In this paper, we further study the dynamic characteristics of the Yu–Wang chaotic system obtained by Yu and Wang in 2012. The system can show a four-wing chaotic attractor in any direction, including all 3D spaces and 2D planes. For this reason, our interest is focused on multistability generation and chaotic FPGA implementation. The stability analysis, bifurcation diagram, basin of attraction, and Lyapunov exponent spectrum are given as the methods to analyze the dynamic behavior of this system. The analyses show that each system parameter has different coexistence phenomena including coexisting chaotic, coexisting stable node, and coexisting limit cycle. Some remarkable features of the system are that it can generate transient one-wing chaos, transient two-wing chaos, and offset boosting. These phenomena have not been found in previous studies of the Yu–Wang chaotic system, so they are worth sharing. Then, the RK4 algorithm of the Verilog 32-bit floating-point standard format is used to realize the autonomous multistable 4D Yu–Wang chaotic system on FPGA, so that it can be applied in embedded engineering based on chaos. Experiments show that the maximum operating frequency of the Yu–Wang chaotic oscillator designed based on FPGA is 161.212 MHz.

Image captioning aims to generate a corresponding description of an image. In recent years, neural encoder-decoder models have been the dominant approaches, in which the Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM) are used to translate an image into a natural language description. Among these approaches, the visual attention mechanisms are widely used to enable deeper image understanding through fine-grained analysis and even multiple steps of reasoning. However, most conventional visual attention mechanisms are based on high-level image features, ignoring the effects of other image features, and giving insufficient consideration to the relative positions between image features. In this work, we propose a Position-Aware Transformer model with image-feature attention and position-aware attention mechanisms for the above problems. The image-feature attention firstly extracts multi-level features by using Feature Pyramid Network (FPN), then utilizes the scaled-dot-product to fuse these features, which enables our model to detect objects of different scales in the image more effectively without increasing parameters. In the position-aware attention mechanism, the relative positions between image features are obtained at first, afterwards the relative positions are incorporated into the original image features to generate captions more accurately. Experiments are carried out on the MSCOCO dataset and our approach achieves competitive BLEU-4, METEOR, ROUGE-L, CIDEr scores compared with some state-of-the-art approaches, demonstrating the effectiveness of our approach.

With the development of Internet technology, deepfake (DF) videos can spread rapidly through online platforms, providing a new way of cyberbullying by generating nude pictures of female victims and using their faces to generate pornographic movies, which bring potential harm to individuals, society, and the country. Recently, there have been some really impressive results with DF detection models. These models have shown excellent outstanding performance when they are trained and tested using data from the same dataset. However, detecting DF remains difficult when the data comes from challenging datasets. To address this issue, this article aims to enhance the model’s generalization by taking full advantage of the learning and representation capabilities of convolutional neural networks (CNNs) to adaptively suppress image texture information and catch deeper and more universal forgery features. Specifically, we introduce the texture suppression module (TSM) as a first step to suppress image content while simultaneously revealing the differences between authentic and tampered regions. Then, we carefully designed the cross stream interaction module (CSIM) and the cross stream mix block (CSMB) module to fully exploit the extracted forgery traces. Our proposed model has demonstrated superior generalization performance in extensive experiments.