Search Results (1,819)

Generating non-standard fonts, such as running script (e.g., XingShu), poses significant challenges due to their high stroke continuity, structural flexibility, and stylistic diversity, which traditional component-based prior knowledge methods struggle to model effectively. While diffusion models excel at capturing continuous feature spaces and stroke variations through iterative denoising, they face critical limitations: (1) style leakage, where large stylistic differences lead to inconsistent outputs due to noise interference; (2) structural distortion, caused by the absence of explicit structural guidance, resulting in broken strokes or deformed glyphs; and (3) style confusion, where similar font styles are inadequately distinguished, producing ambiguous results. To address these issues, we propose a novel skeleton-guided diffusion model with three key innovations: (1) a skeleton-constrained style rendering module that enforces semantic alignment and balanced energy constraints to amplify critical skeletal features, mitigating style leakage and ensuring stylistic consistency; (2) a cross-scale skeleton preservation module that integrates multi-scale glyph skeleton information through cross-dimensional interactions, effectively modeling macro-level layouts and micro-level stroke details to prevent structural distortions; (3) a contrastive style refinement module that leverages skeleton decomposition and recombination strategies, coupled with contrastive learning on positive and negative samples, to establish robust style representations and disambiguate similar styles. Extensive experiments on diverse font datasets demonstrate that our approach significantly improves the generation quality, achieving superior style fidelity, structural integrity, and style differentiation compared to state-of-the-art diffusion-based font generation methods. Full article

In recent years, research in sequential recommendation has primarily refined user intent by constructing sequence-level contrastive learning tasks through data augmentation or by extracting preference information from the latent space of user behavior sequences. However, existing methods suffer from two critical limitations. Firstly, they fail to account for how random data augmentation may introduce unreasonable item associations in contrastive learning samples, thereby perturbing sequential semantic relationships. Secondly, the neglect of temporal dependencies may prevent models from effectively distinguishing between incidental behaviors and stable intentions, ultimately impairing the learning of user intent representations. To address these limitations, we propose TCLRec, a novel temporal-aware and intent contrastive learning framework for sequential recommendation, incorporating symmetry into its architecture. During the data augmentation phase, the model employs a symmetrical contrastive learning architecture and incorporates semantic enhancement operators to integrate user preferences. By introducing user rating information into both branches of the contrastive learning framework, this approach effectively enhances the semantic relevance between positive sample pairs. Furthermore, in the intent contrastive learning phase, TCLRec adaptively attenuates noise information in the frequency domain through learnable filters, while in the pre-training phase of sequence-level contrastive learning, it introduces a temporal-aware network that utilizes additional self-supervised signals to assist the model in capturing both long-term dependencies and short-term interests from user behavior sequences. The model employs a multi-task training strategy that alternately performs intent contrastive learning and sequential recommendation tasks to jointly optimize user intent representations. Comprehensive experiments conducted on the Beauty, Sports, and LastFM datasets demonstrate the soundness and effectiveness of TCLRec, where the incorporation of symmetry enhances the model’s capability to represent user intentions. Full article

In free space optical (FSO) communications, signals are affected by turbulence when transmitted through the atmosphere. Fluctuations in intensity caused by atmospheric turbulence lead to an increase in the bit error rate of FSO systems. Deep learning (DL), as a current research hotspot, offers a promising approach to improve the accuracy of signal detection. In this paper, we propose a signal detection method based on a bidirectional gated recurrent unit (BiGRU) neural network for FSO communications. The proposed detection method considers the temporal correlation of received signals due to the properties of the BiGRU neural network, which is not available in existing detection methods based on DL. In addition, the proposed detection method does not require channel state information (CSI) for channel estimation, unlike maximum likelihood (ML) detection technology with perfect CSI. Numerical results demonstrate that the proposed BiGRU-based detector achieves significant improvements in bit error rate (BER) performance compared with a multilayer perceptron (MLP)-based detector. Specifically, under weak turbulence conditions, the BiGRU-based detector achieves an approximate 2 dB signal-to-noise ratio (SNR) gain at a target BER of ${10}^{-6}$ compared to the MLP-based detector. Under moderate turbulence conditions, it achieves an approximate 6 dB SNR gain at the same target BER of ${10}^{-6}$. Under strong turbulence conditions, the proposed detector obtains a 6 dB SNR gain at a target BER of ${10}^{-4}$. Additionally, it outperforms conventional methods by more than one order of magnitude in BER under the same turbulence and SNR conditions. Full article

