Search

In this study, we proposed the preparation of phosphate composite coatings (LSPCs) using a Fe3O4/hexagonal boron nitride (h-BN) hybrid, where the ordered dispersion and orientation of h-BN was achieved through a weak magnetic field. The evolution of the physiochemical structure of Fe3O4/h-BN before and after the modification was investigated by FTIR, XRD, XPS, TEM, SEM, and EDS. In addition, the corrosion protection performance of LSPCs was evaluated by electrochemical tests combining the analysis of the microstructure and phase characterization. Results indicate that the nano-Fe3O4 particles are successfully deposited on the surface of h-BN after modification. In addition, electrochemical results confirm that the corrosion protection performance of the layered phosphate composite coating is higher than that of the randomly dispersed coating. That is because the layered structure promotes the densification of the phosphate composite coating, thus delaying the permeation of corrosive media and makes the coatings more protective. [ABSTRACT FROM AUTHOR]

Action recognition has found extensive applications in fields such as video classification and security monitoring. However, existing action recognition methods, such as those based on 3D convolutional neural networks, often struggle to capture comprehensive global information. Meanwhile, transformer-based approaches face challenges associated with excessively high computational complexity. We introduce a Multi-Scale Video Longformer network (MSVL), built upon the 3D Longformer architecture featuring a "local attention + global features" attention mechanism, enabling us to reduce computational complexity while preserving global modeling capabilities. Specifically, MSVL gradually reduces the video feature resolution and increases the feature dimensions across four stages. In the lower layers of the network (stage 1, stage 2), we leverage local window attention to alleviate local redundancy and computational demands. Concurrently, global tokens are employed to retain global features. In the higher layers of the network (stage 3, stage 4), this local window attention evolves into a dense computation mechanism, enhancing overall performance. Finally, extensive experiments are conducted on UCF101 (97.6%), HMDB51 (72.9%), and the assembly action dataset (100.0%), demonstrating the effectiveness and efficiency of the MSVL. [ABSTRACT FROM AUTHOR]