Search Results (322)

Millimeter-wave radar imaging plays an increasingly important role in autonomous driving road perception due to its robustness under adverse weather conditions. However, radar images are inherently contaminated by multiplicative speckle noise, which severely degrades structural continuity, weakens target boundaries, and limits the perception of road scenes and surrounding objects. To address this problem, this paper proposes a structural-prior deep learning network for millimeter-wave radar image enhancement. The proposed framework first introduces an adaptive Otsu-based masking strategy to extract salient scattering structures and generate a coarse image structural prior for subsequent restoration. Guided by this prior, the network performs progressive feature enhancement through a continuous attention mechanism that integrates residual channel attention, context-aware feature extraction, and convolutional block attention, thereby enabling effective multi-scale representation learning while suppressing signal-dependent speckle interference. In addition, a composite loss function is designed by combining logarithmic denoising gain, total variation regularization, and a $\beta$-index edge-preservation term to jointly improve noise suppression, spatial smoothness, and structural fidelity. The proposed method is evaluated on the synthetic UC Merced dataset under different noise intensities and via cross-domain inference on the real-world RADIATE millimeter-wave radar dataset for autonomous driving scenarios. Experimental results demonstrate that the proposed network consistently outperforms conventional filtering methods and representative deep learning baselines in terms of PSNR, SSIM, $\beta$-index, and ENL while providing a superior preservation of road structures, target contours, and scene geometry. Ablation studies further confirm the effectiveness of the structural-prior guidance and continuous attention design. Furthermore, the network achieves a rapid inference latency of 12.35 milliseconds. These results indicate that the proposed method provides an effective and robust solution for millimeter-wave radar image enhancement and offers practical value for downstream road-scene perception in autonomous driving environments. Full article

Object detection in Unmanned Aerial Vehicle (UAV) imagery faces severe challenges, including small target scales, dense spatial distributions, and complex backgrounds. To address the feature attenuation and noise interference inherent in existing deep learning models, this paper proposes DOL-DETR, an efficient small object detection algorithm based on the Real-Time DEtection TRansformer (RT-DETR) architecture. Our model introduces three key innovations. First, the DAttention-based Intra-scale Feature Interaction (DAIFI) module reconstructs intra-scale feature interactions using deformable attention to focus on salient regions with linear complexity. Second, the Omni-Modulated Feature Fusion (OMFF) mechanism adaptively captures multi-scale features and dynamically suppresses background noise. Finally, Linear De-redundancy Convolution (LDConv) replaces standard downsampling to dynamically adapt to object deformations. While introducing a complex dynamic resampling mechanism, it strategically optimizes parameter allocation, significantly enhancing localization precision without introducing excessive computational overhead. Extensive experiments on the VisDrone2019 benchmark demonstrate that DOL-DETR achieves an mAP@0.5 of 52.4% (a 4.2% improvement over the baseline) while maintaining a real-time inference speed of 120.1 FPS with only 20.1M parameters. Furthermore, generalization experiments on the large-scale DOTA dataset yield a 76.1% mAP@0.5, outperforming the baseline by 3.8%. These results indicate that DOL-DETR provides a better trade-off between detection accuracy, inference efficiency, and cross-domain generalization in UAV remote sensing scenarios. Full article

Several well-known models in present-day computer vision take the form of Markov random fields. Any model of this kind amounts to a network of soft constraints, which are called potentials. These are the subject of this study. First, three kinds of information that are involved in any computer vision inference task are identified, namely, evidence, target, and principled information, and the concept of a variable as applied in this context is discussed. The general meaning of a potential is then described, which is a local soft constraint that aims to promote a corresponding desired condition. Following this, the formal structure of a potential is highlighted, which includes a set of parameters and an analytic frame, with this being a hierarchy of operations by which the value of the potential can be computed. The possible presence of a core in the analytic frame is considered, and two salient kinds of cores are distinguished and illustrated using examples from the literature: one involving a distance function and the other given by a probabilistic conditional. In summary, this contribution highlights substantial aspects of the semantics and syntax of potentials in Markov field models of computer vision, and constructs a framework within which these aspects may be consistently arranged and explained. Full article