Makerspaces are increasingly integrated into educational activities in both formal and nonformal contexts, from primary to higher education, particularly as interdisciplinary learning spaces that foster creativity and the “do-it-yourself” approach. Their hands-on approach stimulates agency, critical thinking, and innovation—competences closely tied to the entrepreneurship competence. However, empirical studies exploring the relationship between makerspaces and the development of entrepreneurship competence remain limited, often addressing only specific types of makerspaces or partial aspects of entrepreneurial competence. The aim of this study is to identify, based on a systematic literature review, if/how makerspaces contribute to developing entrepreneurial competences of students in secondary education. In total, 35 articles published in the last 10 years, indexed in ERIC, Web of Science, and Google Scholar, selected according to the PRISMA guidelines, met the inclusion criteria. The selected databases ensure both quality and broad coverage. The studies were analyzed using a structured framework based on four thematic categories: identity (makerspace as learning space influencing entrepreneurial competences), competence (focus on entrepreneurial competences), program (educational initiatives fostering entrepreneurial competences), environment (contextual factors shaping entrepreneurial competences in makerspaces). The findings reveal that the identity of makerspaces, characterized by values such as collaboration, valuing ideas, and hands-on learning, converges with the intentional design of learning environments and the structure of educational programs to foster entrepreneurial competences. Makerspaces were found to cultivate dimensions such as creativity, problem-solving, teamwork, initiative, and ethical thinking, all of which are listed as units of the entrepreneurial competence by EntreComp. The study concludes that makerspaces can act as effective pedagogical means for supporting entrepreneurial competence development. The results provide valuable insights and examples that can inform the design of future educational strategies and programs to promote entrepreneurship education and develop entrepreneurial competences in nonformal and formal learning settings acting as makerspaces. Full article

The accurate segmentation of multiple sclerosis (MS) lesions in magnetic resonance imaging (MRI) is essential for diagnosis, disease monitoring, and therapeutic assessment. Despite the significant advances in deep learning-based segmentation, the current boundary-aware approaches are limited by their reliance on spatial distance transforms, which fail to fully exploit the rich texture and intensity information inherent in MRI data. This limitation is particularly problematic in regions where MS lesions and normal-appearing white matter exhibit overlapping intensity distributions, resulting in ambiguous boundaries and reduced segmentation accuracy. To address these challenges, we propose a novel Mahalanobis distance map (MDM) and a corresponding Mahalanobis distance loss, which generalize traditional distance transforms by incorporating spatial coordinates, the FLAIR intensity, and radiomic texture features into a unified feature space. Our method leverages the covariance structure of these features to better distinguish ambiguous regions near lesion boundaries, mimicking the texture-aware reasoning of expert radiologists. Experimental evaluation on the ISBI-MS and MSSEG datasets demonstrates that our approach achieves superior performance in both boundary quality metrics (HD95, ASSD) and overall segmentation accuracy (Dice score, precision) compared to state-of-the-art methods. These results highlight the potential of texture-integrated distance metrics to overcome MS lesion segmentation difficulties, providing more reliable and reproducible assessments for MS management and research. Full article

The year 2025 marks the fifth anniversary of the COVID-19 pandemic, a crisis that profoundly disrupted secondary schools in England and intensified existing inequalities, including those experienced by LGBTQ+ students. Through an analysis of teacher interviews and the lens of intimate citizenship, this article explores how pandemic-driven changes, such as remote learning, school closures, and ‘social bubbles’, exposed the precariousness of LGBTQ+ inclusion and embodiment within educational institutions. The research highlights how cisheteronormativity was sustained through symbolic institutional compliance and cisheteronormative fragility, as LGBTQ+ inclusion was deprioritised through the erasure of safe spaces and restrictions on self-expression. While previous research has primarily focused on students’ well-being, this article centres the perspectives of teachers to consider what can be learned from their experiences to better support students in future crises. The pandemic revealed critical gaps in inclusion efforts, underscoring the urgent need for proactive strategies that extend beyond individual teacher initiatives or informal, hidden curriculum practices. The findings emphasise that LGBTQ+ visibility and inclusion must be structurally embedded within curricula, school policies, and teacher training and that the emotional and relational labour of inclusion must be institutionally recognised rather than left to individual educators. Full article

