGB color space and multi-scale retinex with color restoration (MSRCR) space are fed to TSViT to learn the distinguishing features of presentation attack detection. To effectively fuse features from two sources (RGB color space images and MSRCR images), a feature fusion method based on self-attention is built, which can effectively capture the complementarity of two features. Experiments and analysis on Oulu-NPU, CASIA-MFSD, and Replay-Attack databases show that it outperforms most existing methods in intra-database testing and achieves good generalization performance in cross-database testing.     

A customized low-rank prior model for structured cartoon–texture image decomposition

The mathematical characterization of the texture component plays an instrumental role in image decomposition. In this paper, we are concerned with a low-rank texture prior based cartoon–texture image decomposition model, which utilizes a total variation norm and a global nuclear norm to characterize the cartoon and texture components, respectively. It is promising that our decomposition model is not only extremely simple, but also works perfectly for globally well-patterned images in the sense that the model can recover cleaner texture (or details) than the other novel models. Moreover, such a model can be easily reformulated as a separable convex optimization problem, thereby enjoying a splitting nature so that we can employ a partially parallel splitting method (PPSM) to solve it efficiently. A series of numerical experiments on image restoration demonstrate that PPSM can recover slightly higher quality images than some existing algorithms in terms of taking less iterations or computing time in many cases.     

Progress of Air Pollution Control in China and Its Challenges and Opportunities in the Ecological Civilization Era

China’s past economic growth has substantially relied on fossil fuels, causing serious air pollution issues. Decoupling economic growth and pollution has become the focus in developing ecological civilization in China. We have analyzed the three-decade progress of air pollution controls in China, highlighting a strategic transformation from emission control toward air quality management. Emission control of sulfur dioxide (SO₂) resolved the deteriorating acid rain issue in China in 2007. Since 2013, control actions on multiple precursors and sectors have targeted the reduction of the concentration of fine particulate matter (PM_2.5), marking a transition to an air-quality-oriented strategy. Increasing ozone (O₃) pollution further requires O₃ and PM_2.5 integrated control strategies with an emphasis on their complex photochemical interactions. Fundamental improvement of air quality in China, as a key indicator for the success of ecological civilization construction, demands the deep de-carbonization of China’s energy system as well as more synergistic pathways to address air pollution and global climate change simultaneously.     

Ecological Planting Imperative: Functional Systems,Not Stylized Ecologies

The ability of landscape architectural projects to mitigate the worst effects of climate change will depend upon designed ecological systems. These systems will be built with plants. Despite the recognition of ecology as an essential driver of landscapes, the professionals of landscape architecture too often lack the knowledge and practical skills to create robust vegetative systems. New approaches and tools are required. This article outlines principles and methods for designing biodiverse plant systems for urban sites. Planting methods that increase species richness, functional diversity, and spatial complexity are emphasized as a way of developing more resilient plantings. Selecting species with similar evolutionary adaptions to stress, disturbance, and competition—as well as creating multi-layered compositions of diverse plant morphologies—allows designers to create compatible, long-lived plant mixes. To balance the increased visual complexity of diverse plant mixes, the article explores design techniques to make plantings more appealing to the public. The strategies explored here are based on the projects, experience, and research of Phyto Studio, a Washington, D.C. based studio. The methods build on work described in the author’s book, Planting in a Post-Wild World, an exploration of how to create designed plant communities.     

影视广告的生态伦理批评

数字媒体时代下,人们所看到的广告已经不再是单纯的平面化、实体化的户外印刷广告,更多的是以数字媒体为载体的互联网终端广告,影视广告就是典型的存在。为了博得大众眼球、达到广告宣传效果,部分影视广告在内容和形式表现上忽视了生态伦理价值。文章通过对案例分析得出在生态伦理意识上公益影视广告对比商业影视广告的优势,并提出解决商业影视广告生态伦理问题的方法与策略。     

