Search Results (4,724)

Building change detection and building damage assessment are two essential tasks in post-disaster analysis. Building change detection focuses on identifying changed building areas between bi-temporal images, while building damage assessment involves segmenting all buildings and classifying their damage severity. These tasks play a critical role in disaster response and urban development monitoring. Although supervised learning has significantly advanced building change detection and damage assessment, its reliance on large labeled datasets remains a major limitation. In contrast, self-supervised learning enables the extraction of meaningful data representations without explicit training labels. To address this challenge, we propose a self-supervised learning approach that unifies denoising autoencoders and contrastive learning, enabling effective data representation for building change detection and damage assessment. The proposed architecture integrates a dual denoising autoencoder with a Vision Transformer backbone and contrastive learning strategy, complemented by a Feature Pyramid Network-ResNet dual decoder and an Edge Guidance Module. This design enhances multi-scale feature extraction and enables edge-aware segmentation for accurate predictions. Extensive experiments were conducted on five public datasets, including xBD, LEVIR, LEVIR+, SYSU, and WHU, to evaluate the performance and generalization capabilities of the model. The results demonstrate that the proposed Denoising AutoEncoder-enhanced Dual-Fusion Network (DAEDFN) approach achieves competitive performance compared with fully supervised methods. On the xBD dataset, the largest dataset for building damage assessment, our proposed method achieves an F1 score of 0.892 for building segmentation, outperforming state-of-the-art methods. For building damage severity classification, the model achieves an F1 score of 0.632. On the building change detection datasets, the proposed method achieves F1 scores of 0.837 (LEVIR), 0.817 (LEVIR+), 0.768 (SYSU), and 0.876 (WHU), demonstrating model generalization across diverse scenarios. Despite these promising results, challenges remain in complex urban environments, small-scale changes, and fine-grained boundary detection. These findings highlight the potential of self-supervised learning in building change detection and damage assessment tasks. Full article

Object detection in remote sensing imagery is critical in environmental monitoring, urban planning, and land resource management. However, the task remains challenging due to significant scale variations, arbitrary object orientations, and complex background clutter. To address these issues, we propose a novel orientation module (SOAM Block) that jointly models object scale and directional features while exploiting geometric symmetry inherent in many remote sensing targets. The SOAM Block is constructed upon a lightweight and efficient Adaptive Multi-Scale (AMS) Module, which utilizes a symmetric arrangement of parallel depth-wise convolutional branches with varied kernel sizes to extract fine-grained multi-scale features without dilation, thereby preserving local context and enhancing scale adaptability. In addition, a Strip-based Context Attention (SCA) mechanism is introduced to model long-range spatial dependencies, leveraging horizontal and vertical 1D strip convolutions in a directionally symmetric fashion. This design captures spatial correlations between distant regions and reinforces semantic consistency in cluttered scenes. Importantly, this work is the first to explicitly analyze the coupling between object scale and orientation in remote sensing imagery. The proposed method addresses the limitations of fixed receptive fields in capturing symmetric directional cues of large-scale objects. Extensive experiments are conducted on two widely used benchmarks—DOTA and HRSC2016—both of which exhibit significant scale variations and orientation diversity. Results demonstrate that our approach achieves superior detection accuracy with fewer parameters and lower computational overhead compared to state-of-the-art methods. The proposed SOAM Block thus offers a robust, scalable, and symmetry-aware solution for high-precision object detection in complex aerial scenes. Full article

