Search Results (96)

Oriented object detection constitutes a fundamental yet challenging task in Artificial Intelligence of Things (AIoT)-enabled maritime surveillance, where real-time processing of dense visual streams is imperative. However, existing detectors suffer from three critical limitations: sequential attention mechanisms that fail to capture coupled spatial–channel dependencies, unconstrained deformable convolutions that yield unstable predictions for elongated vessels, and center-based distance metrics that ignore angular alignment in sample assignment. To address these challenges, we propose JAOSD (Joint Attention-based Oriented Ship Detection), an anchor-free framework incorporating three novel components: (1) a joint attention module that processes spatial and channel branches in parallel with coupled fusion, (2) an adaptive geometric convolution with two-stage offset refinement and spatial consistency regularization, and (3) an orientation-aware Adaptive Sample Selection strategy based on corner-aware distance metrics. Extensive experiments on three benchmarks demonstrate that JAOSD achieves state-of-the-art performance—94.74% mAP on HRSC2016, 92.43% AP₅₀ on FGSD2021, and 80.44% mAP on DOTA v1.0—while maintaining real-time inference at 42.6 FPS. Cross-domain evaluation on the Singapore Maritime Dataset further confirms robust generalization capability from aerial to shore-based surveillance scenarios without domain adaptation. Full article

Salvia miltiorrhiza Bunge is a traditional Chinese medicinal plant whose roots are rich in water-soluble phenolic acids. Rosmarinic acid and salvianolic acid B are representative components that confer antibacterial, antioxidant, and cardio-cerebrovascular protective activities. However, these metabolites often accumulate at low and unstable levels in planta, which limits their efficient development and use. This review summarises recent advances in understanding salvianolic acid biosynthesis and its transcriptional regulation in S. miltiorrhiza. Current evidence supports a coordinated pathway composed of the phenylpropanoid route and a tyrosine-derived branch, which converge to generate rosmarinic acid and subsequently more complex derivatives through oxidative coupling reactions. Key findings on transcription factor families that fine-tune pathway flux by regulating core structural genes are synthesised. Representative positive regulators such as SmMYB111, SmMYC2, and SmTGA2 activate key nodes (e.g., PAL, TAT/HPPR, RAS, and CYP98A14) to promote phenolic acid accumulation. Conversely, negative regulators such as SmMYB4 and SmMYB39 repress pathway genes and/or interfere with activator complexes. Major regulatory features include hormone-inducible signalling, cooperative regulation through transcription factor complexes, and emerging post-transcriptional and post-translational controls. Future directions and challenges are discussed, including overcoming regulatory redundancy and strong spatiotemporal specificity of transcriptional control. Integrating spatial and single-cell omics with functional genomics (e.g., genome editing and rational TF stacking) is highlighted as a promising strategy to enable predictive metabolic engineering for the stable, high-yield production of salvianolic acid-type compounds. Full article

Change detection plays a crucial role in geological disaster tasks such as landslide identification, post-earthquake building reconstruction assessment, and unstable rock mass monitoring. However, real-world scenarios often pose significant challenges, including complex surface backgrounds, illumination and seasonal variations between temporal phases, and diverse change patterns. To address these issues, this paper proposes a multi-stage model for geological disaster change detection, termed MSMCD, which integrates strategies of global dependency modeling, local difference enhancement, edge constraint, and frequency-domain fusion to achieve precise perception and delineation of change regions. Specifically, the model first employs a DualTimeMamba (DTM) module for two-dimensional selective scanning state-space modeling, explicitly capturing cross-temporal long-range dependencies to learn robust shared representations. Subsequently, a Multi-Scale Perception (MSP) module highlights fine-grained differences to enhance local discrimination. The Edge–Change Interaction (ECI) module then constructs bidirectional coupling between the change and edge branches with edge supervision, improving boundary accuracy and geometric consistency. Finally, the Frequency-domain Change Fusion (FCF) module performs weighted modulation on multi-layer, channel-joint spectra, balancing low-frequency structural consistency with high-frequency detail fidelity. Experiments conducted on the landslide change detection dataset (GVLM-CD), post-earthquake building change detection dataset (WHU-CD), and a self-constructed unstable rock mass change detection dataset (TGRM-CD) demonstrate that MSMCD achieves state-of-the-art performance across all benchmarks. These results confirm its strong cross-scenario generalization ability and effectiveness in multiple geological disaster tasks. Full article

