Branching Characteristics Research Articles

Low-light enhancement method with dual branch feature fusion and learnable regularized attention

Restricted by the lighting conditions, the images captured at night tend to suffer from color aberration, noise, and other unfavorable factors, making it difficult for subsequent vision-based applications. To solve this problem, we propose a two-stage size-controllable low-light enhancement method, named Dual Fusion Enhancement Net (DFEN). The whole algorithm is built on a double U-Net structure, implementing brightness adjustment and detail revision respectively. A dual branch feature fusion module is adopted to enhance its ability of feature extraction and aggregation. We also design a learnable regularized attention module to balance the enhancement effect on different regions. Besides, we introduce a cosine training strategy to smooth the transition of the training target from the brightness adjustment stage to the detail revision stage during the training process. The proposed DFEN is tested on several low-light datasets, and the experimental results demonstrate that the algorithm achieves superior enhancement results with the similar parameters. It is worth noting that the lightest DFEN model reaches 11 FPS for image size of 1224×1024 in an RTX 3090 GPU.Graphical

Neurosurgical Importance on Temporal Branch of the Facial Nerve.

We aimed to determine anatomic features of the temporal branch (TB) of the facial nerve and its relation to various anatomic landmarks on the face in order to prevent damage in the surgical approach after head trauma or in planned neurosurgical interventions. Nine male cadavers preserved with formalin, were bilaterally dissected under a microscope at the laboratory of anatomy department of the university. The anatomical features of the branch and branching pattern of facial nerve and its relationships with adjacent neurovascular structures were evaluated using descriptive statistical data. The mean distance at the lateral canthus level between the far most anterior branch and far most posterior branch of the TB (APD) was 14.93 mm. The mean distance to the tragus of the entrance point of the TB to the orbicularis oculi muscle (ETT) was 74.72 mm. The mean distance between the origin point of the TB to the tragus (TT) was 24.50 mm. The angle between the far most anterior branch and far most posterior branch at the level of the lateral canthus (APA) was minimum 15°, maximum 40° and the mean value of APA was 24.61°. The number of branches originating from the TB (NB) were one to three branches which lay under the zygomatic arch and two to five branches upper the zygomatic arch, respectively. The number of anastomosis between the TB and zygomatic branch (AN) varies between 1 and 4; AN was found to be less intense in 10 sides and very intense in eight sides. The APA and APD value is mentioned for the first time in this study and nerve angle is considered to be as important as temporal branching in directing facial neurosurgical operations. We found that the unsafety zone may be exist for a 40 degree and 1.5 cm long area at the lateral canthus level, especially on the zygomatic arc where branching pattern is greater and 2.5 cm in front of the tragus. The data is significant for neurosurgeons to reach exactly this area without causing postoperative complications such as facial paralysis.

Structure and position-aware graph neural network for airway labeling

We present a novel graph-based approach for labeling the anatomical branches of a given airway tree segmentation. The proposed method formulates airway labeling as a branch classification problem in the airway tree graph, where branch features are extracted using convolutional neural networks and enriched using graph neural networks. Our graph neural network is structure-aware by having each node aggregate information from its local neighbors and position-aware by encoding node positions in the graph.We evaluated the proposed method on 220 airway trees from subjects with various severity stages of Chronic Obstructive Pulmonary Disease (COPD). The results demonstrate that our approach is computationally efficient and significantly improves branch classification performance than the baseline method. The overall average accuracy of our method reaches 91.18% for labeling 18 segmental airway branches, compared to 83.83% obtained by the standard CNN method and 87.37% obtained by the existing method. Furthermore, the reader study done on an additional set of 40 subjects shows that our algorithm performs comparably to human experts in labeling segmental-airways. We published our source code at https://github.com/DIAGNijmegen/spgnn. The proposed algorithm is also publicly available at https://grand-challenge.org/algorithms/airway-anatomical-labeling/.