Automated surface defect detection in steel manufacturing is pivotal for ensuring product quality, yet it remains an open challenge owing to the extreme heterogeneity of defect morphologies—ranging from hairline cracks and microscopic pores to elongated scratches and shallow dents. Existing approaches, whether classical vision pipelines or recent deep-learning paradigms, struggle to simultaneously satisfy the stringent demands of industrial scenarios: high accuracy on sub-millimeter flaws, insensitivity to texture-rich backgrounds, and real-time throughput on resource-constrained hardware. Although contemporary detectors have narrowed the gap, they still exhibit pronounced sensitivity–robustness trade-offs, particularly in the presence of scale-varying defects and cluttered surfaces. To address these limitations, we introduce MBY (MBDNet-Attention-YOLO), a lightweight yet powerful framework that synergistically couples the MBDNet backbone with the YOLO detection head. Specifically, the backbone embeds three novel components: (1) HGStem, a hierarchical stem block that enriches low-level representations while suppressing redundant activations; (2) Dynamic Align Fusion (DAF), an adaptive cross-scale fusion mechanism that dynamically re-weights feature contributions according to defect saliency; and (3) C2f-DWR, a depth-wise residual variant that progressively expands receptive fields without incurring prohibitive computational costs. Building upon this enriched feature hierarchy, the neck employs our proposed MultiSEAM module—a cascaded squeeze-and-excitation attention mechanism operating at multiple granularities—to harmonize fine-grained and semantic cues, thereby amplifying weak defect signals against complex textures. Finally, we integrate the Inner-SIoU loss, which refines the geometric alignment between predicted and ground-truth boxes by jointly optimizing center distance, aspect ratio consistency, and IoU overlap, leading to faster convergence and tighter localization. Extensive experiments on two publicly available steel-defect benchmarks—NEU-DET and PVEL-AD—demonstrate the superiority of MBY. Without bells and whistles, our model achieves 85.8% mAP@0.5 on NEU-DET and 75.9% mAP@0.5 on PVEL-AD, surpassing the best-reported results by significant margins while maintaining real-time inference on an NVIDIA Jetson Xavier. Ablation studies corroborate the complementary roles of each component, underscoring MBY’s robustness across defect scales and surface conditions. These results suggest that MBY strikes an appealing balance between accuracy, efficiency, and deployability, offering a pragmatic solution for next-generation industrial quality-control systems. Full article

In this paper, a novel online detection system is designed to enhance accuracy and operational efficiency in the outbound logistics of automotive components after production. The system consists of a scanning portal system and an improved YOLOv12-based detection algorithm which captures images of automotive parts passing through the scanning portal in real time. By integrating deep learning, the system enables real-time monitoring and identification, thereby preventing misdetections and missed detections of automotive parts, in this way promoting intelligent automotive part recognition and detection. Our system introduces the A2C2f-SA module, which achieves an efficient feature attention mechanism while maintaining a lightweight design. Additionally, Dynamic Space-to-Depth (Dynamic S2D) is employed to improve convolution and replace the stride convolution and pooling layers in the baseline network, helping to mitigate the loss of fine-grained information and enhancing the network’s feature extraction capability. To improve real-time performance, a GFL-MBConv lightweight detection head is proposed. Furthermore, adaptive frequency-aware feature fusion (Adpfreqfusion) is hybridized at the end of the neck network to effectively enhance high-frequency information lost during downsampling, thereby improving the model’s detection accuracy for target objects in complex backgrounds. On-site tests demonstrate that the system achieves a comprehensive accuracy of 97.3% and an average vehicle detection time of 7.59 s, exhibiting not only high precision but also high detection efficiency. These results can make the proposed system highly valuable for applications in the automotive industry. Full article

Magnetic parameters of river sediments are commonly used as end-members for source tracing in the coasts and shelves. The eastern continental shelf area of China, with multiple sources of input, is a key region for discussing sediment sources. However, magnetic parameters are influenced by grain size, and the nature of this influence remains unclear. In this study, the Jiulong River was selected as a case to analyze the magnetic parameters and mineral characteristics for both the coarse (>63 μm) and fine-grained (<63 μm) fractions. Results show that the magnetic minerals mainly contain detrital-sourced magnetite and hematite. In the North River, a tributary of the Jiulong River, the content of coarse-grained magnetic minerals increases from upstream to downstream, contrary to fine-grained magnetic minerals, suggesting the influence of hydrodynamic forces. Some samples with abnormally high magnetic susceptibility may result from the combined influence of the parent rock and human activities. In the scatter diagrams of magnetic parameters for provenance tracing, samples of the <63 μm fractions have a more concentrated distribution than that of the >63 μm fractions. Hence, magnetic parameters for the <63 μm fraction are more useful in provenance identification. Full article