Disinformation, amplified by digital platforms and algorithmic distribution systems, represents a growing challenge for media trust, public health communication, and societal stability. This narrative literature review examines disinformation through an integrative psychosocial perspective, focusing on how patterns of exposure interact with individual vulnerability factors—including education, political beliefs, social identity, personality traits, and emotional responses to uncertainty—to influence the processing and acceptance of misleading information. The review synthesises interdisciplinary evidence on how algorithmic amplification and emotionally salient content increase susceptibility to disinformation and shape risk perception, health-related decision-making, and preventive behaviours. Findings indicate that repeated exposure to false or misleading information reinforces perceived credibility through familiarity effects, contributes to declining trust in institutional sources, and intensifies social and political polarisation. Disinformation is therefore conceptualised not only as an informational problem but also as a psychosocial process affecting emotional regulation, cognitive evaluation, and collective responses to crises, particularly in public health contexts. The analysis further highlights a recursive feedback loop in which reduced media trust increases vulnerability to subsequent disinformation, with broader implications for democratic participation and social cohesion. Mitigation strategies discussed include media literacy initiatives, critical thinking education, platform governance, regulatory approaches, and interventions targeting psychosocial drivers of susceptibility. Full article

Early detection of agricultural fires with Unmanned Aerial Vehicles (UAVs) is important for environmental safety, yet it remains difficult because ignition cues are extremely small, smoke patterns vary widely, and farmland scenes often contain strong background interference such as specular reflections. Model development is further constrained by the scarcity of data from the early ignition stage. To address these challenges, we propose a joint data and model optimization framework. We first build a hybrid dataset through an ROI-guided synthesis pipeline, in which latent diffusion models are used to insert high-fidelity, carefully screened fire samples into real farmland backgrounds. We then introduce EF-YOLO, a detector designed for high sensitivity to small targets. The network uses SPD-Conv to reduce feature loss during spatial downsampling and includes a high-resolution P2 head to improve the detection of minute objects. To reduce background clutter, a Dual-Path Frequency–Spatial Enhancement (DP-FSE) module serves as a lightweight statistical surrogate that extracts global contextual cues and local salient features in parallel, thereby suppressing high-frequency noise. Experimental results show that EF-YOLO achieves an ${AP}_S$ of 40.2% on sub-pixel targets, exceeding the YOLOv8s baseline by 15.4 percentage points. With a recall of 88.7% and a real-time inference speed of 78 FPS, the proposed framework offers a strong balance between detection performance and efficiency, making it well suited for edge-deployed agricultural fire early-warning systems. Full article

Kuwait faces mounting challenges in municipal solid waste (MSW) management alongside continued dependence on fossil-fuel-based electricity generation. Per capita waste generation in Kuwait is approximately 1.7 kg/person/day, exceeding the global average of 0.74 kg/person/day, indicating substantial potential for resource recovery and energy conversion. This study evaluates public perceptions of waste-to-energy (WtE) in Kuwait’s residential sector and estimates the potential electricity that could be generated from household waste. A structured online household survey (n = 470) was administered to assess socio-demographic characteristics and key perception constructs, including awareness, perceived risks, perceived benefits, and overall attitudes toward WtE. In parallel, a quantitative estimation was undertaken using literature-based parameters for monthly per capita waste generation and electricity consumption to derive household-level waste quantities, corresponding energy potential, and generated-to-consumed energy ratios. Survey findings indicate generally favourable attitudes toward WtE and recognition of its potential to reduce landfill dependence and contribute to electricity supply, although respondents showed stronger support for locating WtE facilities away from residential neighbourhoods. Perceived risks—particularly related to health and environmental impacts—remained salient, while perceived benefits associated with waste reduction and local economic value were also acknowledged. The technical assessment indicates that higher waste generation increases theoretical energy recovery potential; however, high residential electricity demand reduces the relative contribution of WtE, with a generated-to-consumed energy ratio of approximately 2, compared with a global benchmark ratio of 4.1. This study highlights the need for targeted public engagement, improved source segregation, and more detailed Kuwait-specific technical and economic evaluations to support evidence-based WtE policy and investment decisions. Full article