Crashworthiness analysis of bio-inspired hierarchical multi-cell circular tubes under axial crushing

Drawing inspiration from nature’s hierarchical organization, we propose a novel bio-inspired hierarchical multi-cellular circular tubes (BHMC) with a fractal structure. Using an experimentally validated LS-DYNA finite element model, we investigated the impact resistance of this structure under axial loading. Numerical analysis was conducted to explore the energy absorption performance of BHMC tubes with varying numbers of branches, fractal orders, and tube masses. The numerical findings indicate that specific energy absorption (SEA) increases with higher numbers of fractal orders. Specifically, the SEA of 2nd order BHMC tubes surpasses that of conventional multicellular circular and single-layer tubes by approximately 35.07% and 17.10%, respectively. Optimal performance is achieved with the proposed structure featuring tree branching (N = 6) and 2nd order fractal characteristics, yielding the highest specific absorption energy across different parameters. These results offer valuable insights for designing multicellular bilayer tubes with superior energy absorption efficiency, providing an effective guideline for structural optimization.

Boundary-Aware Gradient Operator Network for Medical Image Segmentation.

Medical image segmentation is a crucial task in computer-aided diagnosis. Although convolutional neural networks (CNNs) have made significant progress in the field of medical image segmentation, the convolution kernels of CNNs are optimized from random initialization without explicitly encoding gradient information, leading to a lack of specificity for certain features, such as blurred boundary features. Furthermore, the frequently applied down-sampling operation also loses the fine structural features in shallow layers. Therefore, we propose a boundary-aware gradient operator network (BG-Net) for medical image segmentation, in which the gradient convolution (GConv) and the boundary-aware mechanism (BAM) modules are developed to simulate image boundary features and the remote dependencies between channels. The GConv module transforms the gradient operator into a convolutional operation that can extract gradient features; it attempts to extract more features such as images boundaries and textures, thereby fully utilizing limited input to capture more features representing boundaries. In addition, the BAM can increase the amount of global contextual information while suppressing invalid information by focusing on feature dependencies and the weight ratios between channels. Thus, the boundary perception ability of BG-Net is improved. Finally, we use a multi-modal fusion mechanism to effectively fuse lightweight gradient convolution and U-shaped branch features into a multilevel feature, enabling global dependencies and low-level spatial details to be effectively captured in a shallower manner. We conduct extensive experiments on eight datasets that broadly cover medical images to evaluate the effectiveness of the proposed BG-Net. The experimental results demonstrate that BG-Net outperforms the state-of-the-art methods, particularly those focused on boundary segmentation.

BMCS-Net: A Bi-directional multi-scale cascaded segmentation network based on transformer-guided feature Aggregation for medical images

convolutional neural networks (CNNs) show great potential in medical image segmentation tasks, and can provide reliable basis for disease diagnosis and clinical research. However, CNNs exhibit general limitations on modeling explicit long-range relation, and existing cures, resorting to building deep encoders along with aggressive downsampling operations, leads to loss of localized details. Transformer has naturally excellent ability to model the global features and long-range correlations of the input information, which is strongly complementary to the inductive bias of CNNs. In this paper, a novel Bi-directional Multi-scale Cascaded Segmentation Network, BMCS-Net, is proposed to improve the performance of medical segmentation tasks by aggregating these features obtained from Transformers and CNNs branches. Specifically, a novel feature integration technique, termed as Two-stream Cascaded Feature Aggregation (TCFA) module, is designed to fuse features in two-stream branches, and solve the problem of gradual dilution of global information in the network. Besides, a Multi-Scale Expansion-Aware (MSEA) module based on the convolution of feature perception and expansion is introduced to capture context information, and further compensate for the loss of details. Extensive experiments demonstrated that BMCS-Net has an excellent performance on both skin and Polyp segmentation datasets.

An interpretable TFAFI-1DCNN-LSTM framework for UGW-based pre-stress identification of steel strands