Recent advancements in generative artificial intelligence have significantly progressed the field of text-to-music generation, enabling users to create music from natural language descriptions. Despite the success of various models, such as MusicLM, MusicGen, and AudioLDM, the current approaches struggle to capture fine-grained genre-specific characteristics, precisely control musical attributes, and handle underrepresented cultural data. This paper introduces a novel, lightweight fine-tuning method for the AudioLDM framework using low-rank adaptation (LoRA). By updating only selected attention and projection layers, the proposed method enables efficient adaptation to musical genres with limited data and computational cost. The proposed method enhances controllability over key musical parameters such as rhythm, emotion, and timbre. At the same time, it maintains the overall quality of music generation. This paper represents the first application of LoRA in AudioLDM, offering a scalable solution for fine-grained, genre-aware music generation and customization. The experimental results demonstrate that the proposed method improves the semantic alignment and statistical similarity compared with the baseline. The contrastive language–audio pretraining score increased by 0.0498, indicating enhanced text-music consistency. The kernel audio distance score decreased by 0.8349, reflecting improved similarity to real music distributions. The mean opinion score ranged from 3.5 to 3.8, confirming the perceptual quality of the generated music. Full article

Background: Compared to the conventional method of machining granite, abrasive water jet machining (AWJM) offers several benefits, including flexible cutting mechanisms and machine efficiency, among other possible advantages. The high-speed particles carried by water remove the materials, preventing heat damage and maintaining the granite’s structure. Methods: Three types of granite with different compressive strengths are investigated in terms of the effects of pump pressure (P), traverse speed (T), and abrasive mass flow (A) on the cutting depth. Results: The results of the study demonstrated that the coarse-grained granite negatively affected the penetration depth, while the fine-grained granite produced a higher cutting depth. The value of an optimal depth of penetration was also generated; for example, the optimum depth obtained for Black Galaxy Granite, M1 (32.27 mm), was achieved at P = 300 MPa, T = 100 mm/min, and A = 180.59 g/min. Conclusions: In terms of processing parameters, the maximum penetration depth can be achieved in granite with a higher compressive strength. Full article

Frame-wise steganalysis is a crucial task in low-bit-rate speech streams that can achieve active defense. However, there is no common theory on how to extract steganalysis features for frame-wise steganalysis. Moreover, existing frame-wise steganalysis methods cannot extract fine-grained steganalysis features. Therefore, in this paper, we propose a frame-wise steganalysis method based on mask-gating attention and bilinear codeword feature interaction mechanisms. First, this paper utilizes the mask-gating attention mechanism to dynamically learn the importance of the codewords. Second, the bilinear codeword feature interaction mechanism is used to capture an informative second-order codeword feature interaction pattern in a fine-grained way. Finally, multiple fully connected layers with a residual structure are utilized to capture higher-order codeword interaction features while preserving lower-order interaction features. The experimental results show that the performance of our method is better than that of the state-of-the-art frame-wise steganalysis method on large steganography datasets. The detection accuracy of our method is 74.46% on 1000K testing samples, whereas the detection accuracy of the state-of-the-art method is 72.32%. Full article

Semantic segmentation is one of the key tasks in the intelligent interpretation of remote sensing images with extensive potential applications. However, when ultra-high resolution (UHR) remote sensing images exhibit complex background intersections and significant variations in object sizes, existing multimodal fusion segmentation methods based on convolutional neural networks and Transformers face challenges such as limited receptive fields and high secondary complexity, leading to inadequate global context modeling and multimodal feature representation. Moreover, the lack of accurate boundary detail feature constraints in the final segmentation further limits segmentation accuracy. To address these challenges, we propose a novel boundary-enhanced multilevel multimodal fusion Mamba-Large Strip Convolution network (FMLSNet) for remote sensing image segmentation, which offers the advantages of a global receptive field and efficient linear complexity. Specifically, this paper introduces a new multistage Mamba multimodal fusion framework (FMB) for UHR remote sensing image segmentation. By employing an innovative multimodal scanning mechanism integrated with disentanglement strategies to deepen the fusion process, FMB promotes deep fusion of multimodal features and captures cross-modal contextual information at multiple levels, enabling robust and comprehensive feature integration with enriched global semantic context. Additionally, we propose a Large Strip Spatial Detail (LSSD) extraction module, which adaptively combines multi-directional large strip convolutions to capture more precise and fine-grained boundary features. This enables the network to learn detailed spatial features from shallow layers. A large number of experimental results on challenging remote sensing image datasets show that our method exhibits superior performance over state-of-the-art models. Full article

