Search Results (1,714)

Accurate cloud detection remains a significant challenge due to the spectral ambiguity between clouds and bright or heterogeneous surfaces (e.g., snow, desert). While multi-angle and polarization data offer rich information, the discriminative power of joint spectral analysis for resolving these ambiguities has been underexploited. In this work, we demonstrate that physically motivated spectral band ratios and differences can robustly enhance cloud signatures. Motivated by this insight, we propose a novel deep learning framework, the Multi-angle Polarization Feature Pyramid Structure (MP-FPS), that explicitly leverages joint spectral features as discriminative priors. Our architecture employs a dual-branch network to disentangle and adaptively fuse spectral and multi-angle polarization modalities. Within this framework, a hierarchical, multi-scale cross-channel multi-angle fusion module dynamically captures spatial–spectral–angular dependencies, enriching the structural representation of clouds. Furthermore, a channel-space dual-path attention mechanism refines sub-pixel responses, significantly improving detection accuracy in challenging regions such as cloud edges and thin cirrus. Evaluated on the global POLDER-3 dataset, MP-FPS achieves a mean Intersection over Union (mIoU) of 0.8662 across diverse surface types, surpassing the official baseline by 12.4%. This study establishes joint spectral analysis as a critical enabler for high-precision cloud masking, and demonstrates its synergistic value when integrated with multi-angle polarimetric information in a unified deep architecture. Full article

Intelligent road distress detection technology has emerged as an important research topic in the field of highway maintenance. However, the accuracy and practicality of pavement distress detection are constrained by multiple factors, primarily including the irregular shapes of distress, the tendency for fine cracks to be overlooked, and the high parameter count of detection models that makes deployment difficult. Therefore, this study proposes a lightweight road distress detection model based on an improved RT-DETR architecture—LRD-DETR. First, this work integrates the C2f-LFEM module with the ADown adaptive down-sampling strategy into the backbone network, significantly reducing the number of model parameters and computational load while effectively enhancing the representation capacity of multi-scale pavement distress features. Second, a frequency-domain spatial attention is embedded in the S4 feature layer, where synergistic integration of frequency-domain filtering and spatial attention enables detail enhancement of distress edges and contours, automatically focuses on the distress regions, and suppresses background interference. The polarity-aware linear attention is incorporated into the S5 feature layer, by explicitly modeling polarity interactions, it effectively captures textural discrepancies between damaged regions and the intact road surface, and a learnable power function dynamically rescales attention weights to strengthen distress-specific feature responses. Finally, a cross-scale spatial feature fusion module (CSF${}^2$M) is developed to reconstruct and fuse multi-level spatial featurez, thereby improving detection robustness for pavement distresses with diverse morphologies under complex background conditions. Quantitative experiments indicate that, in contrast with the baseline RT-DETR, the presented framework improves the F1-score by 7.1% and mAP@50 by 9.0%, while reducing computational complexity and parameter quantity by 43.8% and 38.0%, respectively. These advantages enable LRD-DETR to be suitably deployed on resource-limited embedded platforms for real-time road distress detection. Full article

In Transformer-based image restoration models, the self-attention mechanism often introduces attention noise from irrelevant contextual feature, hindering the recovery of underlying clear content. Although many methods have been proposed to suppress attention noise, we note that most existing approaches are often developed for general vision tasks and fail to generalize across remote sensing image dehazing, where large-scale spatial structures pose additional challenges for attention modeling. How to effectively model scale-aware attention to suppress redundant activations becomes crucial for remote sensing image dehazing. In this paper, we propose a scale-adaptive differential Transformer (SDTformer), an architecture designed to suppress attention noise through a differential attention mechanism, thereby improving reconstruction fidelity. Specifically, the model incorporates a scale-adaptive differential self-attention module, which models contextual dependencies across different spatial scales and reduces redundant contextual interference by computing differential attention maps. Additionally, a dynamic differential feed-forward network is proposed to adaptively select informative spatial features, strengthening feature aggregation. To further enhance feature representation, a gated fusion module is introduced to aggregate multi-scale features generated by different encoder blocks, which facilitates the learning process of each decoder block and improves the final reconstruction performance. Extensive experimental results on the commonly used benchmarks show that our method achieves favorable performance against state-of-the-art approaches. Full article

