Search

Crowd counting based on convolutional neural networks (CNNs) has made significant progress in recent years. However, the limited receptive field of CNNs makes it challenging to capture global features for comprehensive contextual modeling, resulting in insufficient accuracy in count estimation. In comparison, vision transformer (ViT)-based counting networks have demonstrated remarkable performance by exploiting their powerful global contextual modeling capabilities. However, ViT models are associated with higher computational costs and training difficulty. In this paper, we propose a novel network named JMFEEL-Net, which utilizes joint multi-scale feature enhancement and lightweight transformer to improve crowd counting accuracy. Specifically, we use a high-resolution CNN as the backbone network to generate high-resolution feature maps. In the backend network, we propose a multi-scale feature enhancement module to address the problem of low recognition accuracy caused by multi-scale variations, especially when counting small-scale objects in dense scenes. Furthermore, we introduce an improved lightweight ViT encoder to effectively model complex global contexts. We also adopt a multi-density map supervision strategy to learn crowd distribution features from feature maps of different resolutions, thereby improving the quality and training efficiency of the density maps. To validate the effectiveness of the proposed method, we conduct extensive experiments on four challenging datasets, namely ShanghaiTech Part A/B, UCF-QNRF, and JHU-Crowd++, achieving very competitive counting performance. [ABSTRACT FROM AUTHOR]

Arsenic pollution poses a serious threat to human health, and is one of the most concerning environmental problems worldwide. The adsorption, fixation, and dissolution behaviors of arsenic on the surface of iron-(hydr-) oxides influence the environmental routes of arsenic cycle geochemistry. Both inner-sphere and outer-sphere adsorption configurations of arsenic on iron oxides have been proposed based on X-ray adsorption spectra. However, there is no systematic study on the in situ speciation analysis and adsorption kinetics of these species at such interfaces, because of the lack of an efficient monitoring strategy. The correlation of surface speciation and environmental stability is still unknown. Here, a shell-isolated SiO2@Ag@Au-based surface-enhanced Raman spectroscopy (SERS) platform was developed for speciation analysis of the adsorbed arsenic species by eliminating the chemical interaction between arsenic and silver. Using ferrihydrite as a typical iron oxide, the intrinsic Raman spectra of the inner-sphere (∼ 830 cm−1) and outer-sphere (∼ 660 cm−1) complexes at the adsorption interface were identified. For the first time, the in situ kinetic monitoring of the formation and transformation of these species was realized. By correlating the speciation to the sequential extraction results, the environmental stability of arsenic on ferrihydrite was shown to be closely related to the adsorption configuration. It was shown that stability can be significantly promoted by transforming loosely bonded species (outer-sphere complexes) into inner-sphere structures. Our work demonstrated the applicability of SERS with shell-isolated plasmonic particles for arsenic geochemical cycle monitoring and mechanism studies. It also provided a convenient tool for developing effective strategies for arsenic pollutant control and abatement. [ABSTRACT FROM AUTHOR]

Electrochemical degradation behavior of thermally oxidized pure Ti in the fluoride-containing acidic environments was investigated. Compact TiO2 oxides with acceptable hardness and superior corrosion resistance are formed through the thermal oxidation at 650 °C for 24 h. Corrosion of the oxidized Ti depends on the oxidation condition and fluoride content, resulting in the various interfacial structures at the oxide/solution and metal/solution interface. Degradation of the oxidized Ti consists of three stages during long-term immersion, while its critical fluoride concentration is increased by 1~2 orders of magnitude, attributed to the high stability of the TiO2 thermal oxides. [ABSTRACT FROM AUTHOR]

The effect of the aging treatment process on the microstructure and properties of 7050T451 aluminum alloy plates was investigated. The microstructural evolution and the variety of properties of 7050T451 aluminum alloy with different aging times were analyzed by means of optical microscopy, energy dispersive X-ray spectroscopy, transmission electron microscopy, and measuring of tensile properties and Vickers hardness. The results show that the aging process had little influence on the grain size and nonuniform ω phase of 7050T451 alloy. At the early stage of the aging process at 433 K (160 °C), the redissolution of the GP zone and the precipitation of $$ {{\eta}}\prime $$ phase led to the increase of strength and hardness. And, the transition of $$ {{\eta}}\prime $$ to $$ {{\eta}} $$ and coarsening of $$ {{\eta}}\prime $$ made the properties of the material decrease gradually to a minimum with the increase of aging time. Then, the abundant redissolution of the GP zone and the continuative precipitation of $$ {{\eta}}\prime $$ phase induced the strength and hardness of 7050T451 alloy to improve gradually. During the aging process, intergranular precipitates coarsened and became discontinuous with the increase of aging time, and the width of the precipitation-free zone also increased. [ABSTRACT FROM AUTHOR]