Search Results (1,558)

Facial beauty prediction (FBP) is a cutting-edge task in deep learning that aims to equip machines with the ability to assess facial attractiveness in a human-like manner. In human perception, facial beauty is strongly associated with facial symmetry, where balanced structures often reflect aesthetic appeal. Leveraging symmetry provides an interpretable prior for FBP and offers geometric constraints that enhance feature learning. However, existing multi-task FBP models still face challenges such as limited annotated data, insufficient frequency–temporal modeling, and feature conflicts from task heterogeneity. The Mamba model excels in feature extraction and long-range dependency modeling but encounters difficulties in parameter sharing and computational efficiency in multi-task settings. In contrast, mixture-of-experts (MoE) enables adaptive expert selection, reducing redundancy while enhancing task specialization. This paper proposes MoMamba, a multi-task decoder combining Mamba’s state-space modeling with MoE’s dynamic routing to improve multi-scale feature fusion and adaptability. A detail enhancement module fuses high- and low-frequency components from discrete cosine transform with temporal features from Mamba, and a state-aware MoE module incorporates low-rank expert modeling and task-specific decoding. Experiments on SCUT-FBP and SCUT-FBP5500 demonstrate superior performance in both classification and regression, particularly in symmetry-related perception modeling. Full article

Prosopis cineraria (L.) Druce is a keystone tree species in the arid and semi-arid regions of West and South Asia, with critical ecological, cultural, and conservation significance. In the United Arab Emirates (UAE) and other regions of the Arabian Peninsula, this beneficial tree is called Ghaf. Despite its importance, genomic resources and population-level diversity data for the tree remain limited. Here, we present the first comprehensive population genomics study of Ghaf based on whole-genome resequencing of 204 individual trees collected across the UAE. Following Single-Nucleotide Polymorphism (SNP) discovery and stringent filtering, we analyzed 57,183 high-quality LD-pruned SNPs to assess population structure, diversity, and gene flow. Principal component analysis (PCA), sparse non-negative matrix factorization (sNMF), and discriminant analysis of principal components (DAPC) revealed four well-defined genetic clusters, broadly corresponding to geographic origins. The genetic diversity varied significantly among the groups, with observed heterozygosity (Ho), inbreeding coefficients (F), and nucleotide diversity ($\pi$) showing strong population-specific trends. Genome-wide fixation index F_ST scans identified multiple highly differentiated genomic regions, enriched for genes involved in stress response, transport, and signaling. Functional enrichment using Gene Ontology (GO), Kyoto Encyclopedia of Genes and Genomes (KEGG), and Pfam annotations indicated overrepresentation of protein kinase activity, ATP binding, and hormone signaling pathways. TreeMix analysis revealed gene flow into one of the genetic clusters from both others, suggesting historical admixture and geographic connectivity. This work provides foundational insights into the population genomic profile of P. cineraria, supporting conservation planning, restoration strategies, and long-term genetic monitoring in arid ecosystems. Full article

Background: Accurate annotation of gene isoforms remains one of the major obstacles in translating genomic data into meaningful biological insight. Laminin-binding integrins, particularly integrin α6 (ITGA6), exemplify this challenge through their complex splicing patterns. The rare ITGA6 X1X2 isoform, generated by the alternative inclusion of exons X1 and X2 within the β-propeller domain, has remained poorly characterized despite decades of integrin research. Methods: We combined comparative genomics across primates with targeted re-alignment to assess exon conservation and annotation fidelity; analyzed RNA-seq for exon-level usage; applied splice-site prediction to evaluate inclusion potential; surveyed cancer mutation resources for exon-specific variants; and used structural/disorder modeling to infer effects on the β-propeller. Results: Exon X2 is conserved at the genomic level but inconsistently annotated, reflecting the limitations of current annotation pipelines rather than genuine evolutionary loss. RNA-seq analyses reveal low but detectable expression of X2, consistent with weak splice site predictions that suggest strict regulatory control and condition-specific expression. Despite its rarity, recurrent mutations in exon X2 are reported in cancer datasets, implying possible roles in disease. Structural modeling further indicates that X2 contributes to a flexible, disordered region within the β-propeller domain, potentially influencing laminin binding or β-subunit dimerization. Conclusions: Altogether, our results suggest that ITGA6 X1X2 could be a rare, tightly regulated isoform with potential functional and pathological relevance. Full article