Hyperspectral image (HSI) classification requires the extraction of discriminative features from high-dimensional spatial–spectral data. While the Mamba architecture has shown promise in long-sequence modeling with linear complexity, its application to HSI remains constrained by two major hurdles: the unidirectional causal scanning which fails to capture non-causal global dependencies, and the serialization-induced loss of two-dimensional spatial topology and local textures. To overcome these limitations, we propose HAMamba, a novel Hybrid Attention State Space Model. HAMamba facilitates deep representation learning through two core components: a Multi-Scale Dynamic Fusion (MSDF) module and a Hybrid Attention Mamba Encoder (HAME). Specifically, the MSDF module augments spatial perception through parallelized feature extraction and dynamically weighted integration. The HAME synergizes a Bidirectional Sequence Scan Mamba (BSSM) to establish global semantic context and a Spatial–Spectral Gated Attention (SSGA) module to refine local structural details. Comprehensive experiments on four public benchmark datasets demonstrate that the proposed HAMamba significantly outperforms state-of-the-art approaches, achieving a superior balance between classification accuracy and computational efficiency. Full article

Acute Lymphoblastic Leukemia (ALL) is a highly prevalent hematological malignancy, especially in children, for whom precise and prompt subtype identification is essential to establish suitable treatment protocols. Current deep learning-based computer-aided diagnosis (CAD) methods for identifying ALL are hindered by numerous drawbacks, such as a dependence on solely spatial feature depictions, elevated feature dimensions, computationally extensive deep learning architectures, inadequate multi-layer feature utilization, and poor interpretability. This paper introduces LUMINA-Net, a custom, lightweight, and interpretable deep learning CAD for the automated identification and subtype diagnosis of ALL using microscopic blood smear pictures. LUMINA-Net makes four principal contributions: first, it integrates a self-attention module within a lightweight custom Convolution Neural Network (CNN) to effectively capture long-range spatial relationships across clinically pertinent cytological patterns while preserving a compact design. Second, it employs a Discrete Wavelet Transform (DWT)-based wavelet pooling layer that decreases feature dimensions by up to 96.875% while enhancing the obtained depictions with spatial-spectral information. Third, it utilizes a multi-layer feature fusion strategy that combines wavelet-pooled features from two deep layers with a third fully connected layer to create a discriminating multi-scale feature vector. Fourth, it incorporates Gradient-weighted Class Activation Mapping as a dedicated explainability process to furnish clinicians with apparent visual explanations for each classification decision. Withoit the need for image enhancement or segmentation preprocessing, LUMINA-Net outperforms the competing state-of-the-art methods on the same dataset, achieving a peak accuracy of 99.51%, specificity of 99.84%, and sensitivity of 99.51% on the publicly available Kaggle ALL dataset. This demonstrates that LUMINA-Net has the potential to be a dependable, effective, and clinically interpretable CAD tool for ALL diagnosis. Full article

Folic acid, an essential vitamin for human health, plays a crucial role in maintaining intestinal homeostasis and functional stability, and its absorption is frequently impaired in Crohn’s disease, where it is closely associated with clinical complications and nutritional management. Nevertheless, the quantitative relationship between the complex multiscale architecture of intestinal villi, their morphological dynamics, and the efficiency of folic acid absorption remains insufficiently understood, primarily because existing studies rely on oversimplified representations of villous geometry and neglect the internal vascular structure, thereby limiting their ability to capture the coupled transport processes within individual villi. While existing studies have considered the influence of villous morphology on intestinal absorption, they generally rely on oversimplified representations and do not account for the internal structural organization of villi. This study aims to elucidate the quantitative relationship between villous multiscale architecture and folic acid absorption efficiency under pathological conditions of Crohn’s disease. Herein, a two-dimensional multiphysics numerical model is developed that integrates the external environment of intestinal villi with their internal microstructure, simulating folic acid transport via diffusion and Michaelis–Menten kinetics, coupled with convection–diffusion in the microvascular network under Stokes flow conditions. We find a reduction in villus height to 400 μm or local blood flow velocity to 0.01 mm/s leads to a marked decrease in folic acid absorption capacity, by approximately 57% and 50%, respectively. These changes are primarily attributed to inflammation-induced villus atrophy, which reduces the effective absorptive surface area. Furthermore, reduced blood flow velocity lowers the Peclet number, facilitating the accumulation of folic acid within the villi, which in turn further reduces the efficiency of folic acid absorption. This work contributes to a deeper understanding of how diseases affect the absorptive function of intestinal villi and provides a theoretical basis for the pathological mechanisms of the gut. Full article

