An Expert System to Detect Political Arabic Articles Orientation Using CatBoost Classifier Boosted by Multi-Level Features

The number of blogs and other forms of opinionated online content has increased dramatically in recent years.Many fields,including academia and national security,place an emphasis on automated political article orientation detection.Political articles(especially in the Arab world)are different from other articles due to their subjectivity,in which the author’s beliefs and political affiliation might have a significant influence on a political article.With categories representing the main political ideologies,this problem may be thought of as a subset of the text categorization(classification).In general,the performance of machine learning models for text classification is sensitive to hyperparameter settings.Furthermore,the feature vector used to represent a document must capture,to some extent,the complex semantics of natural language.To this end,this paper presents an intelligent system to detect political Arabic article orientation that adapts the categorical boosting(CatBoost)method combined with a multi-level feature concept.Extracting features at multiple levels can enhance the model’s ability to discriminate between different classes or patterns.Each level may capture different aspects of the input data,contributing to a more comprehensive representation.CatBoost,a robust and efficient gradient-boosting algorithm,is utilized to effectively learn and predict the complex relationships between these features and the political orientation labels associated with the articles.A dataset of political Arabic texts collected from diverse sources,including postings and articles,is used to assess the suggested technique.Conservative,reform,and revolutionary are the three subcategories of these opinions.The results of this study demonstrate that compared to other frequently used machine learning models for text classification,the CatBoost method using multi-level features performs better with an accuracy of 98.14%.

Identification of a Printed Anti-Counterfeiting Code Based on Feature Guidance Double Pool Attention Networks

The authenticity identification of anti-counterfeiting codes based on mobile phone platforms is affected by lighting environment,photographing habits,camera resolution and other factors,resulting in poor collection quality of anti-counterfeiting codes and weak differentiation of anti-counterfeiting codes for high-quality counterfeits.Developing an anticounterfeiting code authentication algorithm based on mobile phones is of great commercial value.Although the existing algorithms developed based on special equipment can effectively identify forged anti-counterfeiting codes,the anti-counterfeiting code identification scheme based on mobile phones is still in its infancy.To address the small differences in texture features,low response speed and excessively large deep learning models used in mobile phone anti-counterfeiting and identification scenarios,we propose a feature-guided double pool attention network(FG-DPANet)to solve the reprinting forgery problem of printing anti-counterfeiting codes.To address the slight differences in texture features in high-quality reprinted anti-counterfeiting codes,we propose a feature guidance algorithm that creatively combines the texture features and the inherent noise feature of the scanner and printer introduced in the reprinting process to identify anti-counterfeiting code authenticity.The introduction of noise features effectively makes up for the small texture difference of high-quality anti-counterfeiting codes.The double pool attention network(DPANet)is a lightweight double pool attention residual network.Under the condition of ensuring detection accuracy,DPANet can simplify the network structure as much as possible,improve the network reasoning speed,and run better on mobile devices with low computing power.We conducted a series of experiments to evaluate the FG-DPANet proposed in this paper.Experimental results show that the proposed FG-DPANet can resist highquality and small-size anti-counterfeiting code reprint forgery.By comparing with the existing algorithm based on texture,it is shown that the proposed method has a higher authentication accuracy.Last but not least,the proposed scheme has been evaluated in the anti-counterfeiting code blurring scene,and the results show that our proposed method can well resist slight blurring of anti-counterfeiting images.

Guided-YNet: Saliency Feature-Guided Interactive Feature Enhancement Lung Tumor Segmentation Network