Many studies have investigated tree-contact arcing ground faults. However, the effects of branch moisture content and wind speed are still not fully understood. Therefore, this paper addresses the wildfire risk caused by tree-contact arc grounding faults in distribution networks. A 10 kV distribution-line tree-contact arcing fault test platform is built. A two-dimensional multi-physics plasma model is also developed based on magnetohydrodynamics. Experiments and simulations are combined. The effects of wind speed, branch moisture content, and conductor type on arc evolution and fault characteristics are systematically studied. The results show that higher wind speed causes stronger arc-column deformation. The fault current contains more high-frequency components and sharp spikes. At 9 m/s and 16 m/s, the fault current shows strong disturbances and much lower stability. Higher moisture content increases the branch conductivity indirectly. It strengthens the carbonized conductive path and helps sustain stable arcing. For the high-moisture sample (64%), the current waveform is smooth, and its amplitude increases monotonically with fault development. For the low-moisture sample (30%), the current amplitude decreases, and spikes become more frequent. The arc tends to extinguish and reignite repeatedly, which indicates an unstable discharge process. The simulations further reveal the coupling between the arc-root temperature field and the airflow field under different wind speeds and conductivities. They also show clear differences in temperature evolution between bare conductors and insulated conductors. These findings provide experimental evidence and simulation support for identifying wildfires initiated by tree-contact arcing faults. Full article

This study investigates the impact of eddy viscosity on equatorially trapped waves and the instability of the background shear in a simple barotropic–baroclinic model. It is the first study to include eddy viscosity in the study of tropical wave dynamics. This study also unifies the study of baroclinic and barotropic instabilities by using a coupled barotopic and baroclinic model of the tropical atmosphere. Linear wave theory is combined with a systematic Galerkin projection of the baroclinic dynamical fields onto parabolic cylinder functions. This study investigates varying shear strengths, eddy viscosities, and their combined effects. In the absence of shear, baroclinic and barotropic waves decouple. The baroclinic waves themselves separate into triads, forming the equatorially trapped wave modes known as Matsuno waves. However, when a strong eddy viscosity is included, the structure and propagation characteristics of these equatorial waves are significantly altered. Different wave types interact, leading to strong mixing in the meridional direction and coupling between meridional modes. This coupling destroys the Matsuno mode separation and offers pathways for these waves to couple and interact with one another. These results suggest that viscosity does not simply suppress growth; it may also reshape the propagation characteristics of unstable modes. In the presence of a background shear, some wave modes become unstable, and barotropic and baroclinic waves are coupled. Without eddy viscosity, instability begins with small scale and slowly propagating modes, at arbitrary small shear strengths. This instability manifests as an ultra-violet catastrophe. As the shear strength increases, the catastrophic instability at small scales expands to high-frequency waves. Meanwhile, instability peaks emerge at synoptic and planetary scales along several Rossby mode branches. When a small eddy viscosity is reintroduced, the catastrophic small-scale instabilities disappear, while the large-scale Rossby wave instabilities persist. These westward-moving modes exhibit a mixed barotropic–baroclinic structure with signature vortices straddling the equator. Some vortices are centered close to the equator, while others are far away. Some waves resemble synoptic-scale monsoon depressions and tropical easterly waves, while others operate on the planetary scale and present elongated shapes reminiscent of atmospheric-river flow patterns. Full article

High-quality test cases are vital for ensuring software reliability and security. However, existing symbolic execution tools generally rely on single-path search strategies, have limited feature extraction capability, and exhibit unstable model predictions. These limitations make them prone to local optima in complex or cross-scenario tasks and hinder their ability to balance testing quality with execution efficiency. To address these challenges, this paper proposes a Deep Active Ensemble Learning Framework for symbolic execution path exploration. During training, the framework integrates active learning with ensemble learning to reduce annotation costs and improve model robustness, while constructing a heterogeneous model pool to leverage complementary model strengths. In the testing stage, a dynamic ensemble mechanism based on sample similarity adaptively selects the optimal predictive model to guide symbolic path exploration. In addition, a gated graph neural network is employed to extract structural and semantic features from the control flow graph, improving program behavior understanding. To balance efficiency and coverage, a dynamic sliding window mechanism based on branch density enables real-time window adjustment under path complexity awareness. Experimental results on multiple real-world benchmark programs show that the proposed framework detects up to 16 vulnerabilities and achieves a cumulative 27.5% increase in discovered execution paths in hybrid fuzzing. Furthermore, the dynamic sliding window mechanism raises the F1 score to 93%. Full article

