PSA-HWT: handwritten font generation based on pyramid squeeze attention.

The generator, which combines convolutional neural network (CNN) and Transformer as its core modules, serves as the primary model for the handwriting font generation network and demonstrates effective performance. However, there are still problems with insufficient feature extraction in the overall structure of the font, the thickness of strokes, and the curvature of strokes, resulting in subpar detail in the generated fonts. To solve the problems, we propose a method for constructing a handwritten font generation model based on Pyramid Squeeze Attention, called PSA-HWT.

Temporal-spatial distribution of synthetic pyrethroids in overlying water and surface sediments in Guangzhou waterways: potential input mechanisms and ecological risk to aquatic systems.

Temporal-spatial distribution of synthetic pyrethroids (SPs) in overlying water and surface sediments and ecological risk to aquatic systems were investigated, where paired water and surface sediments were collected during dry and wet periods in Guangzhou urban waterways. Eight target SPs (i.e.