This study investigates instances of conflation and misattribution in the transmission of three Chinese Buddhist catalogues that share the title Zhongjing mulu 眾經目錄 (Catalogue of Various Scriptures), attributed, respectively, to Fajing 法經, Yancong 彥琮, and Jingtai 靜泰 during the Sui and Tang dynasties. Although these catalogues differ in structure, doctrinal classification, and historical context, their identical titles and overlapping content may have led to instances of conflation in the editorial processes of later Buddhist canons. This phenomenon is revealed and analyzed in the present study. Drawing primarily on the phonetic glosses appended to fascicles (suihan yinshi 隨函音釋) in the Pilu Canon 毗盧藏 and examining the bibliographic entries and marginal annotations referencing these catalogues in other editions, the study conducts a philological comparison with sources such as the Qisha 磧砂, Sixi 思溪, and Hongwu Southern Canons 洪武南藏. It identifies specific cases of misattribution, annotation displacement, and the merging of catalogue content without clear attribution. The findings suggest that ambiguity in catalogue entries and textual transmission resulted in instances where the three Zhongjing mulu catalogues were not clearly distinguished in later canons and modern databases. The article contributes to a clearer understanding of the editorial history and philological challenges involved in the formation of the Chinese Buddhist canon. Full article

Accurate and efficient detection of underwater targets in sonar imagery is critical for applications such as marine exploration, infrastructure inspection, and autonomous navigation. However, sonar-based object detection remains challenging due to low resolution, high noise, cluttered backgrounds, and the scarcity of annotated data. To address these issues, we propose UWS-YOLO, a novel detection framework specifically designed for underwater sonar images. The model integrates three key innovations: (1) a C2F-Ortho module that enhances multi-scale feature representation through orthogonal channel attention, improving sensitivity to small and low-contrast targets; (2) a DySnConv module that employs Dynamic Snake Convolution to adaptively capture elongated and irregular structures such as pipelines and cables; and (3) a cross-modal transfer learning strategy that pre-trains on large-scale optical underwater imagery before fine-tuning on sonar data, effectively mitigating overfitting and bridging the modality gap. Extensive evaluations on real-world sonar datasets demonstrate that UWS-YOLO achieves a mAP@0.5 of 87.1%, outperforming the YOLOv8n baseline by 3.5% and seven state-of-the-art detectors in accuracy while maintaining real-time performance at 158 FPS with only 8.8 GFLOPs. The framework exhibits strong generalization across datasets, robustness to noise, and computational efficiency on embedded devices, confirming its suitability for deployment in resource-constrained underwater environments. Full article

A 9.4T brain MRI is the highest resolution MRI scanner in the public market. It offers submillimeter brain imaging with exceptional anatomical detail, making it one of the most powerful tools for detecting subtle structural changes associated with neurological conditions. Current segmentation models are optimized for lower-field MRI (1.5T–3T), and they struggle to perform well on 9.4T data. In this study, we present the GA-MS-UNet++, the world’s first deep learning-based model specifically designed for 9.4T brain MRI segmentation. Our model integrates multi-scale residual blocks, gated skip connections, and spatial channel attention mechanisms to improve both local and global feature extraction. The model was trained and evaluated on 12 patients in the UltraCortex 9.4T dataset and benchmarked against four leading segmentation models (Attention U-Net, Nested U-Net, VDSR, and R2UNet). The GA-MS-UNet++ achieved a state-of-the-art performance across both evaluation sets. When tested against manual, radiologist-reviewed ground truth masks, the model achieved a Dice score of 0.93. On a separate test set using SynthSeg-generated masks as the ground truth, the Dice score was 0.89. Across both evaluations, the model achieved an overall accuracy of 97.29%, precision of 90.02%, and recall of 94.00%. Statistical validation using the Wilcoxon signed-rank test (p < 1 × 10⁻⁵) and Kruskal–Wallis test (H = 26,281.98, p < 1 × 10⁻⁵) confirmed the significance of these results. Qualitative comparisons also showed a near-exact alignment with ground truth masks, particularly in areas such as the ventricles and gray–white matter interfaces. Volumetric validation further demonstrated a high correlation (R² = 0.90) between the predicted and ground truth brain volumes. Despite the limited annotated data, the GA-MS-UNet++ maintained a strong performance and has the potential for clinical use. This algorithm represents the first publicly available segmentation model for 9.4T imaging, providing a powerful tool for high-resolution brain segmentation and driving progress in automated neuroimaging analysis. Full article