Spinach (Spinacia oleracea L.) is a commonly consumed crop with a diverse array of unique flavonoids. These molecules likely contribute to the health benefits associated with spinach consumption. However, little is known about the genetic diversity of these molecules, their bioaccessibility, and the heritability of these traits. We assembled a diversity panel of 30 F₁ and open-pollinated spinach accessions and cultivated them under controlled conditions over two periods. Quantification of 39 flavonoids revealed that their concentration is largely influenced by environmental factors, and at least two divergent branches in the spinach flavonoid biosynthesis pathway may exist. Despite generally similar trends in the amounts of major flavonoids, open-pollinated and F₁ varieties of spinach could be distinguished based on the concentrations of minor flavonoid species. Broad-sense heritability estimates for absolute bioaccessibility accounted for more genetic variation than raw material content, suggesting that this trait is preferable for breeders seeking to alter the phytochemical profile of spinach. Lastly, we found that several spinach flavonoids are unstable under digestive conditions, which was made evident by the proportion of aglycones rising from 0.1% to approximately 15% of total flavonoids after digestion. Together, these data suggest that spinach flavonoid biosynthesis and bioaccessibility are complex and contextualize how these molecules may behave in vivo. Full article

Citrus Huanglongbing (HLB) is one of the most destructive diseases in the global citrus industry; its pathogen is transmitted primarily by the Asian citrus psyllid (ACP), Diaphorina citri Kuwayama, making timely monitoring and control of ACP populations essential. Real-world ACP monitoring faces several challenges, including tiny targets easily confused with the background, noise amplification and spurious detections caused by textures, stains, and specular glare on yellow-boards, unstable localization due to minute shifts of small boxes, and strict constraints on parameters, computation, and model size for long-term edge deployment. To address these challenges, we focus on the yellow-board ACP monitoring scenario and create the ACP Yellow Sticky Trap Dataset (ACP-YSTD), which standardizes background and acquisition procedures, covering common interference sources. The dataset consists of 600 images with 3837 annotated ACP, serving as a unified basis for training and evaluation. On the modeling side, we propose TGSP-YOLO11, an improved YOLO11-based detector: the detection head is reconfigured to the two scales P2 + P3 to match tiny targets and reduce redundant paths; Guided Scalar Fusion (GSF) is introduced on the high-resolution branch to perform constrained, lightweight scalar fusion that suppresses noise amplification; ShapeIoU is adopted for bounding-box regression to enhance shape characterization and alignment robustness for small objects; and Network Slimming is employed for channel-level structured pruning, markedly reducing parameters, FLOPs, and model size to satisfy edge deployment, without degrading detection performance. Experiments show that on the ACP-YSTD test set, TGSP-YOLO11 achieves precision 92.4%, recall 95.5%, and F1 93.9, with 392,591 parameters, a model size of 1.4 MB, and 6.0 GFLOPs; relative to YOLO11n, recall increases by 4.6%, F1 by 2.4, and precision by 0.2%, while the parameter count, model size, and computation decrease by 84.8%, 74.5%, and 4.8%, respectively. Compared to representative detectors (SSD, RT-DETR, YOLOv7-tiny, YOLOv8n, YOLOv9-tiny, YOLOv10n, YOLOv12n, YOLOv13n), TGSP-YOLO11 improves recall by 33.9%, 19.0%, 8.5%, 10.1%, 6.3%, 4.6%, 6.9%, and 5.7%, respectively, and F1 by 19.9, 14.9, 5.1, 6.0, 2.6, 5.6, 3.6, and 3.9, respectively. Additionally, it reduces parameter count, model size, and computation by 84.0–98.8%, 74.5–97.9%, and 3.2–94.2%, respectively. Transfer evaluation indicates that on 20 independent yellow-board images not seen during training, the model attains precision 94.3%, recall 95.8%, F1 95.0, and 159.2 FPS. Full article