Multimodal lung tumor medical images can provide anatomical and functional information for the same lesion.Such as Positron Emission Computed Tomography(PET),Computed Tomography(CT),and PET-CT.How to utilize the lesion anatomical and functional information effectively and improve the network segmentation performance are key questions.To solve the problem,the Saliency Feature-Guided Interactive Feature Enhancement Lung Tumor Segmentation Network(Guide-YNet)is proposed in this paper.Firstly,a double-encoder single-decoder U-Net is used as the backbone in this model,a single-coder single-decoder U-Net is used to generate the saliency guided feature using PET image and transmit it into the skip connection of the backbone,and the high sensitivity of PET images to tumors is used to guide the network to accurately locate lesions.Secondly,a Cross Scale Feature Enhancement Module(CSFEM)is designed to extract multi-scale fusion features after downsampling.Thirdly,a Cross-Layer Interactive Feature Enhancement Module(CIFEM)is designed in the encoder to enhance the spatial position information and semantic information.Finally,a Cross-Dimension Cross-Layer Feature Enhancement Module(CCFEM)is proposed in the decoder,which effectively extractsmultimodal image features through global attention and multi-dimension local attention.The proposed method is verified on the lung multimodal medical image datasets,and the results showthat theMean Intersection overUnion(MIoU),Accuracy(Acc),Dice Similarity Coefficient(Dice),Volumetric overlap error(Voe),Relative volume difference(Rvd)of the proposed method on lung lesion segmentation are 87.27%,93.08%,97.77%,95.92%,89.28%,and 88.68%,respectively.It is of great significance for computer-aided diagnosis.

Observability analysis of feature aided terminal guidance systems

Feature aided design of estimators and guidance laws can significantly improve the interception performance of the terminal guidance system. The achieved enhancement can be effectively assessed by observability analysis methods. This paper first analyzes and discusses the existing assessment methods in a typical endgame scenario with target orientation observations. To get over their deficiencies, a novel singular value decomposition（SVD） method is proposed. Employing both theoretical analysis and numerical simulation, the proposed method can represent the degree of state observability which is enhanced by integrating target features more completely and quantitatively.

Traffic Scene Captioning with Multi-Stage Feature Enhancement

Traffic scene captioning technology automatically generates one or more sentences to describe the content of traffic scenes by analyzing the content of the input traffic scene images,ensuring road safety while providing an important decision-making function for sustainable transportation.In order to provide a comprehensive and reasonable description of complex traffic scenes,a traffic scene semantic captioningmodel withmulti-stage feature enhancement is proposed in this paper.In general,the model follows an encoder-decoder structure.First,multilevel granularity visual features are used for feature enhancement during the encoding process,which enables the model to learn more detailed content in the traffic scene image.Second,the scene knowledge graph is applied to the decoding process,and the semantic features provided by the scene knowledge graph are used to enhance the features learned by the decoder again,so that themodel can learn the attributes of objects in the traffic scene and the relationships between objects to generate more reasonable captions.This paper reports extensive experiments on the challenging MS-COCO dataset,evaluated by five standard automatic evaluation metrics,and the results show that the proposed model has improved significantly in all metrics compared with the state-of-the-art methods,especially achieving a score of 129.0 on the CIDEr-D evaluation metric,which also indicates that the proposed model can effectively provide a more reasonable and comprehensive description of the traffic scene.

Multi-Level Feature-Based Ensemble Model for Target-Related Stance Detection

Stance detection is the task of attitude identification toward a standpoint.Previous work of stance detection has focused on feature extraction but ignored the fact that irrelevant features exist as noise during higher-level abstracting.Moreover,because the target is not always mentioned in the text,most methods have ignored target information.In order to solve these problems,we propose a neural network ensemble method that combines the timing dependence bases on long short-term memory(LSTM)and the excellent extracting performance of convolutional neural networks(CNNs).The method can obtain multi-level features that consider both local and global features.We also introduce attention mechanisms to magnify target information-related features.Furthermore,we employ sparse coding to remove noise to obtain characteristic features.Performance was improved by using sparse coding on the basis of attention employment and feature extraction.We evaluate our approach on the SemEval-2016Task 6-A public dataset,achieving a performance that exceeds the benchmark and those of participating teams.