Steel strands serve as the key load-bearing components of pre-stressed bridges, yet the identification of effective pre-stress for steel strands is a challenging task. In this study, a time and frequency adaptive fusion input-one dimensional convolutional neural network-long short-term memory (TFAFI-1DCNN-LSTM) framework was proposed for ultrasonic guided wave (UGW)-based effective pre-stress identification of steel strands. In this framework, the time and frequency domain signals of UGW were input into the network as two parallel branches, CNN and LSTM were utilized to extract spatial and serial-related features, and a trainable weight coefficient was introduced for adaptive fusion of time and frequency domain features. Firstly, ablation studies were conducted to investigate the influence of each key component in the proposed framework on the prediction results. Secondly, deep learning (DL) models of Res Net, Dense Net and Inception Net were introduced as comparisons, and the prediction results based on TFAFI-1DCNN-LSTM were compared with those based on the above DL models. Thirdly, the noise-robustness and performance under a few trainable samples of TFAFI-1DCNN-LSTM were also investigated. Finally, the outputs of various key layers of the proposed framework were subjected to dimensionality reduction and visualization to provide an intuitive demonstration of the feature extraction process, and the inherent mechanisms of the proposed framework were interpreted using local interpretable model-agnostic explanations (LIME). Results show that the architecture of TFAFI-1DCNN-LSTM is reasonably designed and all key components are necessary. The weights of features in time and frequency domain branches are rationally assigned due to the addition of an adaptive weight coefficient. Compared with other DL models, the proposed TFAFI-1DCNN-LSTM exhibits higher pre-stress identification accuracy, excellent noise-robustness, and superior performance under only a few trainable samples. The correlation between features extracted by the network and the pre-stress labels significantly increases with the deepening of the network, and the correlation between input UGW signals and predicted pre-stress values is effectively interpreted utilizing LIME, proving that the architecture of the proposed framework is reasonable and effective, the predicted results are reliable and credible.

A high-speed YOLO detection model for steel surface defects with the channel residual convolution and fusion-distribution

Abstract Accurately and efficiently detecting steel surface defects is a critical step in steel manufacturing. However, the compromise between the detection speed and accuracy remains a major challenge, especially for steel surface defects with large variations in the scale. To address the issue, an improved you only look once (YOLO) based detection model is proposed through the reinforcement of its backbone and neck. Firstly, for the reduction of the redundant parameters and also the improvement of the characterization ability of the model, an effective channel residual structure is adopted to construct a channel residual convolution module and channel residual cross stage partial module as components of the backbone network, respectively. They realize the extraction of both the shallow feature and multi-scale feature simultaneously under a small number of convolutional parameters. Secondly, in the neck of YOLO, a fusion-distribution strategy is employed, which extracts and fuses multi-scale feature maps from the backbone network to provide global information, and then distributes global information into local features of different branches through an inject attention mechanism, thus enhancing the feature gap between different branches. Then, a model called CRFD-YOLO is derived for the steel surface defect detection and localization for the situations where both speed and accuracy are demanding. Finally, extensive experimental validations are conducted to evaluate the performance of CRFD-YOLO. The validation results indicate that CRFD-YOLO achieves a satisfactory detection performance with a mean average precision of 81.3% on the NEU-DET and 71.1% on the GC10-DET. Additionally, CRFD-YOLO achieves a speed of 161 frames per second, giving a great potential in real-time detection and localization tasks.

WDFF-Net: Weighted Dual-Branch Feature Fusion Network for Polyp Segmentation With Object-Aware Attention Mechanism.

Colon polyps in colonoscopy images exhibit significant differences in color, size, shape, appearance, and location, posing significant challenges to accurate polyp segmentation. In this paper, a Weighted Dual-branch Feature Fusion Network is proposed for Polyp Segmentation, named WDFF-Net, which adopts HarDNet68 as the backbone network. First, a dual-branch feature fusion network architecture is constructed, which includes a shared feature extractor and two feature fusion branches, i.e. Progressive Feature Fusion (PFF) branch and Scale-aware Feature Fusion (SFF) branch. The branches fuse the deep features of multiple layers for different purposes and with different fusion ways. The PFF branch is to address the under-segmentation or over-segmentation problems of flat polyps with low-edge contrast by iteratively fusing the features from low, medium, and high layers. The SFF branch is to tackle the the problem of drastic variations in polyp size and shape, especially the missed segmentation problem for small polyps. These two branches are complementary and play different roles, in improving segmentation accuracy. Second, an Object-aware Attention Mechanism (OAM) is proposed to enhance the features of the target regions and suppress those of the background regions, to interfere with the segmentation performance. Third, a weighted dual-branch the segmentation loss function is specifically designed, which dynamically assigns the weight factors of the loss functions for two branches to optimize their collaborative training. Experimental results on five public colon polyp datasets demonstrate that, the proposed WDFF-Net can achieve a superior segmentation performance with lower model complexity and faster inference speed, while maintaining good generalization ability.