High-performance deep learning models require extensive computational resources and datasets, making their ownership protection a pressing concern. To address this challenge, we focus on advancing model security through robust watermarking mechanisms. In this work, we propose a novel deep neural network watermarking method that embeds ownership information directly within the image feature space. Unlike existing approaches that often suffer from low embedding success rates and significant performance degradation, our method leverages convolutional kernels with orthogonal preferences to extract multiperspective features, which are then linearly mapped at the output layer for watermark embedding. Furthermore, we introduce an orthogonal regularization constraint into the loss function to increase the watermark robustness. This constraint enforces orthogonality in both convolutional and fully connected layer weights, suppresses redundancy in hidden layer representations, and minimizes interference between the watermark and the model’s original feature space. Through these innovations, we significantly improve the embedding reliability and preserve model integrity. Experimental results obtained on ResNet-18 and ResNet-101 demonstrate a 100% watermark detection rate with less than 1% performance impact, underscoring the practical security value of our approach. Comparative analysis further validates that our method achieves superior harmlessness and effectiveness relative to state-of-the-art techniques. These contributions highlight the role of our work in strengthening intellectual property protection and the trustworthy deployment of deep learning models. Full article

The medical imaging domain frequently encounters the dual challenges of annotation scarcity and class imbalance. A critical issue lies in effectively extracting information from limited labeled data while mitigating the dominance of head classes. The existing approaches often overlook in-depth modeling of sample relationships in low-dimensional spaces, while rigid or suboptimal dynamic thresholding strategies in pseudo-label generation are susceptible to noisy label interference, leading to cumulative bias amplification during the early training phases. To address these issues, we propose a semi-supervised medical image classification framework combining labeled data-contrastive learning with class-adaptive pseudo-labeling (CLCP-MT), comprising two key components: the semantic discrimination enhancement (SDE) module and the class-adaptive pseudo-label refinement (CAPR) module. The former incorporates supervised contrastive learning on limited labeled data to fully exploit discriminative information in latent structural spaces, thereby significantly amplifying the value of sparse annotations. The latter dynamically calibrates pseudo-label confidence thresholds according to real-time learning progress across different classes, effectively reducing head-class dominance while enhancing tail-class recognition performance. These synergistic modules collectively achieve breakthroughs in both information utilization efficiency and model robustness, demonstrating superior performance in class-imbalanced scenarios. Extensive experiments on the ISIC2018 skin lesion dataset and Chest X-ray14 thoracic disease dataset validate CLCP-MT’s efficacy. With only 20% labeled and 80% unlabeled data, our framework achieves a 10.38% F1-score improvement on ISIC2018 and a 2.64% AUC increase on Chest X-ray14 compared to the baselines, confirming its effectiveness and superiority under annotation-deficient and class-imbalanced conditions. Full article

Border surveillance, as a critical component of national security, places increasingly stringent demands on the target perception capabilities of video monitoring systems, especially in wide-area and complex environments. To address the limitations of existing systems in low-confidence target detection and multi-camera collaboration, this paper proposes a novel visual enhancement method for cooperative control of multiple PTZ (Pan–Tilt–Zoom) cameras based on hierarchical reinforcement learning. The proposed approach establishes a hierarchical framework composed of a Global Planner Agent (GPA) and multiple Local Executor Agents (LEAs). The GPA is responsible for global target assignment, while the LEAs perform fine-grained visual enhancement operations based on the assigned targets. To effectively model the spatial relationships among multiple targets and the perceptual topology of the cameras, a graph-based joint state space is constructed. Furthermore, a graph neural network is employed to extract high-level features, enabling efficient information sharing and collaborative decision-making among cameras. Experimental results in simulation environments demonstrate the superiority of the proposed method in terms of target coverage and visual enhancement performance. Hardware experiments further validate the feasibility and robustness of the approach in real-world scenarios. This study provides an effective solution for multi-camera cooperative surveillance in complex environments. Full article