CPC INTERNATIONAL WORK FEATURING “POLITICAL GUIDANCE” UNDER NEW SITUATION

Since the 18th CPC National Congress,General Secretary Xi Jinping has raised new requirements for the Party’s international work under the new situation,emphasizing that on the basis of summarizing

基于跨模态引导和对齐的多模态预训练方法

现有的视觉语言多模态预训练方法仅在图像和文本的全局语义上进行特征对齐,对模态间细粒度特征交互的探索不足.针对这一问题,本文提出了一种基于跨模态引导和对齐的多模态预训练方法.该方法在模态特征提取阶段,采用基于视觉序列压缩的双流特征提取网络,在视觉编码器中联合图像和文本信息逐层引导视觉序列压缩,缓解与文本无关的冗余视觉信息对模态间细粒度交互的干扰;在模态特征对齐阶段,对图像和文本特征进行细粒度关系推理,实现视觉标记与文本标记的局部特征对齐,增强对模态间细粒度对齐关系的理解.实验结果表明,本文方法能够更好地对齐视觉文本的细粒度特征,在图文检索任务中,微调后的图像检索和文本检索的平均召回率分别达到了86.4%和94.88%,且零样本图文检索的整体指标相较于经典图文检索算法CLIP(Contrastive Language-Image Pre-training)提升了5.36%,在视觉问答等分类任务中,准确率也优于目前主流多模态预训练方法.

预指导的多阶段特征融合的图像语义分割网络

针对目前语义分割对图像边缘和小物体不能进行精确识别,以及简单融合多阶段特征会造成信息冗余、混杂不清等问题,提出了一个预指导的多阶段特征融合的网络(pre-guidanced multi-stage feature fusion network,PGMFFNet),PGMFFNet采用编解码器结构,编码阶段利用预指导模块对各阶段信息进行指导,增强各阶段特征之间的联系,解决各阶段特征在后续融合过程中产生的语义混杂问题。在解码阶段,利用多路径金字塔上采样模块融合高级语义特征,然后使用改进的密集空洞空间金字塔池化模块对融合后的特征进一步扩大感受野,最后将高低层次的特征信息融合,使得对小物体的分割效果更优。PGMFFNet在CityScapes公开数据集上进行了验证,得到了78.38%的平均交并比(mean intersection over union,MIoU),分割效果较好。

基于局部-全局特征耦合与边界引导的遥感图像建筑物变化检测

针对现有变化检测方法局部特征和全局特征难以兼顾、变化对象和背景之间分界模糊的问题,提出了一种基于局部-全局特征耦合与边界引导的遥感图像建筑物变化检测方法。该方法在编码阶段采用并行的卷积神经网络和Transformer分别提取遥感图像的局部特征与全局表示。在不同尺度下,使用局部-全局特征耦合模块融合局部特征和全局特征表示,以增强图像特征的表达能力。引入边界引导分支获取变化对象的先验边界信息,使其引导变化图突出建筑物的结构特征,促进边界精确定位。该方法在LEVIRCD和WHU数据集上进行实验验证,其F 1-score分别为91.25%和91.27%,IoU分别为83.90%和83.95%。实验结果表明,该方法在检测精度上有较大的提升,且具有良好的泛化能力。

基于视频图像驱动的驾驶人注意力估计方法

驾驶人视觉注意力的深入研究对于预测不安全驾驶行为和理解驾驶行为具有重要意义。为此,提出一种基于视频图像驱动的驾驶人注意力估计方法,以估计驾驶人在行车时注意到视域内的行人或车辆等各种对象。该方法利用深度神经网络学习交通场景视频与驾驶员注意力特征之间的映射关系,并融入引导学习模块来提取与驾驶员注意力最相关的特征。考虑到驾驶的动态性,使用动态交通场景视频作为模型输入,设计时空特征提取模块。在稀疏、密集、低照度等常见的交通场景中,将估计的驾驶员注意力模型与收集的驾驶员注意力数据点进行对比。实验结果表明,所提方法能够准确估计驾驶员在驾驶过程中的注意力,对于预测不安全驾驶行为以及促进人们更好地理解驾驶行为具有重要的理论和实用价值。

基于全局特征引导和注意力的宫颈细胞核分割

针对宫颈细胞中正常和异常细胞核大小形态各异、细胞图像中存在干扰物影响分割等问题,本文提出一种基于全局特征引导和注意力的分割网络来提高细胞核分割精度。首先以U型网络结构作为主体,引入全局特征引导模块,充分提取各个阶段的特征获得不同层次的全局上下文信息,克服了U型网络单阶段上下文信息提取能力不足的问题以更好地处理不同形状的细胞核,提高边缘分割精度;其次,引入改进的注意门结构抑制图像中干扰物的信息,突出细胞核的信息,提高模型对干扰信息的辨别能力。在Herlev数据集上的实验结果表明,本文的方法能够有效地提高细胞核分割精度,在定量分析中Dice系数为0.9413,相较于其他方法具有一定的优势。