UCP2-ACGAN: An adaptive condition GAN guided by U-shaped context perceptual processor for PET/CT images fusion

In order to better highlight the lesion area information and edge detailed information of the fused images, an adaptive condition Generative Adversarial Network (GAN) guided by U-shaped context perceptual processor (UCP2-ACGAN) for Positron Emission Tomography (PET) and Computed Tomography (CT) images fusion is proposed in this paper. Firstly, the network architecture of single generator and dual relative discriminators with weights sharing is used in UCP2-ACGAN. Secondly, a multi-granularity adaptive feature extraction module from coarse to fine (MGAFE) is proposed in generator, it is used to extract the valid information contained in the source images. Thirdly, a dual branch feature interactive fusion module guided by U-shaped context perceptual processor (UCP2-DBFIF) is proposed in generator. The context perceptual feature maps are obtained by U-shaped context perceptual processor (UCP2) and multiply them with the feature extraction results as the guiding conditions in the fusion process. In addition, in order to supplement the effective information lost during the feature fusion process, this paper converges the feature information of different granularity during the feature extraction stage. Finally, compared to the best of the 6 comparison methods, the results of comparison experiments show that UCP2-ACGAN is effective on several evaluation metrics values. For example, on the evaluation metrics of Average Gradient (AG), Edge Intensity (EI), Spatial Frequency (SF), Visual Information Fidelity (VIF) and Mutual Information (MI), the metrics values of CT mediastinal window images and PET fused images average increased by 30.74%, 29.35%, 40.24%, 35.47% and 26.18%.

Light field image super-resolution using a Content-Aware Spatial–Angular Interaction network

Light field images record a series of viewpoints of a scene and thus have many attractive applications. However, the trade-off between angular and spatial resolution in the imaging process makes light field image super-resolution necessary. In this paper, we propose a Content-Aware Spatial–Angular Interaction (dubbed CASAI) network for light field image super-resolution. The gradient branch of CASAI makes full use of the context information of the low-resolution gradient map and the multi-level features of the super-resolution branch to generate the high-resolution gradient map, which enables the awareness of structure, texture and detail, and provides effective prior knowledge for the super-resolution process. The super-resolution branch of CASAI generates high-quality super-resolution images by making full use of intra-view (i.e., spatial) and inter-view (i.e., angular) information through a spatial–angular adaptive interaction block and using the high-resolution gradient prior as guidance. The spatial–angular adaptive interaction block enables the awareness of the different importance of spatial features and angular features, so as to better integrate intra-view and inter-view information to improve the performance of light field image super-resolution. The experimental results indicate that when the upsampling factor is 4, our method outperforms our baseline (LF-InterNet) with an average PSNR increase of 0.48 dB, while also achieving the best SSIM. Visualization results demonstrate the advantage of our method in simultaneously generating natural SR images and restoring structures.

A Visible and Synthetic Aperture Radar Image Fusion Algorithm Based on a Transformer and a Convolutional Neural Network

For visible and Synthetic Aperture Radar (SAR) image fusion, this paper proposes a visible and SAR image fusion algorithm (TCFuse) based on a Transformer and a Convolutional Neural Network (CNN). Firstly, in this paper, the Restormer Block is used to extract cross-modal shallow features. Then, we introduce an improved Transformer–CNN Feature Extractor (TCFE) with a two-branch residual structure. This includes a Transformer branch that introduces the Lite Transformer (LT) and DropKey for extracting global features and a CNN branch that introduces the Convolutional Block Attention Module (CBAM) for extracting local features. Finally, the fused image is output based on global features extracted by the Transformer branch and local features extracted by the CNN branch. The experiments show that the algorithm proposed in this paper can effectively achieve the extraction and fusion of global and local features of visible and SAR images, so that high-quality visible and SAR fusion images can be obtained.

Reservoir properties inversion using attention-based parallel hybrid network integrating feature selection and transfer learning

The inversion of subsurface reservoir properties is of profound significance to the oil and gas energy development and utilization. The strong heterogeneity and complex pore structure of underground reservoirs pose a challenge to efficient oil and gas energy development and utilization across the world, which increases the necessity of developing an efficient reservoir properties inversion method. However, traditional model-driven methods are confronted with the challenges of strong nonlinearity and geological heterogeneity. Moreover, previous studies rarely emphasized the importance of nonlinear feature selection and transfer learning (TL). Aiming to address the research gaps, a reservoir properties inversion method was proposed by combining random forest (RF) feature selection, bidirectional temporal convolutional network (BiTCN), bidirectional gated recurrent units (BiGRU) network, multi-head attention (MHA) mechanism and TL strategy. First, the RF was used to screen the features with significant correlation with the target reservoir properties. Thereafter, combining BiTCN and BiGRU network to leverage their complementary strengths, a parallel dual branch feature learning network was constructed to learn richer geological information from logging data. Meanwhile, MHA was introduced to fuse the output features of the dual network structure. Finally, the fused features were passed through the fully connected module to output the inversion results. TL was used to associate the correlation between reservoir properties and model inversion to improve the inversion performance. The application results with actual field data showed that the proposed method was accurate and robust in reservoir properties inversion. This study can provide a new way for reliable reservoir properties inversion and promote the application of artificial intelligence in data-driven energy science.