Timely detection of road surface defects such as cracks and potholes is critical for ensuring traffic safety and reducing infrastructure maintenance costs. While recent advances in image-based deep learning techniques have shown promise for automated road defect detection, existing models remain limited to closed-set detection settings, making it difficult to recognize newly emerging or fine-grained defect types. To address this limitation, we propose an attribute-aware open-vocabulary crack detection (AOVCD) framework, which leverages the alignment capability of pretrained vision–language models to generalize beyond fixed class labels. In this framework, crack types are represented as combinations of visual attributes, enabling semantic grounding between image regions and natural language descriptions. To support this, we extend the existing PPDD dataset with attribute-level annotations and incorporate a multi-label attribute recognition task as an auxiliary objective. Experimental results demonstrate that the proposed AOVCD model outperforms existing baselines. In particular, compared to CLIP-based zero-shot inference, the proposed model achieves approximately a 10-fold improvement in average precision (AP) for novel crack categories. Attribute classification performance—covering geometric, spatial, and textural features—also increases by 40% in balanced accuracy (BACC) and 23% in AP. These results indicate that integrating structured attribute information enhances generalization to previously unseen defect types, especially those involving subtle visual cues. Our study suggests that incorporating attribute-level alignment within a vision–language framework can lead to more adaptive and semantically grounded defect recognition systems. Full article

Plant melatonin is widely recognized as a pleiotropic regulator. As a growth-regulating hormone, it extensively participates in various growth and developmental processes and has significant functions in stress responses and disease resistance. Plant melatonin is synthesized primarily through the catalytic actions of five enzymes: TDC (tryptophan decarboxylase), T5H (tryptamine-5-hydroxylase), SNAT (serotonin N-acetyltransferase), ASMT (N-acetylserotonin methyltransferase), and COMT (caffeic acid-O-methyltransferase). There are multiple genes for each of these five enzymes in citrus genomes, however, with the exception of COMT5—whose function has recently been elucidated—and SNAT, which has only been preliminarily identified, the remaining genes have not been unequivocally characterized or functionally annotated. Hence, we carried out a genome-wide analysis of melatonin biosynthesis enzyme-related gene families in trifoliate orange (Poncirus trifoliata), one of the most common citrus rootstock varieties. Through bioinformatics approaches, we identified 96 gene family members encoding melatonin biosynthetic enzymes and characterized their protein sequence properties, phylogenetic relationships, gene structures, chromosomal distributions, and promoter cis-acting elements. Furthermore, by analyzing expression patterns in different tissues and under various stresses, we identified multiple stress-responsive melatonin synthase genes. These genes likely participate in melatonin synthesis under adverse conditions, thereby enhancing stress adaptation. Specifically, PtCOMT5, PtASMT11, and PtTDC9 were significantly induced by low temperature; PtSNAT1, PtSNAT14, PtSNAT18, and PtTDC10 were markedly responsive to drought; and PtASMT15, PtSNAT15, PtASMT16, and PtSNAT3 were strongly induced by ABA. Among them, PtASMT23 expression was induced up to 120-fold under low temperature, while PtSNAT18 showed over 100-fold upregulation under dehydration treatment. These findings strongly suggest that PtASMT23 and PtSNAT18 play critical roles in regulating melatonin biosynthesis in response to cold and drought stress, respectively. Collectively, these findings pinpoint novel genetic targets for enhancing stress resilience in citrus breeding programs and lay the foundation for the functional characterization of specific melatonin biosynthesis pathway gene family members in citrus and other horticultural crop species. Full article

