Heterogeneous face recognition (HFR), referring to matching face images across different domains, is a challenging problem due to the vast cross-domain discrepancy and insufficient pairwise cross-domain training data. This paper proposes a quadruplet framework for learning domain-invariant discriminative features (DIDF) for HFR, which integrates domain-level and class-level alignment in one unified network. The domain-level alignment reduces the cross-domain distribution discrepancy. The class-level alignment based on a special quadruplet loss is developed to further diminish the intra-class variations and enlarge the inter-class separability among instances, thus handling the misalignment and adversarial equilibrium problems confronted by the domain-level alignment. With a bidirectional cross-domain data selection strategy, the quadruplet loss-based method prominently enriches the training set and further eliminates the cross-modality shift. Benefiting from the joint supervision and mutual reinforcement of these two components, the domain invariance and class discrimination of identity features are guaranteed. Extensive experiments on the challenging CASIA NIR-VIS 2.0 database, the Oulu-CASIA NIR&VIS database, the BUAA-VisNir database, and the IIIT-D viewed sketch database demonstrate the effectiveness and preferable generalization capability of the proposed method.

Extreme precipitation events greatly threaten people's daily lives and safety, making accurate and timely precipitation estimation especially critical. However, common methods like radar and satellite remote sensing have limitations due to coverage and environmental factors. Existing deep learning models struggle with complex scenarios and multi-source data correlations. These make the precipitation estimation tasks chal lenging. This paper proposes a Multi-Scale-Dual-Cross-Attention-UNet (MS-DCA-UNet) model for near-real-time precipitation estimation. It integrates Doppler weather radar and FY-4A satellite data to overcome single-source data limitations. To narrow the semantic gap among the encoder feature maps, the MS-DCA-UNet model introduces a Dual-Cross Attention (DCA) module at the skip connections of the backbone network U-Net. The DCA module mainly employs a Channel Cross-Attention (CCA) and a Spatial Cross-Attention (SCA) to capture remote dependencies and enable multi-scale feature fusion. A Multi-Scale Convolution (MSC) module is designed to reduce the risk of the model falling into local optima. It is a multi-branch upsampling strategy that runs parallel to the decoder. Experimental results show that the Critical Success Index (CSI), Root Mean Square Error (RMSE), and Pearson's Correlation Coefficient (CC) of MS-DCA-UNet are 0.6033, 0.5949 mm/h, and 0.8460, respectively, with the hourly CMPAS precipitation as the benchmark. These outperform the other comparisons, such as FY-4A QPE, GPM IMERG, U-Net, Attention-UNet, and DCA-UNet on the CSI, RMSE, and CC metrics. MS-DCA-UNet reduces the RMSE of Attention-UNet, UNet, and DCA-UNet by a margin of 34.68% (0.5949 mm/h vs. 0.9107 mm/h), 10.24%(0.5949 mm/h vs. 0.6628 mm/h), 6.96% (0.5949 mm/h vs. 0.6394 mm/h), respectively.

Near-surface air temperature is a crucial weather parameter that significantly impacts human health and is widely utilized in numerical weather forecasting and climate prediction studies. However, the most common ground-based meteorological station observation and radar observation are often limited by geographic and natural constraints. With the advantages of global coverage and high spatiotemporal resolution, satellite remote sensing has become a valuable support in overcoming data scarcity issues related to ground-based station and radar observations in complex geographic and natural conditions. Although remote sensing indirectly reflects atmosphere variables (e.g., near-surface air temperature), accurately estimating the atmosphere variables through satellite remote sensing remains a significant challenge. This paper introduces a deep learning Transformer-based neural network (TaNet) for near-surface air temperature estimation. TaNet automatically extracts information from imageries captured by China's new-generation geostationary meteorological satellite FengYun-4A and generates grid near-surface air temperature data in near real-time. Extensive experiments conducted using the state-of-the-art operational reanalysis product ERA5 and meteorological station observations as benchmark standards demonstrate the effectiveness and superiority of TaNet. It achieves an impressive Pearson's correlation coefficient (CC) of 0.990 with ERA5 and 0.959 with station observations, outperforming the other products, such as CFSv2, CRA, and U-Net, on root mean square error (RMSE) and CC metrics. TaNet reduces the RMSE of CFSv2, CRA, and U-Net by a margin of 10.551% (2.594 ${}^{\circ }\mathrm{C}$ vs. 2.900 ${}^{\circ }\mathrm{C}$ ), 2.261% (2.594 ${}^{\circ }\mathrm{C}$ vs. 2.654 ${}^{\circ }\mathrm{C}$ ), and 5.535% (2.594 ${}^{\circ }\mathrm{C}$ vs. 2.746 ${}^{\circ }\mathrm{C}$ ), respectively, using station observations as the benchmark.

Recent studies on deepfake detection have achieved promising results when training and testing faces are from the same dataset. However, their results severely degrade when confronted with forged samples that the model has not yet seen during training. In this paper, deepfake data to help detect deepfakes. this paper present we put a new insight into diffusion model-based data augmentation, and propose a Masked Conditional Diffusion Model (MCDM) for enhancing deepfake detection. It generates a variety of forged faces from a masked pristine one, encouraging the deepfake detection model to learn generic and robust representations without overfitting to special artifacts. Extensive experiments demonstrate that forgery images generated with our method are of high quality and helpful to improve the performance of deepfake detection models.

Data representation has been one of the core topics in 3D graphics and pattern recognition in high-dimensional data. Although the high-resolution geometrical information of a physical object can be well preserved in the form of metrical data, e.g., point clouds/triangular meshes, from a regular data (e.g., image/audio) processing perspective, they also bring excessive noise in the course of feature abstraction and regression. For 3D face recognition, preceding attempts focus on treating the scan samples as signals laying on an underlying discrete surface (mesh) or morphable (statistic) models and by embedding auxiliary information, e.g., texture onto the regularized local planar structure to obtain a superior expressive performance to registration-based methods, but environmental variations such as posture/illumination will dissatisfy the integrity or uniform sampling condition, which holistic models generally rely on. In this paper, a geometric deep learning framework for face recognition is proposed, which merely requires the consumption of raw spatial coordinates. The non-uniformity and non-grid geometric transformations in the course of point cloud face scanning are mitigated by modeling each identity as a stochastic process. Individual face scans are considered realizations, yielding underlying inherent distributions under the appropriate assumption of ergodicity. To accomplish 3D facial recognition, we propose a windowed solid harmonic scattering transform on point cloud face scans to extract the invariant coefficients so that unrelated variations can be encoded into certain components of the scattering domain. With these constructions, a sparse learning network as the semi-supervised classification backbone network can work on reducing intraclass variability. Our framework obtained superior performance to current competing methods; without excluding any fragmentary or severely deformed samples, the rank-1 recognition rate (RR1) achieved was $99.84\%$ on the Face Recognition Grand Challenge (FRGC) v2.0 dataset and $99.90\%$ on the Bosphorus dataset.