Rescuing Big Rivers Damaged in Industrial Civilization

Large rivers with beautiful landscapes were dreamlands to the author. However, every time upon his arrival to riversides, he was shocked for the heavily polluted rivers that are dirty, messy, and smelling. Engineered dikes and dams made of concrete and steels for a greater height and hardness are built by cities along rivers. As more highways and railways built along rivers, vehicles run at a faster speed, scaring any life who wants to or has to access the water. Most of the tributaries are no longer free flow but end up as hard ditches and the water is polluted heavily. Forests and wetlands are being damaged and eroded. All of these are resulted from humans’ material desires and lack of respect for nature. Nevertheless, ecological civilization may encourage people to appreciate the beauty of nature and get a thorough understanding on river ecosystems and their services, accompanied by systematic planning and implementation of territorial ecological restoration. Moreover, laws and regulations on large river management should be put in place, and efforts should be made to break the worship of grey engineering approaches to flood control. It is expected that nature-based ecological approaches for a better resilience and sustainability in flood management can be more effective to ensure water safety.     

酸性尾矿废弃地生态修复技术进展

酸性尾矿废弃地废石含有硫化物，在雨水的淋溶作用下会产出硫酸，加剧废弃地的酸化，增加企业环保成本，而生态修复工作就是从源头上控制废弃地的酸化。根据尾矿废弃地酸化机理，结合国内外最新研究进展，分析了生态修复技术现状；概述了隔离覆盖、改良剂改良、植物修复、微生物法等多种处理方法在实践中的适应性及优缺点，并分别介绍了隔离覆盖-植物修复技术、原位改良-植物修复技术在Reden煤矿、永平铜矿的成功应用案例。针对酸性尾矿废弃地的特点，单一处理方法具有较大的局限性，需要采用联合工艺进行治理，隔离覆盖-植物修复技术、原位改良-植物修复技术因见效快、效果好、操作简单，势必成为将来研究的主要方向。     

问题意识与理性思辨的结晶--评刘文良《绿色与安全:生态包装设计论》

《绿色与安全:生态包装设计论》是当前少有的专门研究生态包装设计的学术专著。该著对于生态包装的概念、生态包装设计的困惑与对策、食品药品等重要民生品包装设计的安全策略、方法与技术等重要理论与实践问题进行了深入探讨,尤其在科学界定生态包装的内涵、理性思辨关于生态包装的某些不合理"常识"以及与时俱进的学术与实践视野方面取得了重要建树。其鲜明的问题意识、务实的研究思路、严谨的求真精神在这部学术专著中得到了印证,为生态包装设计指明了方向、提供了遵循,堪称一把打开生态包装设计大门的"金钥匙"。     

Application of fuzzy image restoration in criminal investigation

The advancement of science and technology has a positive effect on the development of law disciplines. The development of algorithms and artificial intelligence also has a certain impact on judicial practice. Image restoration is a significant technique in image processing. It aims to objectively restore the content or quality of the original image from the degraded image. Image degradation is always generated in image transmission, such as distortion, blur. In modern video surveillance system, image restoration is significant for criminal investigation. However, image restoration based on conventional filter algorithms cannot achieve satisfactory performance. Thus, we first introduce the image restoration algorithms based on different degradation model. Then, we propose some applications of fuzzy image restoration in criminal investigation. We conduct experiments on both degraded images and videos and experimental results have shown the effectiveness of fuzzy image restoration applying to the criminal investigation.     

自适应融合层级特征的混合退化图像复原算法

多种退化类型混合的图像比单一类型的退化图像降质更严重,很难建立精确模型对其复原,研究端到端的神经网络算法是复原的关键.现有的基于操作选择注意力网络的算法(operation-wiseattentionnetwork,OWAN)虽然有一定的性能提升,但是其网络过于复杂,运行较慢,复原图像缺乏高频细节,整体效果也有提升的空间.针对这些问题,提出一种基于层级特征融合的自适应复原算法.该算法直接融合不同感受野分支的特征,增强复原图像的结构;用注意力机制对不同层级的特征进行动态融合,增加模型的自适应性,降低了模型冗余;另外,结合L1损失和感知损失,增强了复原图像的视觉感知效果.在DIV2K,BSD500等数据集上的实验结果表明,该算法无论是在峰值信噪比和结构相似性上的定量分析,还是在主观视觉质量方面,均优于OWAN算法,充分证明了该算法的有效性.