Graph convolutional network (GCN) as a combination of deep learning and graph learning has gained increasing attention in hyperspectral image (HSI) classification. However, most GCN methods consider the simple point-to-point structure between two pixels rather than the high-order structure of multiple pixels, which is contradict with the real feature distribution of ground object. And the nonlinear property of HSI also brings challenge for precise structural representation in GCN. To tackle these problems, this work proposes a structure preserved hypergraph convolution network (SPHGCN). It first builds a multiple neighborhood reconstruction (MNR) model to reveal the essential resemblance of multiple pixels in nonlinear spectral feature space. With the high-order structure, SPHGCN designs the hypergraph convolution operation for irregular feature aggregation among similar pixels from different regions, which achieves more discriminative features from multiple pixel nodes. Meanwhile, a structure preservation layer is built to optimize the distribution of convolutional features under the guidance of high-order structure. Moreover, SPHGCN integrates local regular convolution and irregular hypergraph convolution to learn the structured semantic feature of HSI. This strategy breaks the boundary restriction in traditional convolution and aggregates semantic feature across different image patches. Experiments on three HSI data sets indicate that SPHGCN outperforms a few state-of-the-art methods for HSI classification.

Infrared small target detection plays a vital role in remote sensing, industrial monitoring, and various civilian applications. Despite recent progress powered by deep learning, many end-to-end convolutional models tend to pursue performance by stacking increasingly complex architectures, often at the expense of interpretability, parameter efficiency, and generalization. These models typically overlook the intrinsic sparsity prior of infrared small targets–an essential cue that can be explicitly modeled for both performance and efficiency gains. To address this, we revisit the model-based paradigm of Robust Principal Component Analysis (RPCA) and propose Dynamic RPCA Network (DRPCA-Net), a novel deep unfolding network that integrates the sparsity-aware prior into a learnable architecture. Unlike conventional deep unfolding methods that rely on static, globally learned parameters, DRPCA-Net introduces a dynamic unfolding mechanism via a lightweight hypernetwork. This design enables the model to adaptively generate iteration-wise parameters conditioned on the input scene, thereby enhancing its robustness and generalization across diverse backgrounds. Furthermore, we design a Dynamic Residual Group (DRG) module to better capture contextual variations within the background, leading to more accurate low-rank estimation and improved separation of small targets. Extensive experiments on multiple public infrared datasets demonstrate that DRPCA-Net significantly outperforms existing state-of-the-art methods in detection accuracy. Code is available at https://github.com/GrokCV/DRPCA-Net.

A tunable dual-band terahertz sensor based on graphene is proposed. The sensor consists of a metal bottom layer, a middle dielectric layer, and single-layer graphene patterned with four strips on the top. The numerical simulations results show that the proposed sensor exhibits two significant absorption peaks at 2.58 THz and 6.07 THz. The corresponding absorption rates are as high as nearly 100% and 98%, respectively. The corresponding quality factor (Q) value is 11.8 at 2.58 THz and 29.6 at 6.07 THz. By adjusting the external electric field or chemical doping of graphene, the positions of the dual-frequency resonance peak can be dynamically tuned. The excitation of plasma resonance in graphene can illustrate the mechanism of the sensor. To verify the practical application of the device, the terahertz response of different kinds and different thicknesses of the analyte is investigated and analyzed. A phenomenon of obvious frequency shifts of the two resonance peaks can be observed. Therefore, the proposed sensor has great potential applications in terahertz fields, such as material characterization, medical diagnosis, and environmental monitoring.

A polarization-insensitive broadband terahertz absorber with a sandwich structure of metal–dielectric-graphene is designed and simulated. The graphene is patterned as an array of graphene square blocks with circular apertures. The results of the simulations and theoretical analysis show that the absorption exceeds $99\%$ from $0.93\mathrm{to}1.65\mathrm{THz}$ while $90\%$ from $0.80\mathrm{to}1.87\mathrm{THz}$, and a broad relative bandwidth of 80.2% is achieved. The absorption performance is passively enhanced by altering physical dimensions of the graphene pattern and actively adjusted by changing the chemical potential of graphene. When the chemical potential increases from $0.1 \mathrm{eV}$ to $0.7 \mathrm{eV}$, the corresponding terahertz absorption increases from $59.1\%$ to $99\%$. The mechanism of absorption is disclosed by analyzing the impedance matching theory and distribution of electric-field intensity. In addition, different polarization modes and incident angles are also studied. The proposed absorber has the superiorities of broad relative bandwidth, high absorption rate, polarization insensitivity, and a wide incident angle, which offers some potential applications in the field of terahertz technology such as imaging, detection, and cloaking.

Infrared small target detection is crucial for the efficacy of infrared search and tracking systems. Current tensor decomposition methods emphasize representing small targets with sparsity but struggle to separate targets from complex backgrounds due to insufficient use of intrinsic directional information and reduced target visibility during decomposition. To address these challenges, this study introduces a Sparse Differential Directionality prior (SDD) framework. SDD leverages the distinct directional characteristics of targets to differentiate them from the background, applying mixed sparse constraints on the differential directional images and continuity difference matrix of the temporal component, both derived from Tucker decomposition. We further enhance target detectability with a saliency coherence strategy that intensifies target contrast against the background during hierarchical decomposition. A Proximal Alternating Minimizationbased (PAM) algorithm efficiently solves our proposed model. Experimental results on several real-world datasets validate our method’s effectiveness, outperforming ten state-of-the-art methods in target detection and clutter suppression. Our code is available at https://github.com/GrokCV/SDD.

Local collaborative representation (CR) has drawn much attention in exploring data relationships due to considering local knowledge in the global linear combination, subsequently, local CR-based graph embedding methods have been applied to dimensionality reduction of hyperspectral image (HSI). However, HSI data with nonlinear distribution cannot be handled with pure linear combination accurately. Furthermore, the existing local knowledge in terms of binary relations between pairwise neighbors makes it hard to learn the accurate local structure among neighborhood sets through local CR-based graph embedding. To this end, this paper proposes a novel multiple neighborhood-aware nonlinear collaborative analysis (MNNCA) method. Relying on the primary and secondary neighborhoods, a dual-level neighborhood reconstruction is designed to search for optimal neighbors and mine the common attributes within the neighborhood. With the reconstruction information, a nonlinear extend multiple neighborhood-aware collaborative representation (NE-MNACR) model is built on nonlinear geodesic constraint and multi-neighborhood-aware items. It can explore the collaborative relationship among multiple neighborhood sets in the nonlinear space of HSI data. By preserving the multivariate local structure instead of pairwise local relations, a pair of collaborative structure preservation graphs are constructed to realize the final embedding of HSI data. Experimental results on serval HSI data sets demonstrate the superior performance of the proposed MNNCA method and NE-MNACR model in comparison with some state-of-the-art DR methods and local CR models.