Background: Segmenting nerve fibres in histological images is a tricky job because of how much the tissue looks can change. Modern neural network architectures, including U-Net and transformers, demonstrate varying degrees of effectiveness in this area. The aim of this study is to conduct a comparative analysis of the SegFormer, VGG-UNet, and FabE-Net models in terms of segmentation quality and speed. Methods: The training sample consisted of more than 75,000 pairs of images of different tissues (original slice and corresponding mask), scaled from 1024 × 1024 to 224 × 224 pixels to optimise computations. Three neural network architectures were used: the classic VGG-UNet, FabE-Net with attention and global context perception blocks, and the SegFormer transformer model. For an objective assessment of the quality of the models, expert validation was carried out with the participation of four independent pathologists, who evaluated the quality of segmentation according to specified criteria. Quality metrics (precision, recall, F1-score, accuracy) were calculated as averages based on the assessments of all experts, which made it possible to take into account variability in interpretation and increase the reliability of the results. Results: SegFormer achieved stable stabilisation of the loss function faster than the other models—by the 20–30th epoch, compared to 45–60 epochs for VGG-UNet and FabE-Net. Despite taking longer to train per epoch, SegFormer produced the best segmentation quality, with the following metrics: precision 0.84, recall 0.99, F1-score 0.91 and accuracy 0.89. It also annotated a complete histological section in the fastest time. Visual analysis revealed that, compared to other models, which tended to produce incomplete or excessive segmentation, SegFormer more accurately and completely highlights nerve structures. Conclusions: Using attention mechanisms in SegFormer compensates for morphological variability in tissues, resulting in faster and higher-quality segmentation. Image scaling does not impair training quality while significantly accelerating computational processes. These results confirm the potential of SegFormer for practical use in digital pathology, while also highlighting the need for high-precision, immunohistochemistry-informed labelling to improve segmentation accuracy. Full article

The early detection of fire and smoke is essential for mitigating human casualties, property damage, and environmental impact. Traditional sensor-based and vision-based detection systems frequently exhibit high false alarm rates, delayed response times, and limited adaptability in complex or dynamic environments. Recent advances in deep learning and computer vision have enabled more accurate, real-time detection through the automated analysis of flame and smoke patterns. This paper presents a comprehensive review of deep learning techniques for fire and smoke detection, with a particular focus on convolutional neural networks (CNNs), object detection frameworks such as YOLO and Faster R-CNN, and spatiotemporal models for video-based analysis. We examine the benefits of these approaches in terms of improved accuracy, robustness, and deployment feasibility on resource-constrained platforms. Furthermore, we discuss current limitations, including the scarcity and diversity of annotated datasets, susceptibility to false alarms, and challenges in generalization across varying scenarios. Finally, we outline promising research directions, including multimodal sensor fusion, lightweight edge AI implementations, and the development of explainable deep learning models. By synthesizing recent advancements and identifying persistent challenges, this review provides a structured foundation for the design of next-generation intelligent fire detection systems. Full article

Accurate 3D semantic occupancy perception is critical for autonomous driving, enabling robust navigation in unstructured environments. While vision-based methods suffer from depth inaccuracies and lighting sensitivity, LiDAR-based approaches face challenges due to sparse data and dependence on expensive manual annotations. This work proposes LiGaussOcc, a novel self-supervised framework for dense LiDAR-based 3D semantic occupancy prediction. Our method first encodes LiDAR point clouds into voxel features and addresses sparsity via an Empty Voxel Inpainting (EVI) module, refined by an Adaptive Feature Fusion (AFF) module. During training, a Gaussian Primitive from Voxels (GPV) module generates parameters for 3D Gaussian Splatting, enabling efficient rendering of 2D depth and semantic maps. Supervision is achieved through photometric consistency across adjacent camera views and pseudo-labels from vision–language models, eliminating manual 3D annotations. Evaluated on the nuScenes-OpenOccupancy benchmark, LiGaussOcc achieved performance competitive with 30.4% Intersection over Union (IoU) and 14.1% mean Intersection over Union (mIoU). It reached 91.6% of the performance of the fully supervised LiDAR-based L-CONet, while completely eliminating the need for costly and labor-intensive manual 3D annotations. It excelled particularly in static environmental classes, such as drivable surfaces and man-made structures. This work presents a scalable, annotation-free solution for LiDAR-based 3D semantic occupancy perception. Full article

Automated essay scoring (AES) has become an essential tool in educational assessment. However, applying AES to the Arabic language presents notable challenges, primarily due to the lack of labeled datasets. This data scarcity hampers the development of reliable machine learning models and slows progress in Arabic natural language processing for educational use. While manual annotation by human experts remains the most accurate method for essay evaluation, it is often too costly and time-consuming to create large-scale datasets, especially for low-resource languages like Arabic. In this work, we introduce a human–AI collaborative framework designed to overcome the shortage of scored Arabic essays. Leveraging QAES, a high-quality annotated dataset, our approach uses Large Language Models (LLMs) to generate multidimensional essay evaluations across seven key writing traits: Relevance, Organization, Vocabulary, Style, Development, Mechanics, and Structure. To ensure accuracy and consistency, we design prompting strategies and validation procedures tailored to each trait. This system is then applied to two unannotated Arabic essay datasets: ZAEBUC and QALB. As a result, we introduce ZaQQ, a newly annotated dataset that merges ZAEBUC, QAES, and QALB. Our findings demonstrate that human–AI collaboration can significantly enhance the availability of labeled resources without compromising assessment quality. The proposed framework serves as a scalable and replicable model for addressing data annotation challenges in low-resource languages and supports the broader goal of expanding access to automated educational assessment tools where expert evaluation is limited. Full article

