Cloud image prediction is a spatio-temporal sequence prediction task, similar to video prediction. Spatio-temporal sequence prediction involves learning from historical data and using the learned features to generate future images. In this process, the changes in time and space are crucial for spatio-temporal sequence prediction models. However, most models now rely on stacking convolutional layers to obtain local spatial features. In response to the complex changes in cloud position and shape in cloud images, the prediction module of the model needs to be able to extract both global and local spatial features from the cloud images. In addition, for irregular cloud motion, more attention should be paid to the spatio-temporal sequence features between input cloud image frames in the temporal sequence prediction module, considering the extraction of temporal features with long temporal dependencies, so that the spatio-temporal sequence prediction network can learn cloud motion trends more accurately. To address these issues, we have introduced an innovative model called SAM-Net. The self-attention module of this model aims to extract an inner image frame’s spatial features of global and local dependencies. In addition, a memory mechanism has been added to the self-attention module to extract interframe features with long temporal and spatial dependencies. Our method shows better performance than the PredRNN-v2 model on publicly available datasets such as MovingMNIST and KTH. We achieved the best performance in both the 4-time-step and 10-time-step typhoon cloud image predictions. On a cloud dataset consisting of 10 time steps, we observed a decrease in MSE of 180.58, a decrease in LPIPS of 0.064, an increase in SSIM of 0.351, and a significant improvement in PSNR of 5.56 compared to PredRNN-v2.

Although deep networks-based 3D reconstruction methods can recover the 3D geometry given few inputs, they may produce unfaithful reconstruction when predicting occluded parts of 3D objects. To address the issue, we propose Detail-Enhanced Generative Adversarial Network (DEGAN) which consists of Encoder–Decoder-Based Generator (EDGen) and Voxel-Point Embedding Network-Based Discriminator (VPDis) for 3D reconstruction from a monocular depth image of an object. Firstly, EDGen decodes the features from the 2.5D voxel grid representation of an input depth image and generates the 3D occupancy grid under GAN losses and a sampling point loss. The sampling loss can improve the accuracy of predicted points with high uncertainty. VPDis helps reconstruct the details under voxel and point adversarial losses, respectively. Experimental results show that DEGAN not only outperforms several state-of-the-art methods on both public ModelNet and ShapeNet datasets but also predicts more reliable occluded/missing parts of 3D objects.

Facial micro-expressions (MEs) are caused by brief and subtle movements of facial muscles, revealing a person's genuine emotions and offering valuable insights into lie detection, criminal analysis, and numerous human-computer interaction systems. Although deep learning-based micro-expression recognition (MER) approaches have achieved significant success, these methods often incorporate identity information that adversely impacts facial expression recognition and ignore capturing the synergistic interactions among different motion regions. To overcome these limitations, this paper proposes PME-MER, a novel MER method capable of effectively encoding facial position information and capturing muscle motion patterns. Specifically, we introduce Adaptive Positional and Local Motion Encoding (APME), a single-stream framework using cross-attention to align motion features with facial structure, facilitating accurate position calibration and minimizing the impact of identity information. Furthermore, we develop Collaborative Motion Encoding (CME), which utilizes self-attention and the top-k mechanism to explore the synergistic relationships among various facial regions, capturing comprehensive facial muscle movement information while reducing the impact of irrelevant regions on model predictions. Experimental results on four benchmark datasets demonstrate that our method significantly outperforms state-of-the-art methods, and ablation studies further demonstrate the effectiveness of our method.

Due to the constraints posed by the complexity and vast amounts of geospatial data, achieving fine-grained drought geospatial interpolation using sparse observation points has always been a challenging problem. Therefore, to solve the problem, this letter proposes a new model called Geographical Attention Conditional Neural Processes (GACNPs) that extends Spatial Multi-Attention Conditional Neural Processes (SMACNPs). GACNPs as a type of probabilistic model, inherit the flexibility of neural networks in parameterizing stochastic processes. We design a geographic information embedding module by measuring the geographic information correlation between known observation points and target points, thereby better capturing the complexities in spatial data. Considering that real-world data distributions often do not conform to Gaussian distributions, we propose a nonlinear mapping module to handle those more complex distributions that cannot be expressed by Gaussian assumptions, such as multimodal distributions. We utilize MODIS satellite to obtain remote sensing indices with 1 km spatial resolution and integrating these with meteorological drought indices derived from ground weather stations for multi-source data fusion, we conducted an experimental analysis of drought disaster situation in Yunnan Province. Our study demonstrates that the use of GACNPs outperforms traditional methods and other neural network approaches in terms of spatial interpolation accuracy. This improvement facilitates more precise meteorological drought monitoring tasks.