Plant Leaf Functional Adaptions along Urban-Rural Gradients of Jinhua City.

Environmental changes induced by urbanization may significantly alter plant survival strategies, thereby introducing uncertainties in their ability to withstand extreme heat. This study, centered on Jinhua City, distinguished urban, suburban, and rural areas to represent the various intensities of urbanization. It examined the leaf function properties of evergreen and deciduous trees common in these regions, focusing on leaf and branch characteristics. Employing an analysis of variance (ANOVA), principal component analysis (PCA), and path analysis (PA) of the plant functional traits and the climatic factors of each region, this study assessed the impact of urbanization on plant survival strategies. By tracking changes in plant functional traits from June to August, it explored the capacity of plants to acclimate to urban-warming-related heat stress across different urbanization gradients. The findings revealed that leaf thickness (LT) and stomatal size (SS) initially decreased and then increased, whereas specific leaf area (SLA) and leaf tissue density (LTD) first rose and then declined, from rural to urban regions. From June to August, branch wood density (WD), chlorophyll (Chl) content, LTD, and leaf dry matter content (LDMC) increased, whereas SLA and leaf water content (LWC) diminished, in all regions. PCA suggested that there was no significant change in the resource allocation strategy of plants (p > 0.05), with drought tolerance significantly reduced in the suburbs on the gradient of urbanization (p < 0.05). During the summer, with high temperature, plants were predominantly biased towards slow-return, conservative strategies, particularly among evergreen species. Compared to precipitation, PA revealed a significant urban warming effect. During summer, temperature was the main factor influencing resource investment strategy and drought resistance, with a notably stronger impact on the former. The high temperature in summer promoted a conservative survival strategy in plants, and the urbanization effect increased their tolerance to high temperatures.

Hydra: Multi-head low-rank adaptation for parameter efficient fine-tuning

The recent surge in large-scale foundation models has spurred the development of efficient methods for adapting these models to various downstream tasks. Low-rank adaptation methods, such as LoRA, have gained significant attention due to their outstanding parameter efficiency and no additional inference latency. This paper investigates a more general form of adapter module based on the analysis that parallel and sequential adaptation branches learn novel and general features during fine-tuning, respectively. The proposed method, named Hydra, combines parallel and sequential branch to integrate capabilities, which is more expressive than existing single branch methods and enables the exploration of a broader range of optimal points in the fine-tuning process. In addition, the proposed method explicitly leverages the pre-trained weights by performing a linear combination of the pre-trained features. It allows the learned features to have better generalization performance across diverse downstream tasks. Furthermore, we perform a comprehensive analysis of the characteristics of each adaptation branch with empirical evidence. Through an extensive range of experiments, we substantiate the efficiency and demonstrate the superior performance of Hydra. This comprehensive evaluation underscores the potential impact and effectiveness of Hydra in a variety of applications. The source code of this work is publicly opened on https://github.com/extremebird/Hydra.

Molecular dynamics study of free volume coalescence around nonyl ethoxylate in polyethylene with vinyl acetate‐modified branches