Anomaly detection of catenary support components (CSCs) is an important component in railway condition monitoring systems. However, because the abnormal features of CSCs loosening are not obvious, and the current CNN models and visual Transformer models have problems such as limited remote modeling capabilities and secondary computational complexity, it is difficult for existing deep learning anomaly detection methods to effectively exert their performance. The state space model (SSM) represented by Mamba is not only good at long-range modeling, but also maintains linear computational complexity. In this paper, using the state space model (SSM), we proposed a new visual state space reconstruction network (VSM-UNet) for the detection of CSC loosening anomalies. First, based on the structure of UNet, a visual state space block (VSS block) is introduced to capture extensive contextual information and multi-scale features, and an asymmetric encoder–decoder structure is constructed through patch merging operations and patch expanding operations. Secondly, the CBAM attention mechanism is introduced between the encoder–decoder structure to enhance the model’s ability to focus on key abnormal features. Finally, a stable abnormality score calculation module is designed using MLP to evaluate the degree of abnormality of components. The experiment shows that the VSM-UNet model, learning strategy and anomaly score calculation method proposed in this article are effective and reasonable, and have certain advantages. Specifically, the proposed method framework can achieve an AUROC of 0.986 and an FPS of 26.56 in the anomaly detection task of looseness on positioning clamp nuts, U-shaped hoop nuts, and cotton pins. Therefore, the method proposed in this article can be effectively applied to the detection of CSCs abnormalities. Full article

A fundamental limitation of maximum likelihood and Bayesian methods under model misspecification is that the asymptotic covariance matrix of the pseudo-true parameter vector ${\mathsf{\theta }}_{*}$ is not the inverse of the Fisher information, but rather the sandwich covariance matrix ${\displaystyle \frac{1}{n}}{\mathbf{A}}_{*}^{-1}{\mathbf{B}}_{*}^{\phantom{-1}}{\mathbf{A}}_{*}^{-1}$, where ${\mathbf{A}}_{*}$ and ${\mathbf{B}}_{*}$ are the sensitivity and variability matrices, respectively, evaluated at ${\mathsf{\theta }}_{*}$ for training data record ${\omega }_1,\dots ,{\omega }_n$. This paper makes three contributions. First, we review existing approaches to robust posterior sampling, including the open-faced sandwich adjustment and magnitude- and curvature-adjusted Markov chain Monte Carlo (MCMC) simulation. Second, we introduce a new sandwich-adjusted MCMC method. Unlike existing approaches that rely on arbitrary matrix square roots, eigendecompositions or a single scaling factor applied uniformly across the parameter space, our method employs a parameter-dependent learning rate $\lambda \left(\mathsf{\theta }\right)$ that enables direction-specific tempering of the likelihood. This allows the sampler to capture directional asymmetries in the sandwich distribution, particularly under model misspecification or in small-sample regimes, and yields credible regions that remain valid when standard Bayesian inference underestimates uncertainty. Third, we propose information-theoretic diagnostics for quantifying model misspecification, including a strictly proper divergence score and scalar summaries based on the Frobenius norm, Earth mover’s distance, and the Herfindahl index. These principled diagnostics complement residual-based metrics for model evaluation by directly assessing the degree of misalignment between the sensitivity and variability matrices, ${\mathbf{A}}_{*}$ and ${\mathbf{B}}_{*}$. Applications to two parametric distributions and a rainfall-runoff case study with the Xinanjiang watershed model show that conventional Bayesian methods systematically underestimate uncertainty, while the proposed method yields asymptotically valid and robust uncertainty estimates. Together, these findings advocate for sandwich-based adjustments in Bayesian practice and workflows. Full article

Understanding who makes up online affinity spaces as well as how information flows within those spaces is important as more people access news, research topics, collaborate with others, and entertain themselves. During a month-long period in summer 2021, we collected 100,000 tweets from 53,311 Twitter users who used the hashtags #ScienceTwitter, #SciComm, and #AcademicTwitter. We then classified users and determined the type of social network they formed. Scientists, the public, and educators formed this affinity space. They built connections by initiating activities and interacting with others, which created a Community Clusters social network structure, characterized by several medium-sized groups of closely connected users and a fair number of isolates. All three categories of people were in positions of influence in this network leading and controlling the conversations. The results show that scientists, the public, and educators share the space and contribute to communication in this online world. This research is important as it illustrates that online affinity spaces about scientific topics are not solely spaces for scientists to communicate but rather act as spaces where people with varied expertise can exchange ideas and learn from one another. Full article