Spatial and temporal ontologies play a foundational role in modeling dynamic real-world phenomena across domains such as geographic information systems, artificial intelligence, and the Semantic Web. Although decades of research have advanced spatial reasoning, temporal logic, and ontology engineering, fully integrated spatio-temporal frameworks remain fragmented across disciplinary traditions. This paper presents a comprehensive review of spatial, temporal, and spatio-temporal ontologies, examining their conceptual foundations, formal logical models and Semantic Web standards. The literature is analyzed to classify major modeling paradigms and to evaluate their theoretical assumptions, representational capabilities, and computational trade-offs. The review proposes a taxonomy distinguishing foundational ontologies, spatial-centric models, temporal-centric frameworks, integrated spatio-temporal systems. Comparative discussion highlights tensions between logical expressiveness and scalability, as well as challenges related to interoperability and dynamic reasoning. The analysis identifies persistent gaps, including limited native temporal support in description logics, complexity in modeling evolving spatial relations, absence of unified spatio-temporal standards, and lack of standardized evaluation benchmarks. The paper concludes by outlining research directions focused on hybrid ontology–knowledge graph architectures, multi-scale modeling, event-driven semantics, and neuro-symbolic integration. By synthesizing theoretical and applied perspectives, this review provides a structured foundation for advancing interoperable and scalable spatio-temporal knowledge systems capable of supporting next-generation intelligent applications. Full article

Accurate seamount identification is important for understanding submarine tectonic and magmatic processes and for supporting deep-sea geomorphological analysis. However, seamount recognition faces a severe class imbalance as abyssal plains constitute the majority of deep-sea topography while seamounts occupy only a minimal portion, which makes accurate segmentation difficult. To address this issue, this study proposes an improved U-Net architecture, termed Spatial–Channel Reconstruction U-Net (RSCU-Net), built upon a Residual Spatial–Channel Reconstruction Convolution (Res-SCConv) module. The Res-SCConv module is embedded into each skip connection of the U-Net architecture. The model combines a Spatial Reconstruction Unit (SRU) and a Channel Reconstruction Unit (CRU) to suppress dominant background interference and reduce channel redundancy, and further introduces a Selective Kernel-based Multi-scale Gradient Module (SK-MGM) to improve boundary refinement. Experiments on the GEBCO 2023 bathymetric dataset, including 696 training samples and 88 independent test samples, show that RSCU-Net achieves an Accuracy of 0.938, Recall of 0.833, F1-score of 0.720, and IoU of 0.563. Compared with the baseline U-Net, Recall improves from 0.741 to 0.833 and IoU from 0.405 to 0.563. Additional validation on the Suda Seamount dataset yields an Accuracy of 0.987, F1-score of 0.958, and IoU of 0.920, demonstrating the robustness and generalization capability of the proposed method. Full article

Obtaining multiple MRI contrasts for each patient prolongs scan acquisition time, increases healthcare costs, and may not always be feasible due to patient specific constraints. Deep learning-based MRI contrast synthesis offers a potential solution, yet most existing approaches are evaluated on preprocessed public benchmarks that do not reflect real-world clinical variability. In this study, we propose a fusion U-Net transformer framework for bidirectional T1-weighted ↔ T2-weighted brain MRI synthesis trained and evaluated exclusively on retrospectively acquired clinical data. The proposed architecture integrates multiscale convolutional feature extraction with axial attention mechanisms and a transformer bottleneck for efficient global context modeling. A fusion refinement block is incorporated to mitigate skip connection artifacts. An adversarial training strategy with the least squares GAN objective and a hybrid loss combining L1 reconstruction and structural similarity (SSIM) is employed to promote both pixel-level accuracy and perceptual fidelity. The model is evaluated using SSIM and PSNR metrics alongside qualitative expert assessment conducted by two board-certified radiologists. For both synthesis directions, the framework achieves competitive quantitative performance against baseline models under the challenging conditions of clinical data. Expert evaluation confirms high anatomical fidelity and clinically acceptable image quality across both synthesis directions. These results indicate that the proposed framework represents a promising approach for multi-contrast MRI synthesis in clinically heterogeneous data environments. Full article