AbstractPolyethylene (PE) is susceptible to environmental stress cracking (ESC). In the presence of an amphiphilic compound and subjected to stress, ESC starts with cavitation followed by slow crack growth and ends with brittle fracture. In this study, we used molecular dynamics simulation to study how branch ends which were chemically modified with vinyl acetate groups affect free volume coalescence around an amphiphilic compound, nonyl ethoxylate (NE), dispersed in branched PE models. Branch ends modified with vinyl acetate significantly impact the free volume coalescence dynamics around NE. Compared with methyl branch ends, vinyl acetate branch ends show a much higher affinity, as quantified by the corresponding radial distribution functions, for the hydrophilic ethylene oxide‐segment of NE. However, this is not the case for the hydrophobic ethylene‐segment. Interestingly, vinyl acetate branch ends tend to reduce the power (amplitude) of the free volume size fluctuations around both the ethylene oxide‐ and ethylene‐segments. Indeed, the powers of the fluctuations with different PE branching characteristics decrease with increasing vinyl acetate concentration. We believe that free volume coalescence leads to cavitation and that vinyl acetate branches could inhibit cavitation, thereby crack propagation in PE. The power results seem to be consistent with the experimental observation that the addition of copolymer ethylene vinyl acetate to low‐density polyethylene improves the ESC resistance of the blend.Highlights Vinyl acetate branches reduce free volume coalescence activities. Vinyl acetate branches are attracted to the hydrophilic segment of NE. Cavitation likely starts from the free volume coalescence around NE.

A porcine large animal model of radiofrequency ablation-induced left bundle branch block

Abstract Funding Acknowledgements Type of funding sources: Private company. Main funding source(s): Medtronic Background and Objective ECG features of left bundle branch (LBB) block (LBBB) can be observed in up to 20–30 % of patients that suffer from heart failure with reduced ejection fraction. The resulting mechanical intraventricular asynchrony contributes to the worsening of left ventricular hemodynamics and has a relevant impact on the prognosis of the affected patients. The fact that we still cannot accurately predict which LBBB patients will benefit from cardiac resynchronization therapy (CRT) underscores that our understanding of the pathophysiology of LBBB remains incomplete. Here, a translational animal model of LBBB could be a major contributor to improving our knowledge of the molecular and translational pathomechanisms underlying LBBB. Methods A total of 15 male pigs underwent RF catheter ablation of the LBB, guided by fluoroscopy and intracardiac ECG signals. Before LBBB induction and after a follow-up period of one week or three weeks, a thorough clinical characterization was performed including 12-lead ECG, echocardiography, and electroanatomical mapping. To further test the feasibility of cardiac resynchronization in our model, 3 pigs were implanted with a CRT pacemaker on day seven after LBB ablation. Results Upon LBB ablation, 12-lead ECGs displayed typical characteristics of LBBB like a QRS broadening, a QRS slurring in left lateral leads, and a change of the QRS axis. The QRS width was prolonged from 64.2±4.2 ms to 93,4±7.4 ms and the R wave peak time in V6 was extended from 19.3±3.9 ms to 42.7±4.2 ms. Cardiac electromechanical asynchrony was further confirmed by echocardiography, where the appearance of a septal flash, the prolongation of the septal to posterior wall movement delay and extended left ventricular as well as interventricular electromechanical delays were documented. Electroanatomical mapping demonstrated a shift of the left ventricular breakthrough site. After LBBB-induction, left ventricular activation times, defined as the average of the maximum 10 % of activation times minus the average of the minimum 10 % of activation times were significantly prolonged from 36.3±7.1 ms to 60.8±10.2 ms while right ventricular activation times remained unchanged. Finally, RF-induced LBBB persisted over an observation period of three weeks. The pigs that underwent CRT showed a reduction in QRS duration from 99.1±8.2 ms on day seven after LBBB induction to 75.5±8.2 ms and echocardiography provided additional evidence of successful resynchronization. Conclusions In summary, our porcine large animal model accurately recapitulates the electrical and electromechanical phenotype, observed in LBBB patients. This closed-chest model of LBBB therefore provides an experimental platform to study both, molecular and translational characteristics of cardiac electromechanical asynchrony in a reproducible and clinically relevant setting.

Penya on the borderline of private and public regulation: the tax aspect of external economic activity