基于光斑轮廓特征的目标快速识别算法研究

大视场的视觉着陆引导系统在引导无人机自主着陆过程中,需要快速检测出安装在无人机上的合作目标。该合作目标在图像上是以光斑形式存在,因此为了满足系统的实时性要求,本文提出了基于轮廓特征的快速检测光斑算法。该算法是根据光斑在图像中的特征,采用了目标裁剪方法,将原始图像中的光斑部分裁剪出来,从而降低算法运算量;再通过图像预处理,消除背景的无关信息与噪声干扰,增强光斑的清晰度;最后利用最小二乘算法进行椭圆拟合定位出光斑的中心位置。将本实验算法与其他光斑检测算法进行实验对比,从而验证系统的实时性。结果表明:利用本文算法可以在保证精度的同时将运行时间缩减到36 ms。

基于语义引导的人像自动抠图模型

为解决现有人像抠图方法中存在的语义判别错误和抠图细节模糊问题,提出一种基于语义引导的人像自动抠图模型。首先引入CNN-Transformer混合架构EMO进行特征编码。接着,在语义分割解码分支利用多尺度混合注意力模块处理最高层编码特征,以增强多尺度表征和像素级判别能力。然后,使用特征增强模块融合高层次特征,促使高层语义信息在浅层网络的流动。同时,细节抠取解码分支中的聚合以引导来自模块不同分支的特征聚合,利用聚合特征更好地引导网络提取浅层特征,提高了边缘细节抠取精度。在3个数据集上的实验表明,该方法与所比较方法相比性能达到了最优,并显著降低了参数量和计算复杂度,具有较高的竞争力。

基于特征调节器和双路径引导的RGB-D室内语义分割

针对室内场景图像语义分割结果不精确、显著图粗糙的问题,提出一种基于多模态特征优化提取和双路径引导解码的网络架构(feature regulator and dual-path guidance,FG-Net)。具体来说,设计的特征调节器对每个阶段的多模态特征依次进行噪声过滤、重加权表示、差异性互补和交互融合,通过强化RGB和深度特征聚合,优化特征提取过程中的多模态特征表示。然后,在解码阶段引入特征交互融合后丰富的跨模态线索,进一步发挥多模态特征的优势。结合双路径协同引导结构,在解码阶段融合多尺度、多层次的特征信息,从而输出更细致的显著图。实验在公开数据集NYUD-v2和SUN RGB-D上进行,在主要评价指标mIoU上达到48.5%,优于其他先进算法。结果表明,该算法实现了更精细的室内场景图像语义分割,表现出了较好的泛化性和鲁棒性。

基于暗通道先验引导的图像去雾网络

基于深度学习的去雾方法多数直接学习有雾图像和无雾图像之间的映射关系,未结合有雾图像自身特点,存在雾信息检测不精确、去雾不彻底的问题。针对该问题,提出一种基于暗通道先验引导的图像去雾网络(DCPDNet)。通过卷积层提取有雾图像的浅层特征;构建2个特征增强模块(FEB)来增强图像的空间特征,该模块在2个尺度上对图像特征进行增强,即利用深层特征图实现语义特征的增强,浅层特征图对实现图像细节特征的增强;为使提取的特征更关注雾的区域,基于有雾图像中雾的成像特点设计基于引导图的特征校正模块(FCB),利用暗通道先验理论构建引导图将网络学习的注意力引导到有雾区域,对提取的深层特征图做进一步的细化和校正;利用残差结构的跳转连接,将增强的浅层特征补充网络丢失的细节特征,并经过卷积操作重建去雾后图像。实验结果证明:DCPDNet可以在保持模型轻量型及运行速度较快的情况下实现良好的去雾效果。与近年先进的去雾方法进行比较,DCPDNet不仅在效率上占有优势,其去雾效果在主观视觉感受和客观评价结果上都获得了更好的效果。