To enhance our understanding of the phylogenetics and evolutionary processes within Dacinae, we sequenced and analyzed four complete mitogenomes for the first time, specifically Acroceratitis separata, Acrotaeniostola quadrivittata, Gastrozona parviseta, and Paragastrozona vulgaris, which represent Gastrozonini species. Our results indicated that these four mitogenomes, including A. separata, A. quadrivittata, G. parviseta, and P. vulgaris, comprised 37 mitochondrial genes and an A+T-control region, with a total length of 16,603 bp, 16,112 bp, 16,691 bp, and 16,594 bp, revealing a notably high AT content reaching 77.4%, 78.4%, 75.1%, and 75.1%, respectively. Our phylogenetic analyses using Bayesian inference and Maximum Likelihood methods under site-homogeneous models consistently demonstrated their superiority over the site-heterogeneous mixture model CAT + GTR, given the currently accepted phylogenetic framework. Apart from a few species demonstrating unstable placements, the inferred phylogenetic relationships among the three tribes were strongly supported as monophyletic groups, with the topology represented as ((Ceratitidini + Gastrozonini) + Dacini), and most branches displaying moderate-to-high support values, of which four newly sequenced mitogenomes and A. dissimilis robustly formed a single clade representing Gastrozonini. This study substantially augments the existing mitogenome data, thereby providing more profound insight into the evolutionary history and higher-level phylogenetic structure within the Dacinae. Full article

Polarimetric radar offers strong potential for UAV detection, but time-varying polarization induced by rotor rotation leads to unstable echoes, degrading feature consistency and recognition accuracy. This paper proposes a unified framework that combines rotor phase compensation, adaptive polarization filtering, and a multi-branch polarization aware fusion network (MPAF-Net) to enhance micro-Doppler features. The compensation scheme improves harmonic visibility through rotation-angle-based phase alignment and polarization optimization, while MPAF-Net exploits complementary information across polarimetric channels for robust classification. The framework is validated on both simulated and measured UAV radar data under varying SNR conditions. Results show an average harmonic SNR gain of approximately 1.2 dB and substantial improvements in recognition accuracy: at 0 dB, the proposed method achieves 66.7% accuracy, about 10% higher than Pauli and Sinclair decompositions, and at 20 dB, it reaches 97.2%. These findings confirm the effectiveness of the proposed approach for UAV identification in challenging radar environments. Full article

Few-shot image classification seeks to recognize novel categories from only a handful of labeled examples, but conventional metric-based methods that rely mainly on global image features often produce unstable prototypes under extreme data scarcity, while local-descriptor approaches can lose context and suffer from inter-class local-pattern overlap. To address these limitations, we propose a Global–Local Feature Fusion network that combines a frozen, pretrained global feature branch with a self-attention based multi-local feature fusion branch. Multiple random crops are encoded by a shared backbone (ResNet-12), projected to Query/Key/Value embeddings, and fused via scaled dot-product self-attention to suppress background noise and highlight discriminative local cues. The fused local representation is concatenated with the global feature to form robust class prototypes used in a prototypical-network style classifier. On four benchmarks, our method achieves strong improvements: Mini-ImageNet 70.31% ± 0.20 (1-shot)/85.91% ± 0.13 (5-shot), Tiered-ImageNet 73.37% ± 0.22/87.62% ± 0.14, FC-100 47.01% ± 0.20/64.13% ± 0.19, and CUB-200-2011 82.80% ± 0.18/93.19% ± 0.09, demonstrating consistent gains over competitive baselines. Ablation studies show that (1) naive local averaging improves over global-only baselines, (2) self-attention fusion yields a large additional gain (e.g., +4.50% in 1-shot on Mini-ImageNet), and (3) concatenating global and fused local features gives the best overall performance. These results indicate that explicitly modeling inter-patch relations and fusing multi-granularity cues produces markedly more discriminative prototypes in few-shot regimes. Full article

Micro-expressions are facial movements with extremely short duration and small amplitude, which can reveal an individual’s potential true emotions and have important application value in public safety, medical diagnosis, psychotherapy and business negotiations. Since micro-expressions change rapidly and are difficult to detect, manual recognition is a significant challenge, so the development of automatic recognition systems has become a research hotspot. This paper reviews the development history and research status of micro-expression recognition and systematically analyzes the two main branches of micro-expression analysis: micro-expression detection and micro-expression recognition. In terms of detection, the methods are divided into three categories based on time features, feature changes and deep features according to different feature extraction methods; in terms of recognition, traditional methods based on texture and optical flow features, as well as deep learning-based methods that have emerged in recent years, including motion unit, keyframe and transfer learning strategies, are summarized. This paper also summarizes commonly used micro-expression datasets and facial image preprocessing techniques and evaluates and compares mainstream methods through multiple experimental indicators. Although significant progress has been made in this field in recent years, it still faces challenges such as data scarcity, class imbalance and unstable recognition accuracy. Future research can further combine multimodal emotional information, enhance data generalization capabilities, and optimize deep network structures to promote the widespread application of micro-expression recognition in practical scenarios. Full article