In high-density cities like Hong Kong, green spaces are often characterized by fragmentation and uneven spatial distribution, which negatively impacts their accessibility and equity. To address this issue, studies have proposed the use of informal green spaces (IGSs) as a supplementary component to formal urban green spaces (UGSs). However, the spatial delineation and quantitative analysis of IGSs remain challenging due to the lack of standardized identification and evaluation methods. Building upon the work of urban theorists Henry Lefebvre and Edward Soja, this study explores informal green spaces as third spaces. This study employed remote sensing and GIS technologies to systematically assess the spatial distribution and benefits of IGSs, categorizing them into four types: Urban Interstitial IGSs, Transitional IGSs, Fringe IGSs, and Riparian IGSs. Subsequently, an evaluation framework was constructed across ecological, social, and economic dimensions to quantify the overall value of IGSs. The results reveal that IGS significantly contributes to ecological regulation, social interaction, and economic potential, particularly in urban areas with limited green resources. This demonstrates that IGSs can serve as a vital complement to formal urban green spaces, playing a key role in alleviating green space inequity, enhancing urban livability, and promoting sustainability. Furthermore, this study provides a scientific foundation for precise identification, benefit assessment, and optimized management of IGSs, supporting effective integration and rational utilization in future urban planning. Full article

This study reviews the role of Child-Friendly Green Spaces (CFGS) in supporting children’s psychological, physical, and educational recovery following natural disasters. The main research question guiding this review is the following: how do CFGS contribute to holistic child well-being and resilience in disaster-affected contexts, and what barriers and strategies influence their effective integration into recovery frameworks? Employing a rigorous literature review methodology, we synthesized interdisciplinary evidence from environmental psychology, urban planning, public health, and education, encompassing studies published between 2000 and 2024. Findings demonstrate that CFGS significantly reduce trauma-related symptoms such as anxiety, depression, and post-traumatic stress, promotes physical health through active play, and foster educational engagement by improving concentration, attendance, and informal learning opportunities. Furthermore, CFGS contribute directly to multiple Sustainable Development Goals, particularly SDG 3 (Good Health and Well-being), SDG 4 (Quality Education), and SDG 11 (Sustainable Cities and Communities). Despite these advantages, CFGS are often overlooked in formal disaster recovery planning due to prioritization of immediate relief, financial and logistical challenges, and socio-cultural factors. To address these challenges, this study proposes a participatory, culturally sensitive framework for CFGS implementation, which integrates inclusive design, multi-sector collaboration, and ongoing monitoring and evaluation. Grounded in theoretical perspectives such as the Biophilia Hypothesis, Bronfenbrenner’s Ecological Systems Theory, and restorative environments, CFGS are reframed as critical infrastructures for children’s holistic recovery and resilience. The findings underscore the urgent need to embed CFGS within disaster recovery and urban planning policies to promote child-centered, sustainable community development. Full article

The growing reliance on satellite-based infrastructures for communication, navigation, defense, and environmental monitoring has magnified the urgency of securing Space Information Networks (SINs) against cyber threats. This paper presents a comprehensive review of the vulnerabilities, threat vectors, and advanced countermeasures impacting SINs. Key vulnerabilities, including system complexity, use of Commercial Off-the-Shelf (COTS) components, lack of standardized security frameworks, and emerging quantum threats, are critically analyzed. This paper classifies cyber threats into active and passive categories, highlighting real-world case studies such as Denial-of-Service attacks, message modification, eavesdropping, and satellite transponder hijacking. A detailed survey of countermeasures follows, focusing on AI-driven intrusion detection, federated learning approaches, deep learning techniques, random routing algorithms, and quantum-resistant encryption. This study emphasizes the pressing need for integrated, resilient, and proactive security architectures tailored to the unique constraints of space systems. It concludes by identifying research gaps and recommending future directions to enhance the resilience of SINs against evolving cyber threats in an increasingly contested space environment. Full article