Automated pixel-level detection of steel surface defects is a critical challenge in manufacturing quality control, complicated by the variation in defect size and shape, low contrast with background textures, and the diversity of defect patterns. This paper proposes ID-MSNet, an enhanced version of the UNet3+ architecture, designed specifically for the segmentation of three common steel surface defect types: inclusions, patches, and scratches. The proposed architecture introduces three targeted modifications: (1) a multi-scale feature learning module (MSFLM) in the encoder that uses dilated convolutions at multiple rates to capture contextual features across different scales, combined with DropBlock regularization and batch normalization to improve generalization; (2) an improved down-sampling (IDS) module that replaces standard max-pooling with learnable strided convolutions fused via 1 × 1 convolution, preserving richer feature representations; and (3) a convolutional block attention module (CBAM) integrated into the skip connections to selectively focus the model on spatially and channel-wise relevant defect regions. Experiments on the publicly available SD-saliency-900 dataset demonstrate that ID-MSNet achieved an 86.19% mIoU, outperforming all compared state-of-the-art segmentation models while using only 6.7 million parameters—approximately 75% fewer than the original UNet3+. These results establish ID-MSNet as a strong and efficient baseline for steel surface defect segmentation, with potential applicability to automated quality inspection in broader manufacturing contexts. Full article

Deepfake technology poses significant threats to information authenticity and social trust, necessitating effective detection methods. However, existing detection approaches predominantly rely on high-complexity network architectures that, while accurate in controlled environments, suffer from prohibitive computational costs that hinder deployment in resource-constrained scenarios such as social media platforms. To address this efficiency-accuracy dilemma, we propose a lightweight face forgery detection method that systematically learns multi-scale forgery traces. Our approach features a four-stage lightweight architecture that hierarchically extracts features from local textures to global semantics, mimicking the human visual system. Within each stage, a multi-scale dynamic perception mechanism divides feature channels into parallel groups equipped with lightweight attention modules to capture forgery cues spanning pixel-level anomalies, local structures, regional patterns, and semantic inconsistencies. Furthermore, rather than relying on conventional feature fusion that risks suppressing subtle artifacts, we introduce a novel Context-Guided Dynamic Convolution. This mechanism uses mid-level spatial anomalies as active anchors to dynamically modulate high-level semantic filters, with the goal of mitigating the disconnect between semantic content and forgery evidence. Our model achieves strong performance, yielding an AUC of 91.98% on FaceForensics++ and 93.50% on DeepFake Detection Challenge, outperforming current state-of-the-art lightweight methods. Furthermore, compared to heavy Vision Transformers, our model achieves a superior performance-efficiency trade-off, requiring only 3.06 M parameters and 1.36 G FLOPs, making it highly suitable for real-time, resource-constrained deployment. Full article

The Mediterranean is being recognized as a helpful frame of reference for scholarship in various academic disciplines focusing on that area of the world. Some of these focus on the sea, while others focus on the countries surrounding it. Proponents laud the commonalities and unities that such an approach foregrounds, as well as the new ways of looking at related cultures and cultural products. At the same time, however, scholars recognize a number of challenges that come with this approach, particularly regarding the balance of micro and macro levels of analysis. Given these challenges, as well as the importance of local contexts for understanding aspects of time and agency in most works of art and architecture, how useful might such a lens be for scholars of medieval art and architecture in the region? How might we capitalize on the benefits of a Mediterranean frame of reference while also allowing for its challenges to be addressed? In response to these questions, consumption is suggested as a framework of analysis. Scholars of certain aspects of consumption have sought to balance similar tensions and their studies provide useful insights into how the local and the regional, the micro and the macro, might be effectively balanced. Such a consciously multiscale approach has the potential to help us see how the local and the Mediterranean are intertwined. In this way, thinking about certain aspects of medieval Mediterranean art via a lens of consumption can help us to make sense of how it reflects some of the complexities of the region. Full article