Transformer models have achieved powerful performance in various computer vision tasks. However, their black-box nature severely limits model interpretability and the reliability of real-world applications. Most existing interpretation methods generate explanation maps by perturbing masks from the last layer of the Transformer encoder, but they often overlook uncertain information in masks and detail loss during upsampling and downsampling, resulting in coarse localization, blurred boundaries, and significant background noise in explanations. To address these issues, this paper proposes a self-distillation object segmentation method based on sequential three-way mask and attention fusion (SAF-SD), targeting salient and camouflaged binary object segmentation tasks (sub-tasks of binary pixel-level segmentation). The method consists of two core modules: the sequential three-way mask (S3WM) module and the attention fusion (AF) module. The S3WM module performs strict threshold filtering on masks generated from the final-layer feature maps of the Transformer, aiming to accurately segment foreground objects from backgrounds via binary pixel-level prediction. The AF module aggregates attention matrices across all Transformer encoder layers to construct a cross-layer relation matrix, capturing global semantic dependencies among image patches (e.g., interactions between foreground, background, and edge regions). It then computes the importance score for each patch, refining details and suppressing noise in the initial explanation results. Extensive experimental results demonstrate that SAF-SD significantly outperforms existing baseline methods across key evaluation metrics. Full article

This study explores the digital competence of foreign language teachers in Bulgarian secondary education by focusing on the institutional context of which they are a part, the strengths and gaps of their competence, and their levels of competence. It draws upon empirical data that were collected and analyzed within an integrated, dual-instrument framework, combining the SELFIE (Self-reflection on Effective Learning by Fostering the Use of Innovative Educational Technologies) and SELFIE for TEACHERS (Self-reflection on Effective Learning by Fostering the Use of Innovative Educational Technologies for Teachers) EU-aligned assessment tools. The results from the questionnaire data show that the foreign language teachers state that they work in a relatively good technological environment and evaluate the usage of digital technologies for teaching and communication purposes within the school context as a salient aspect of their digital competence. The results also reveal three areas in the study participants’ digital competence that are in need of improvement: (1) empowering learners/personalizing the educational process, (2) assessment and (3) facilitating learners’ digital competence. In addition, the findings indicate that the foreign language educators rate their digital competence at a low to medium level. By blending institutional and teacher-oriented perspectives into a single integrated study of Bulgarian secondary school foreign language teachers, this investigation extends the existing research and makes evidence-based recommendations for institutional capacity building, teacher education policy and targeted professional development aimed at improving the educators’ digital competence. Full article

With the development of cross-modal image fusion in multi-sensor systems, current fusion technologies have made significant progress in feature extraction, facilitating more effective image analysis. However, insufficient fusion information may degrade the correlation between the source and fused images, often resulting in the omission of critical features from the original modalities. Therefore, in order to preserve as much information as possible, especially for the complete extraction of effective feature information in source images, this paper proposes a new cross-modal image fusion method based on low-rank representation and convolutional sparse learning named LRCFuse. Firstly, the learned low-rank representation (LLRR) blocks are employed to perform dimensionality reduction on the source images while simultaneously extracting their low-rank and sparse feature components. Nevertheless, considering that the low-rank representation has insufficient modeling ability for different modal images, we introduce common feature preservation module (CFPM) blocks based on convolutional sparse coding. By leveraging the CFPM module, LRCFuse recovers common features from both source images to mitigate the loss caused by the imperfect assumptions of low-rank representation. Based on this, a multi-level optimization strategy incorporating pixel loss, shallow-level loss, mid-level loss, deep-level loss, and sobel loss is proposed to hierarchically learn and refine diverse image features. Quantitative and qualitative evaluations are conducted across various datasets, revealing that LRCFuse can effectively detect targets infrared salient targets, preserve additional details in visible images, and achieve better fusion results for subsequent downstream tasks. Full article