As large language models (LLMs) increasingly enter specialized domains, inference without external resources often leads to knowledge gaps, opaque reasoning, and hallucinations. To address these challenges in power equipment defect grading, we propose a zero-shot question-answering framework that requires no task-specific examples. Our system performs two-stage retrieval—first using a Sentence-BERT model fine-tuned on power equipment maintenance texts for coarse filtering, then combining TF-IDF and semantic re-ranking for fine-grained selection of the most relevant knowledge snippets. We embed both the user query and the retrieved evidence into a Chain-of-Thought (CoT) prompt, guiding the pre-trained LLM through multi-step reasoning with self-validation and without any model fine-tuning. Experimental results show that on a held-out test set of 218 inspection records, our method achieves a grading accuracy of 54.2%, which is 6.0 percentage points higher than the fine-tuned BERT baseline at 48.2%; an Explanation Coherence Score (ECS) of 4.2 compared to 3.1 for the baseline; a mean retrieval latency of 28.3 ms; and an average LLM inference time of 5.46 s. Ablation and sensitivity analyses demonstrate that a fine-stage retrieval pool size of k = 30 offers the optimal trade-off between accuracy and latency; human expert evaluation by six senior engineers yields average Usefulness and Trustworthiness scores of 4.1 and 4.3, respectively. Case studies across representative defect scenarios further highlight the system’s robust zero-shot performance. Full article

A (NiCoCr)_99.25C_0.75 medium entropy alloy (MEA) was developed via laser powder bed fusion (LPBF) using pre-alloyed powder feedstock containing 0.75 at%C, followed by a precipitation heat treatment. The as-built alloy exhibited high density (>99.9%), columnar grains, fine substructures, and strong <111> texture. Heat treatment at 700 °C for 1 h promoted the precipitation of Cr-rich carbides (Cr₂₃C₆) along grain and substructure boundaries, which stabilized the microstructure through Zener pinning and the consumption of carbon from the matrix. The heat-treated alloy achieved excellent cryogenic tensile properties at 77 K, with a yield strength of 1230 MPa and an ultimate tensile strength of 1.6 GPa. Compared to previously reported LPBF-built NiCoCr-based MEAs, this alloy exhibited superior strength at both room and cryogenic temperatures, indicating its potential for structural applications in extreme environments. Deformation mechanisms at cryogenic temperature revealed abundant deformation twinning, stacking faults, and strong dislocation–precipitate interactions. These features contributed to dislocation locking, resulting in a work hardening rate higher than that observed at room temperature. This study demonstrates that carbon addition and heat treatment can effectively tune the stacking fault energy and stabilize substructures, leading to enhanced cryogenic mechanical performance of LPBF-built NiCoCr MEAs. Full article

Accurate weld defect detection is critical for ensuring structural safety and evaluating welding quality in industrial applications. Manual inspection methods have inherent limitations, including inefficiency and inadequate sensitivity to subtle defects. Existing detection models, primarily designed for natural images, struggle to adapt to the characteristic challenges of weld X-ray images, such as high noise, low contrast, and inter-defect similarity, particularly leading to missed detections and false positives for small defects. To address these challenges, a multi-dimensional feature fusion model (MADet), which is a multi-branch deep fusion network for weld defect detection, was proposed. The framework incorporates two key innovations: (1) A multi-scale feature fusion network integrated with lightweight attention residual modules to enhance the perception of fine-grained defect features by leveraging low-level texture information. (2) An anchor-based feature-selective detection head was used to improve the discrimination and localization accuracy for five typical defect categories. Extensive experiments on both public and proprietary weld defect datasets demonstrated that MADet achieved significant improvements over the state-of-the-art YOLO variants. Specifically, it surpassed the suboptimal model by 7.41% in mAP@0.5, indicating strong industrial applicability. Full article