UAVThreatBench introduces the first structured benchmark for evaluating large language models in cybersecurity threat identification for unmanned aerial vehicles operating within industrial indoor settings, aligned with the European Radio Equipment Directive. The benchmark consists of 924 expert-curated industrial scenarios, each annotated with five cybersecurity threats, yielding a total of 4620 threats mapped to directive articles on network and device integrity, personal data and privacy protection, and prevention of fraud and economic harm. Seven state-of-the-art models from the OpenAI GPT family and the LLaMA family were systematically assessed on a representative subset of 100 scenarios from the UAVThreatBench dataset. The evaluation applied a fuzzy matching threshold of 70 to compare model-generated threats against expert-defined ground truth. The strongest model identified nearly nine out of ten threats correctly, with close to half of the scenarios achieving perfect alignment, while other models achieved lower but still substantial alignment. Semantic error analysis revealed systematic weaknesses, particularly in identifying availability-related threats, backend-layer vulnerabilities, and clause-level regulatory mappings. UAVThreatBench therefore establishes a reproducible foundation for regulatory-compliant cybersecurity threat identification in safety-critical unmanned aerial vehicle environments. The complete benchmark dataset and evaluation results are openly released under the MIT license through a dedicated online repository. Full article

Bacteriophages, or phages, are sophisticated nanomachines that efficiently infect bacteria. Their infection of lactic acid bacteria (LAB) used in fermentation can lead to significant industrial losses. Among phages that infect monoderm bacteria, those with siphovirion morphology characterized by a long, non-contractile tail are predominant. The initial stage of phage infection involves precise host recognition and binding. To achieve this, phages feature host adhesion devices (HADs) located at the distal end of their tails, which have evolved to recognize specific proteinaceous or saccharidic receptors on the host cell wall. Ceduovirus represents a group of unique lytic siphophages that specifically infect the LAB Lactococcus lactis by targeting proteinaceous receptors. Despite having compact genomes, most of their structural genes are poorly annotated and the architecture and function of their HADs remain unknown. Here we used AlphaFold3 to explore the Ceduovirus HADs and their interaction with the host. We show that Ceduovirus HADs exhibit unprecedented features among bacteriophages infecting Gram⁺, share structural similarities with bacterial secretion system VI, and combine both saccharide and protein-binding modules. Moreover, we could annotate the majority of Ceduovirus genes encoding structural proteins by leveraging their predicted structures, highlighting AlphaFold’s significant contribution to phage genome annotation. Full article

Industry 4.0 produces large volumes of sensor and machine data, offering new possibilities for manufacturing analytics but also creating challenges in combining domain knowledge with visual analysis. We present a systematic review of 13 peer-reviewed knowledge-assisted visual analytics (KAVA) systems published between 2014 and 2024, following PRISMA guidelines for the identification, screening, and inclusion processes. The survey is organized around six predefined building blocks, namely, user group, industrial domain, visualization, knowledge, data and machine learning, with a specific emphasis on the integration of knowledge and visualization in the reviewed studies. We find that ontologies, taxonomies, rule sets, and knowledge graphs provide explicit representations of expert understanding, sometimes enriched with annotations and threshold specifications. These structures are stored in RDF or graph databases, relational tables, or flat files, though interoperability is limited, and post-design contributions are not always persisted. Explicit knowledge is visualized through standard and specialized techniques, including thresholds in time-series plots, annotated dashboards, node–link diagrams, customized machine views from ontologies, and 3D digital twins with expert-defined rules. Line graphs, bar charts, and scatterplots are the most frequently used chart types, often augmented with thresholds and annotations derived from explicit knowledge. Recurring challenges include fragmented storage, heterogeneous data and knowledge types, limited automation, inconsistent validation of user input, and scarce long-term evaluations. Addressing these gaps will be essential for developing adaptable, reusable KAVA systems for industrial analytics. Full article