This paper proposes a novel salient object detection method for operational hole localization in metallurgical furnaces, addressing challenging industrial conditions including extreme illumination variations and strong electromagnetic interference to enable two-level measurement in aluminum electrolysis cells and impact position recognition of the front-of-furnace operation robot. It employs a multi-feature fusion framework combining foreground and background saliency maps with center prior maps. Foreground saliency maps are generated through spatial compactness and local contrast computations, enhancing discriminative features while suppressing shared foreground–background characteristics. Background saliency maps are constructed via sparse reconstruction to exploit redundant features. Then method integrates edge extraction and density clustering to generate center prior maps that emphasize foreground target centroids and mitigate background noise. Comprehensive evaluations on both a specialized operational hole dataset and six public datasets demonstrate superior performance compared to other methods. On the specialized dataset, it achieves a precision of 0.8954, a maximum F-measure of 0.8994, and an S-measure of 0.8662. While maintaining operational robustness, the method offers a practical solution for furnace monitoring and robotic operation guidance in metallurgical processes. Full article

This study examines the False Reality Bias in treasury management, a cognitive distortion through which small and medium-sized enterprises (SMEs) infer financial stability from salient bank balances while overlooking pending obligations and cash-flow timing. Using a firm-level dataset of 50 Spanish meat-processing SMEs, the analysis develops two behavioral-finance indicators: the Liquidity Misperception Index (PEL), capturing the divergence between salient liquidity cues and effective short-term obligations, and the Liquidity Misconfidence Index (ICEL), measuring managerial overconfidence in liquidity assessments. Results show that 41% of firms overestimate liquidity (average PEL = 1.21), while 40% exhibit excessive confidence (ICEL > 1.3), both significantly associated with liquidity distress. Econometric estimates indicate that firms with PEL values above 1.2 are 4.48 times more likely to experience liquidity crises, even after controlling for bank balance levels. Predictive models are used in an exploratory capacity, achieving classification accuracies above 80% and supporting the robustness of the behavioral signals identified. In addition, AI-assisted cash-flow simulations reduce liquidity misperception by 34.7% (p < 0.01). Overall, the findings provide micro-level evidence that cognitive biases systematically distort SME treasury decisions but can be partially corrected through targeted decision-support tools, offering practical insights for managers, advisors, and policymakers. Full article

The article examines how framing and actor identity structure attention in short-video politics using a country-level corpus from Ecuador. It assembles 4612 public TikTok videos from official accounts and politically salient hashtags, extracts multimodal text via automatic speech recognition and on-screen OCR, and constructs two continuous indices: a quality index (programmatic, efficacy-oriented content) and a populism index (antagonistic, people-versus-elite cues). Engagement is modeled as a fractional response (binomial GLM with logit link), with robustness checks using OLS on logit(ER) and Poisson counts with an offset for log(plays + 1). Models include affect (positive sentiment and anger), hour/day controls, and actor fixed effects (leader, creator, institution, party, and media). The indices display construct validity: quality aligns with positive/joyful tone and populism with anger. Net of controls, populism is positively and consistently associated with engagement across estimators; quality is small and often null or negative. Effects are heterogeneous: leaders gain under both frames, creators primarily under populism, and media modestly under populism, while institutions face penalties under both, and parties show limited returns. Monthly series reveal event-linked intensification of populism, and hashtag networks are modular, mapping onto institutional, partisan, and creator ecosystems. A design analysis identifies a non-populist pathway—benefit-first micro-explanations, concise captions, targeted hashtags, and joyful/efficacy affect—that raises engagement without antagonism. The study contributes a reproducible, open-source pipeline for survey-free, multimodal framing measurement and clarifies how persona × frame interactions and meso-level discursive structure jointly organize attention in short-video politics. Full article