基于边界特征融合和前景引导的伪装目标检测

伪装目标检测旨在检测隐藏在复杂环境中的高度隐蔽物体,在医学、农业等多个领域有重要应用价值.现有方法结合边界先验过分强调边界区域,对伪装目标内部信息的表征不足,导致模型对伪装目标的内部区域检测不准确.同时,已有方法缺乏对伪装目标前景特征的有效挖掘,使背景区域被误检为伪装目标.为解决上述问题,本文提出一种基于边界特征融合和前景引导的伪装目标检测方法,该方法由特征提取、边界特征融合、主干特征增强和预测等若干个阶段构成.在边界特征融合阶段,首先,通过边界特征提取模块获得边界特征并预测边界掩码;然后,边界特征融合模块将边界特征和边界掩码与最低层次的主干特征有效融合;同时,加强伪装目标边界位置及内部区域特征.此外,设计前景引导模块,利用预测的伪装目标掩码增强主干特征,即将前一层特征预测的伪装目标掩码作为当前层特征的前景注意力,并对特征执行空间交互,提升网络对空间关系的识别能力,使网络关注精细而完整的伪装目标区域.本文在4个广泛使用的基准数据集上的实验结果表明,提出的方法优于对比的19个主流方法,对伪装目标检测任务具有更强鲁棒性和泛化能力.

融合结构与纹理特征的壁画缺陷修复

针对现有算法在修复花纹复杂的壁画时存在结构混乱和纹理模糊等缺陷,提出一种融合结构与纹理特征引导的双重生成对抗网络模型。首先将U-Net引入双重生成网络,利用方向和通道双注意力机制提取到的纹理和结构信息分别引导结构、纹理解码器完成对结构与纹理的特征重构,并结合空洞残差块与跳跃连接实现多尺度特征融合提取。其次将两个分支输出的特征图通过双门控特征融合模块深度融合,完成特征信息交互。最后通过联合双判别器对抗完成缺陷修复,增强壁画修复效果的细节丰富度和全局一致性。实验使用自制数据集五台山某处非国宝级真实壁画进行训练及测试,并通过对比实验和消融实验验证,所提算法在峰值信噪比指标上平均提升4.24 dB,结构相似性指标上平均提升3.6%。实验表明该方法可以对受损的壁画进行有效修复,使其呈现出较好的结构、纹理信息,且视觉效果更清晰自然。

习近平文化思想的价值意蕴与文化引领

文化兴则国运兴,文化强则民族强。习近平文化思想是习近平新时代中国特色社会主义思想的重要组成部分,是新时代中国共产党领导文化建设实践经验的理论总结和智慧结晶。习近平文化思想彰显了党性与人民性相统一、文化传承与文化创新相统一、历史自信与文化自信相统一、民族性与世界性相统一的鲜明特征,它是马克思主义文化理论中国化最新理论成果,表明中国共产党对社会主义文化建设规律的认识达到了新的高度,为新时代新征程推进中国特色社会主义文化强国建设提供了强大的思想武器和科学的理论指南。

特征对齐与上下文引导的多视图三维重建

针对三维重建对细小特征及边缘区域重建欠佳的问题,提出了一个基于特征对齐与上下文引导的多视图三维重建网络,即AGA-MVSNet。首先,构建了一个特征对齐模块(FA)与特征选择模块(FS),能够将特征金字塔不同层级的特征先对齐之后再进行融合,提高对小尺寸物体和边缘区域的特征提取能力;然后,在代价体正则化中加入了一个上下文引导模块,该模块能够在略微增加运行内存的情况下充分利用周围信息,增强成本体积之间的相关性,提高三维重建的精度与完整度;最后,在DTU数据集上进行了实验,实验结果表明,该方法相比于基准网络CasMVSNet精度提升了2.2%,整体重建质量提升了2.5%。此外,在Tanks and Temples数据集上的表现相较一些已知的方法也十分优异,且在BlendedMVS数据集上也生成了不错的点云效果。