This essay provides a fine-grained analysis of selected passages of Giulio Aleni (艾儒略 1582–1649)’s translation of Catholic liturgy into classical Chinese in late imperial China. It focuses on the hitherto underexplored relationships between Aleni’s resort to medieval Aristotelianism and Thomism, as well as his translation-based introduction of Catholic Eucharistic theology into China. The case studies here revolve around Aleni’s Chinese translation of Aristotelian-Thomistic hylomorphism, with a focus on his interpretation of “anima” (i.e., the soul, which corresponds largely to linghun 靈魂 in Chinese), which is a multifaceted Western concept that pertains simultaneously to Aristotelian-Thomistic philosophy and Eucharistic theology. It is argued that in his overarching project of introducing Western learnings (i.e., 西學) to sixteenth- and seventeenth-century China, Aleni’s attention is centered primarily on the body-soul and form-matter relationship. This is, as understood here, motivated to a great extent by his scholarly awareness that properly informing Chinese Catholics of the Aristotelian-Thomistic underpinning of Western metaphysics enacts an indispensable role in introducing Catholic liturgy into China, notably the mystery of the Eucharist and Transubstantiation that would not have been effectively introduced to China without having the Western philosophical underpinnings already made available to Chinese intellectuals. Aleni’s use of medieval European cultural legacy thus requires more in-depth analysis vis-à-vis his translational poetics in China. Accordingly, the intellectual and liturgical knowledge in Aleni’s Chinese œuvres shall be investigated associatively, and the medievalism embodied by Aleni offers a valid entry point and productive critical prism. Full article

The description and assessment of braided river architecture are usually limited by the paucity of real geological datasets from field observations; due to the complexity and diversity of rivers, traditional evaluation models are difficult to apply to braided river systems in different climatic and tectonic settings. This study aims to establish an architectural model suitable for the study area setting by introducing a hierarchical analysis approach through well-exposed three-dimensional outcrops along the Second Songhua River. A micro–macro four-level hierarchical framework is adopted to obtain a detailed anatomy of sedimentary outcrops: lithofacies, elements, element associations, and archetypes. Fourteen lithofacies are identified: three conglomerates, seven sandstones, and four mudstones. Five elements provide the basic components of the river system framework: fluvial channel, laterally accreting bar, downstream accreting bar, abandoned channel, and floodplain. Four combinations of adjacent elements are determined: fluvial channel and downstream accreting bar, fluvial channel and laterally accreting bar, erosionally based fluvial channel and laterally accreting bar, and abandoned channel and floodplain. Considering the sedimentary evolution process, the braided river prototype, which is an element-based channel filling unit, is established by documenting three contact combinations between different elements and six types of fine-grained deposits’ preservation positions in the elements. Empirical relationships are developed among the bankfull channel depth, mean bankfull channel depth, and bankfull channel width. For the braided river systems, the establishment of the model promotes understanding of the architecture and evolution, and the application of the hierarchical analysis approach provides a basis for outcrop, underground reservoir, and tank experiments. Full article

To address the limitations of the existing cotton seedling growth prediction methods in field environments, specifically, poor representation of spatiotemporal features and low visual fidelity in texture rendering, this paper proposes an algorithm for the prediction of cotton seedling growth from images based on FCA-STNet. The model leverages historical sequences of cotton seedling RGB images to generate an image of the predicted growth at time t + 1 and extracts 37 phenotypic traits from the predicted image. A novel STNet structure is designed to enhance the representation of spatiotemporal dependencies, while an Adaptive Fine-Grained Channel Attention (FCA) module is integrated to capture both global and local feature information. This attention mechanism focuses on individual cotton plants and their textural characteristics, effectively reducing the interference from common field-related challenges such as insufficient lighting, leaf fluttering, and wind disturbances. The experimental results demonstrate that the predicted images achieved an MSE of 0.0086, MAE of 0.0321, SSIM of 0.8339, and PSNR of 20.7011 on the test set, representing improvements of 2.27%, 0.31%, 4.73%, and 11.20%, respectively, over the baseline STNet. The method outperforms several mainstream spatiotemporal prediction models. Furthermore, the majority of the predicted phenotypic traits exhibited correlations with actual measurements with coefficients above 0.8, indicating high prediction accuracy. The proposed FCA-STNet model enables visually realistic prediction of cotton seedling growth in open-field conditions, offering a new perspective for research in growth prediction. Full article