Search

The Face Anti-Spoofing (FAS) methods plays a very important role in ensuring the security of face recognition systems. The existing FAS methods perform well in short-distance scenarios, e.g., phone unlocking, face payment, etc. However, it is still challenging to improve the generalization of FAS in long-distance scenarios (e.g., surveillance) due to the varying image quality. In order to address the lack of low-quality images in real scenarios, we build a Low-Quality Face Anti-Spoofing Dataset (LQFA-D) by using Hikvision's surveillance cameras. In order to deploy the model on an edge device with limited computation, we propose a lightweight FAS network based on MobileFaceNet, in which the Coordinate Attention (CA) attention model is introduced to capture the important spatial information. Then, we propose a multi-scale FAS framework for low-quality images to explore multi-scale features, which includes three multi-scale models. The experimental results of the LQFA-D show that the Average Classification Error Rate (ACER) and detection time of the proposed method are 1.39% and 45 ms per image for the low-quality images, respectively. It demonstrates the effectiveness of the proposed method in this paper. [ABSTRACT FROM AUTHOR]

Face recognition technology has been widely used with the WeChat applet on mobile devices; however, facial images are captured on mobile devices and then transmitted to a server for feature extraction and recognition in most existing systems. There are significant security risks related to personal information leakage with these transmissions. Therefore, we propose a face recognition framework for the WeChat applet in which face features are extracted in WeChat by the proposed Face Feature Extraction Model based on Attention Mechanism (FFEM-AM), and only the extracted features are transmitted to the server for recognition. In order to balance the prediction accuracy and model complexity, the structure of the proposed FFEM-AM is lightweight, and Efficient Channel Attention (ECA) was introduced to improve the prediction accuracy. The proposed FFEM-AM was evaluated using a self-built database and the WeChat applet on mobile devices. The experiments show that the prediction accuracy of the proposed FFEM-AM was 98.1%, the running time was less than 100 ms, and the memory cost was only 6.5 MB. Therefore, this demonstrates that the proposed FFEM-AM has high prediction accuracy and can also be deployed with the WeChat applet. [ABSTRACT FROM AUTHOR]

The uncertain responses of aboveground net primary productivity (ANPP) and plant diversity to climate warming and increased precipitation will limit our ability to predict changes in vegetation productivity and plant diversity under future climate change and further constrain our ability to protect biodiversity and ecosystems. A long-term experiment was conducted to explore the responses of ANPP, plant species, phylogenetic α–diversity, and community composition to warming and increased precipitation in an alpine meadow of the Northern Tibet from 2014 to 2019. Coverage, height, and species name were obtained by conventional community investigation methods, and ANPP was obtained using observed height and coverage. Open–top chambers with two different heights were used to simulate low- and high-level climate warming. The low- and high-level increased precipitation treatments were achieved by using two kinds of surface area funnel devices. The high-level warming reduced sedge ANPP (ANPPsedge) by 62.81%, species richness (SR) by 21.05%, Shannon by 13.06%, and phylogenetic diversity (PD) by 14.48%, but increased forb ANPP (ANPPforb) by 56.65% and mean nearest taxon distance (MNTD) by 33.88%. Species richness, Shannon, and PD of the high-level warming were 19.64%, 9.67%, and 14.66% lower than those of the low-level warming, respectively. The high-level warming-induced dissimilarity magnitudes of species and phylogenetic composition were greater than those caused by low-level warming. The low- rather than high-level increased precipitation altered species and phylogenetic composition. There were significant inter-annual variations of ANPP, plant species, phylogenetic α–diversity and community composition. Therefore, climate warming and increased precipitation had non-linear effects on ANPP and plant diversity, which were due to non-linear changes in temperature, water availability, and/or soil nutrition caused by warming and increased precipitation. The inter-annual variations of ANPP and plant diversity were stronger than the effects of warming and especially increased precipitation on ANPP and plant diversity. In terms of plant diversity conservation and related policy formulation, we should pay more attention to regions with greater warming, at least for the northern Tibet grasslands. Besides paying attention to the responses of ANPP and plant diversity to climate change, the large inter-annual changes of ANPP and plant diversity should be given great attention because the large inter-annual variation indicates the low temporal stability of ANPP and plant diversity and thus produces great uncertainty for the development of animal husbandry. [ABSTRACT FROM AUTHOR]