The application of sanctions is a certain summary of the perception that a person has committed an offense. But before the direct application of sanctions, it is necessary to form a vision regarding the type of responsibility. That is, the construction of financial responsibility can be used, but as a certain generic model that unites institutional or sub-sectoral varieties of responsibility. At the same time, characterizing the tax liability consistently in the assessment of its nature and consequences, distinguish not one of the stages of the tax liability (payment of taxes and fees), but the whole construction of the tax liability (accounting-payment-reporting). A systematic view of the construction of tax liability involves both an assessment of the behavior of obligated persons (payers of taxes and fees, etc.) and subjects of authority. The complexity of social relations, which express the peculiarities of foreign economic activity, determines the clear demarcation of these relations into certain sectors, the basis of whose regulation are precisely the branch characteristics of the subject and the method of the corresponding grouping of legal norms. It is necessary to distinguish between sanctions that are applied as a result of financial responsibility and sanctions that have a monetary nature but are regulated by other branches. Fines and interest are tools that are used in both private and public law. This involves, depending on the purpose, the subject of regulation and the application of not just public-law or private-law methods, but the tools of the relevant industry or sub-industry (economic law, customs law, money circulation, tax law). In this sense, we would like to distinguish between the occurrence of adverse consequences for payers and the application of sanctions to them. The use of a penalty refers to the regimes of adverse consequences. But, it is unlikely that there is a reason to equate penalties and sanctions (fines). The basis for applying a sanction (fine) is illegal behavior, commission of an offense. The basis for the application of a penalty is the untimely or incomplete fulfillment of the tax obligation. The determination of the penalty in the analysis of such issues must be connected with the relevant powers of the supervisory body. That is, forming the competence of the subject of power, the controlling body, the state delegates to it not only the right to implement certain measures, but also the imperative duty to implement such a right.

Fusion of satellite and street view data for urban traffic accident hotspot identification

As the number of vehicles and the volume of traffic swell in urban centers, cities have experienced a concomitant increase in traffic accidents. Proactively identifying accident-prone hotspots in urban environments holds the promise of preventing traffic mishaps, thereby curtailing the incidence of accidents and reducing property damage. This research introduces the Two-Branch Contextual Feature-Guided Converged Network (TCFGC-Net) utilizing multimodal satellite and street view data. Designed to extract global structural features from satellite imagery and dynamic continuous features from street view imagery, the model aims to improve the accuracy of detecting urban accident hotspots. For the satellite imagery branch, we propose the Contextual Feature Coupled Convolutional Neural Network (Trans-CFCCNN) designed to extract global spatial features and discern feature correlations across adjacent regions. For the street view imagery branch, we develop the Sequential Feature Recurrent Attention Network (SFRAN) to assimilate and integrate dynamic scene features captured from successive street view images. We designed the Multi-Branch Feature Adaptive Fusion Structure (MBFAF) to aggregate different branch features for accurate identification of accident hotspots. Experimental results show that the model performs well, with an overall accuracy of 93.7 %. Ablation studies confirm that relative to standalone street view and satellite branch analyses, implementing multimodal fusion enhances the model's accuracy by 12.05 % and 17.86 %, respectively. The innovative fusion structure proposed herein garners a 4.22 % increase in model accuracy, outpacing conventional feature concatenation techniques. Furthermore, the model outperforms existing deep learning models in terms of overall efficacy. Additionally, to showcase the efficacy of the proposed model structure, we utilize Class Activation Maps (CAM) to provide visual interpretability for the model. These results suggest that the dual-branch fusion model effectively decreases false alarm occurrences and directs the model's focus toward regions more pertinent to accident hotspots. Finally, the code and model used for identifying hotspots of urban traffic accidents in this study are available for access: https://github.com/gwt-ZJU/TCFGC-Net.

Diffusion-based normality pre-training for weakly supervised video anomaly detection

Weakly supervised video anomaly detection is the task of detecting anomalous frames in videos where no frame-level labels are provided at training phase. Previous methods usually employed a multiple instance learning (MIL)-based ranking loss to ensure inter-class separation. However, these methods are unable to completely utilise the information from the huge amounts of normal frames. Moreover, the performance of these methods is misguided by the erroneous initial prediction of the MIL-based classifier. Taking these shortcomings into consideration, we propose a diffusion-based normality learning pretrain step, which first involves training a Global–Local Feature Encoder (GLFE) model with only normal videos to understand the feature distribution of normal frames. The resulting pre-trained Global–Local feature encoder is further optimised using Multi-Sequence Contrastive loss using both normal and anomalous videos. Our proposed GLFE model captures long- and short-range temporal features using a Transformer block and pyramid of dilated convolutions in a two-branch setup. The model adaptively learns the relation between the two branch features by introducing the Co-Attention module, which provides a learnable fusion of features. Additionally we introduced a triplet contrastive loss to provide better separation between abnormal and normal frames in anomalous videos. The developed methodology is evaluated through extensive experiments on two public benchmark datasets (UCF-Crime and ShanghaiTech). The results obtained are comparable to or better than the existing state-of-the-art weakly supervised methods.