Background/Objectives: Transgender and gender-diverse (TGD) individuals experience disproportionately high rates of childhood trauma and depression; however, the mechanisms linking gender identity and depressive symptoms remain insufficiently understood. This study examines differences in depressive symptoms and childhood trauma between cisgender (CG) and TGD adults. It investigates whether specific subtypes of childhood maltreatment mediate the association between gender identity and depression. Methods: The cross-sectional online study included 249 participants aged 18–72 years (M = 30.85, SD = 12.72), including 144 CG (75 women and 69 men) and 105 TGD individuals (44 transgender and 61 gender diverse individuals). Depression symptoms were assessed using the nine-item Patient Health Questionnaire (PHQ-9), while childhood trauma experiences were measured using the Childhood Trauma Questionnaire–Short Form (CTQ-SF). Results: The independent-sample Student’s t-test showed that TGD participants reported significantly higher levels of depressive symptoms and all forms of childhood trauma than cisgender individuals. Mediation analyses indicated that overall childhood trauma partially mediated the association between gender identity and depression. In parallel mediation models, emotional abuse emerged as the primary statistical mediator, with sexual abuse showing a smaller indirect effect. Conclusions: The findings extend prior prevalence-focused research by identifying specific childhood trauma pathways associated with depressive symptoms in TGD adults. Experiencing traumatic events during childhood may be a key factor contributing to an increased risk of depression in adulthood, particularly among the TGD population. Therefore, intervention and prevention programs should target TGD individuals and their families to minimize the risk of adverse childhood experiences and mental health disorders. The results underscore the importance of trauma-informed and gender-affirming mental health care and highlight emotional abuse as a particularly salient correlate of depression in this population. Full article

Visible-infrared image fusion is crucial for applications like autonomous driving and nighttime surveillance, yet it remains challenging due to the inherent limitations of existing deep learning models. Convolutional Neural Networks (CNNs) are constrained by their local receptive fields, while Transformers suffer from quadratic computational complexity. To address these issues, this paper investigates the application of the Mamba model—a novel State Space Model (SSM) with linear-complexity global modeling and selective scanning capabilities—to the task of visible-infrared image fusion. Building upon Mamba, we propose a novel fusion framework featuring two key designs: (1) A Multi-Path Mamba (MPMamba) module that orchestrates parallel Mamba blocks with convolutional streams to extract multi-scale, modality-specific features; and (2) a Dual-path Mamba Attention Fusion (DMAF) module that explicitly decouples and processes shared and complementary features via dual Mamba paths, followed by dynamic calibration with a Convolutional Block Attention Module (CBAM). Extensive experiments on the MSRS benchmark demonstrate that our framework achieves state-of-the-art performance, outperforming strong baselines such as U2Fusion and SwinFusion across key metrics including Information Entropy (EN), Spatial Frequency (SF), Mutual Information (MI), and edge-based fusion quality (Qabf). Visual results confirm its ability to produce fused images that saliently preserve thermal targets while retaining rich texture details. Full article

The detection of defects in Printed Circuit Boards (PCBs) is a critical yet challenging task in industrial quality control, characterized by the prevalence of small targets and complex backgrounds. While deep learning models like YOLOv5 have shown promise, they often lack the ability to quantify predictive uncertainty, leading to overconfident errors in challenging scenarios—a major source of false alarms and reduced reliability in automated manufacturing inspection lines. From a Bayesian perspective, this overconfidence signifies a failure in probabilistic calibration, which is crucial for trustworthy automated inspection. To address this, we propose MFE-YOLO, a Bayesian-enhanced detection framework built upon YOLOv5 that systematically integrates uncertainty-aware mechanisms to improve both accuracy and operational reliability in real-world settings. First, we construct a multi-background PCB defect dataset with diverse substrate colors and shapes, enhancing the model’s ability to generalize beyond the single-background bias of existing data. Second, we integrate the Convolutional Block Attention Module (CBAM), reinterpreted through a Bayesian lens as a feature-wise uncertainty weighting mechanism, to suppress background interference and amplify salient defect features. Third, we propose a novel FIoU loss function, redesigned within a probabilistic framework to improve bounding box regression accuracy and implicitly capture localization uncertainty, particularly for small defects. Extensive experiments demonstrate that MFE-YOLO achieves state-of-the-art performance, with mAP@0.5 and mAP@0.5:0.95 values of 93.9% and 59.6%, respectively, outperforming existing detectors, including YOLOv8 and EfficientDet. More importantly, the proposed framework yields better-calibrated confidence scores, significantly reducing false alarms and enabling more reliable human-in-the-loop verification. This work provides a deployable, uncertainty-aware solution for high-throughput PCB inspection, advancing toward trustworthy and efficient quality control in modern manufacturing environments. Full article