Quantifying the impact of climate change and vegetation phenology on ecosystem productivity in the alpine grasslands of the Tibetan Plateau (TP) is essential for assessing carbon balance dynamics at regional and global scales. However, the relative contributions of climate change and phenological change to vegetation productivity across various grassland types remain indistinguishable. This study examined the effects of climate change and phenological change on net primary productivity (NPP) in the alpine meadow and alpine steppe ecosystems of the TP from 2001 to 2020. The results revealed that (1) NPP exhibited a positive correlation with vegetation phenology, particularly with an extended growing season length and an earlier start of the growing season. Among the phenological variables studied, changes in the start of the growing season had the strongest influence on NPP variations in both alpine meadows and alpine steppes. (2) NPP displayed a positive correlation with annual precipitation and annual temperature, with changes in annual precipitation playing a dominant role in shaping NPP variations in alpine steppes. (3) NPP showed a negative correlation with annual radiation, and the impact of radiation changes on NPP variations was comparable to that of precipitation or temperature in both alpine meadows and alpine steppes. (4) Climate change exerted a stronger impact on NPP than phenological change in alpine steppes, while NPP was jointly affected by climate change and phenological change in alpine meadows. Our findings indicated that the relative effects of climate change and phenological change on vegetation productivity vary across different grassland types on the TP. [ABSTRACT FROM AUTHOR]

The soil fungal community plays a crucial role in terrestrial decomposition and biogeochemical cycles. However, the responses of the soil fungal community to short-term nitrogen addition and its related dominant drivers still remain unclear. To address this gap, we conducted an experiment to explore how different levels of nitrogen addition (five levels: 0, 2.5, 5, 10, and 20 g N m−2 y−1) affected the soil fungal community in an alpine steppe at the source of Brahmaputra. Results showed that the reduced magnitudes of soil fungal species and phylogenetic α-diversity increased with the increasing nitrogen addition rate. Nitrogen addition significantly changed the community composition of species, and the dissimilarity of the soil fungal community increased with the increasing nitrogen addition rate, with a greater dissimilarity observed in the superficial soil (0–10 cm) compared to the subsurface soil (10–20 cm). Increases in the soil nitrogen availability were found to be the predominant factor in controlling the changes in the soil fungal community with the nitrogen addition gradient. Therefore, short-term nitrogen addition can still cause obvious changes in the soil fungal community in the alpine grassland at the source of Brahmaputra. We should not underestimate the potential influence of future nitrogen deposition on the soil fungal community in the high-altitude grassland of the Qinghai–Tibet Plateau. Adverse effects on the soil fungal community should be carefully considered when nitrogen fertilizer is used for ecosystem restoration of the alpine grassland of the Qinghai–Tibet Plateau. [ABSTRACT FROM AUTHOR]

To mine the cobalt-rich crust deposits at the substrate of the slope of the seamount, the mining vehicle needs to walk on the slope and strip the cobalt-rich crust from the substrate. To achieve safety and control, the vehicle needs to stably walk on the slope. In this paper, we propose a modeling method for mining vehicle performance based on slope stability and antislip and antiskid conditions. The specific energy of three types of mining vehicles is compared based on dimensionless parameters. The dual-drum type is determined to be the best choice in terms of energy costs, followed by the down-milling type. The performance of the compact mining vehicle based on different slope angles and two sea trial results in the South China Sea indicate that the slope angle, substrate, and crust have significant effects on the stability. The modeling method proposed in this paper can help designers estimate the structure and power of mining vehicles based on mining stability. [ABSTRACT FROM AUTHOR]