The growing demand for reliable long-term traffic forecasting has become increasingly critical in the development of intelligent transportation systems (ITS). However, capturing both strong periodic patterns and long-range temporal dependencies presents a significant challenge, and existing approaches often fail to balance these factors effectively, resulting in unstable or suboptimal predictions. To address this issue, we propose MixModel, a novel hybrid framework that integrates TimesNet and Informer to leverage their complementary strengths. Specifically, the TimesNet branch extracts periodic variations through frequency-domain decomposition and multi-scale convolution, while the Informer branch employs ProbSparse attention to efficiently capture long-range dependencies across extended horizons. By unifying these capabilities, MixModel achieves enhanced forecasting accuracy, robustness, and stability compared with state-of-the-art baselines. Extensive experiments on real-world highway datasets demonstrate the effectiveness of our model, highlighting its potential for advancing large-scale urban traffic management and planning. To the best of our knowledge, MixModel is the first hybrid framework that explicitly bridges frequency-domain periodic modeling and efficient long-range dependency learning for long-term traffic forecasting, establishing a new benchmark for future research in Intelligent Transportation Systems. Full article

Background/Objectives: Retained products of conception (RPOC) are typically managed using dilation, curettage, or hysteroscopic resection. However, when the retained tissue is hypervascular, there is a significant risk of hemorrhage, particularly in cases of spontaneous miscarriage, in which vascular RPOC is rarely reported. Uterine artery embolization (UAE) is an established method for controlling acute bleeding. However, using mechanical hysteroscopic morcellation after UAE has not been fully explored. Methods: We report two cases of reproductive-aged women who developed vascular RPOC after spontaneous miscarriage, one following natural conception and the other following assisted reproduction. Both patients initially underwent expectant management but developed either acute or persistent vaginal bleeding. Imaging revealed hypervascular intrauterine lesions. UAE was performed using absorbable gelatin sponge particles targeting the ascending uterine artery branches. Following devascularization, hysteroscopic morcellation using the IBS or TruClear system was performed under direct visualization. Results: Intraoperatively, reddish vascular and whitish avascular degenerative tissues were noted. All retained tissues were completely resected with minimal bleeding. Both patients resumed menstruation shortly thereafter and expressed a desire for future pregnancy. Conclusions: This case series demonstrated the feasibility and effectiveness of a staged approach combining UAE and hysteroscopic morcellation for vascular RPOC management after spontaneous miscarriage. UAE improves surgical visibility and reduces bleeding risk, whereas mechanical morcellation ensures complete removal under direct vision with minimal trauma to the endometrium. This hybrid strategy may be a valuable fertility-preserving option, particularly in complex or hemodynamically unstable cases. Further prospective studies are needed to validate its safety, cost-effectiveness, and impact. Full article

Multi-object tracking (MOT) algorithms are a key research direction in the field of computer vision. Among them, the joint detection and embedding (JDE) method, with its excellent speed and accuracy performance, has become the current mainstream solution. However, in complex scenes with dense targets or occlusions, the tracking performance of existing algorithms is often limited, especially in terms of unstable identity assignment and insufficient tracking accuracy. To address these challenges, this paper proposes a new multi-object tracking model—the Reparameterized and Global Context Track (RGTrack). This model is based on the Correlation-Sensitive Track (CSTrack) framework and innovatively introduces multi-branch training and attention mechanisms, combined with reparameterized convolutional networks and global attention modules, significantly enhancing the network’s feature extraction ability in complex scenes, especially in ignoring irrelevant information and focusing on key areas. It adopted a multiple association strategy to better establish the association relationship between targets in consecutive frames. Through this improvement, the Reparameterized and Global Context Track can better handle scenes with dense targets and severe occlusions, providing more accurate target identity matching and continuous tracking. Experimental results show that compared with the Correlation-Sensitive Track, the Reparameterized and Global Context Track has significant improvements in multiple key indicators: multi-object tracking accuracy (MOTA) increased by 1.15%, Identity F1 Score (IDF1) increased by 1.73%, and Mostly Tracked (MT) increased by 6.86%, while ID-switched (ID Sw) decreased by 47.49%. These results indicate that the Reparameterized and Global Context Track not only can stably track targets in more complex scenes but also significantly improves the continuity of target identities. Moreover, the Reparameterized and Global Context Track increased the frames per second (FPS) by 51.48% and reduced the model size by 3.08%, demonstrating its significant advantages in real-time performance and computational efficiency. Therefore, the Reparameterized and Global Context Track model maintains high accuracy while having stronger real-time processing capabilities, making it especially suitable for embedded devices and resource-constrained application environments. Full article