The large-scale integration and grid connection of renewable energy sources and charging stations introduce a multitude of nonlinear and impact loads, resulting in more severe distortion and higher complexity of disturbance signals in power systems. As a consequence, power quality disturbances (PQDs) in active distribution networks, including overvoltage and harmonics, display greater randomness and diversity, which increases the challenge of PQD identification. To tackle this problem, this study presents a dual-channel early-fusion approach for PQD recognition based on Spatial Post-MultiScale Fusion Entropy (SMFE). SMFE is used as an entropy-based feature-construction pipeline in which a time–frequency representation is formed prior to spatial post-multiscale aggregation to produce a compact complexity map complementary to waveform morphology. Subsequently, a dual-channel model is constructed by integrating waveform-morphology input with SMFE-derived complexity features for joint learning. By leveraging the ConvNeXt architecture and a Squeeze-and-Excitation (SE) mechanism, a multimodal channel-recalibration model is implemented to emphasize informative feature responses during PQD recognition. Experimental verification with simulated signals shows that the proposed approach achieves an identification accuracy of 97.83% under an SNR of 30 dB, indicating robust performance under the tested noise settings. Full article

Urban underground sewage pipelines often suffer from defects such as cracks, irregular joint misalignment, and stratified sedimentation blockages, which may lead to pipeline bursts, sewage overflow, and water pollution. Timely detection of abnormal defects in sewage pipelines is critical to ensuring public health and environmental sustainability. Vision-based sewage pipeline defect detection plays a crucial role in modern urban wastewater treatment systems. However, it still faces challenges such as limited feature extraction capabilities, insufficient multi-scale defect characterization, and poor positioning stability when dealing with low-contrast images and in environments with severe background interference. To address this issue, this study proposes an enhanced SAW-YOLOv8l model that integrates RT-DETR (real-time detection Transformer) with CNN (convolutional neural network) architecture. First, a C2f_SCA module improves the long-distance feature extraction capability and localization precision. Second, an AIFI-PRBN module enhances global feature correlation through attention-mechanism-based intra-scale feature interaction and reduces computational complexity using lightweight techniques. Finally, an adaptive dynamic weighted loss function based on Wise-IoU (weighted intersection over union) further improves training convergence and robustness by balancing the gradient distribution of samples. Experiments on a mixed dataset comprising Sewer-ML and industrial images demonstrate that the SAW-YOLOv8l model achieved mAP@0.5 of 86.2% and precision of 84.4%, which were improvements of 2.4% and 6.6% respectively over the baseline model, significantly enhancing the detection performance of abnormal defects in sewage pipelines. Full article

Unsupervised video anomaly detection (VAD) methods learn from normal data to identify anomalies by capturing pattern deviations. However, they often struggle to model multi-scale features and distinguish between normal and abnormal instances. To address these limitations, we propose a Multi-scale U-shaped Adaptive Clustering Learning (MS-UACL) framework. Built on the U-Net architecture, we redesign it as a 3D-encoder/2D-decoder autoencoder. In the encoder, we introduce a Dual-scale Feature Cascading Module (IDCN), which adopts a pseudo-branch fusion mechanism to systematically model multi-scale spatiotemporal features, thereby enhancing the model’s representational capability. To further enhance the distinction between normal and anomalous patterns, we propose an MLP-based Adaptive Clustering Algorithm (MLP-ACA). Specifically, MLP-ACA employs an initial mapping mechanism to align cluster centers with the underlying normal data distribution, facilitating more accurate feature reconstruction. Additionally, we introduce an adaptive clustering update strategy that optimizes cluster centers by tuning solely the parameters of the MLP. This enables the cluster centers to autonomously converge toward optimal feature representations, thereby accelerating clustering convergence and enhancing pattern separability. Extensive experiments on three benchmark datasets demonstrate that the proposed MS-UACL framework outperforms most existing methods on small- and medium-scale datasets. Full article