Accurate wave component separation is essential for seismic signal processing, playing a key role in seismic source localization and dispersion curve inversion. However, traditional three-component polarization filters struggle to distinguish various wave components due to complex wave propagation and ambient noise. Current single-station six-component methods emphasize wave type identification but lack detailed time-frequency information, limiting their applicability in certain scenarios. To address these limitations, we present a novel algorithm that effectively isolates circularly polarized components using single-station six-component data, offering detailed polarization parameters across time and frequency domains. To validate our algorithm, we conducted a series of experiments, using back azimuth estimation as a key performance metric. Compared to the traditional 3-C method, the proposed algorithm reduces the mean absolute error by 79.81% and the standard deviation by 83.07%. These improvements demonstrate its superior accuracy in distinguishing various wave components and its enhanced convergence in back azimuth estimation. Additionally, it achieves comparable performance with shorter data while providing more time-frequency domain information. These results confirm the advanced capability of the algorithm to accurately isolate different wave components.

Few-shot font generation (FFG) aims to learn the target style from a limited number of reference glyphs and generate the remaining glyphs in the target font. Previous works focus on disentangling the content and style features of glyphs, combining the content features of the source glyph with the style features of the reference glyph to generate new glyphs. However, the disentanglement is challenging due to the complexity of glyphs, often resulting in glyphs that are influenced by the style of the source glyph and prone to artifacts. We propose IF-Font, a novel paradigm which incorporates Ideographic Description Sequence (IDS) instead of the source glyph to control the semantics of generated glyphs. To achieve this, we quantize the reference glyphs into tokens, and model the token distribution of target glyphs using corresponding IDS and reference tokens. The proposed method excels in synthesizing glyphs with neat and correct strokes, and enables the creation of new glyphs based on provided IDS. Extensive experiments demonstrate that our method greatly outperforms state-of-the-art methods in both one-shot and few-shot settings, particularly when the target styles differ significantly from the training font styles. The code is available at [https://github.com/Stareven233/IF-Font](https://github.com/Stareven233/IF-Font).

In this paper, we build a lightweight convolution neural network M-SOSAnet that combines efficiency and accuracy for edge devices. Just as DenseNet connects each layer to every other layer in the neural network. Although dense connection can effectively keep information between the middle layers, the increasing input channels by dense connection leads to resource consumption, which greatly increases the amount of parameters and is inefficient. MobileNet series use depthwise separable convolutions, which reduces the amount of calculation and parameters, but will reduce the accuracy. ESPnetv2 uses group pointwise and depthwise dilated separable convolution to learn representation from a large receptive field with fewer flops and parameters but will get a little accuracy decrease. In order to solve these problems, we propose two module: 1. Mobile SOSA Module 2. Downsampling Block with scoring mechanism, and also introduce the attention mechanism. Compare to some past methods, our model M-SOSAnet has lower flops, higher accuracy, maintains the similar amount of parameters. We evaluated model in the areas of image classification, and semantic segmentation to prove that our methods have better performance.