DOCUMENT/PORTRAIT

m97 Gallery, Shanghai September 4-October 11 All images courtesy of m97 Gallery ■ As one of the only photography galleries in Shanghai,m97 works hard towards its goal to'exhibit the most interesting and innovative photography work in China'.

Attention-Enhanced Voice Portrait Model Using Generative Adversarial Network

Voice portrait technology has explored and established the relationship between speakers’ voices and their facialfeatures, aiming to generate corresponding facial characteristics by providing the voice of an unknown speaker.Due to its powerful advantages in image generation, Generative Adversarial Networks (GANs) have now beenwidely applied across various fields. The existing Voice2Face methods for voice portraits are primarily based onGANs trained on voice-face paired datasets. However, voice portrait models solely constructed on GANs facelimitations in image generation quality and struggle to maintain facial similarity. Additionally, the training processis relatively unstable, thereby affecting the overall generative performance of the model. To overcome the abovechallenges,wepropose a novel deepGenerativeAdversarialNetworkmodel for audio-visual synthesis, namedAVPGAN(Attention-enhanced Voice Portrait Model using Generative Adversarial Network). This model is based ona convolutional attention mechanism and is capable of generating corresponding facial images from the voice ofan unknown speaker. Firstly, to address the issue of training instability, we integrate convolutional neural networkswith deep GANs. In the network architecture, we apply spectral normalization to constrain the variation of thediscriminator, preventing issues such as mode collapse. Secondly, to enhance the model’s ability to extract relevantfeatures between the two modalities, we propose a voice portrait model based on convolutional attention. Thismodel learns the mapping relationship between voice and facial features in a common space from both channeland spatial dimensions independently. Thirdly, to enhance the quality of generated faces, we have incorporated adegradation removal module and utilized pretrained facial GANs as facial priors to repair and enhance the clarityof the generated facial images. Experimental results demonstrate that our AVP-GAN achieved a cosine similarity of0.511, outperforming the performance of our comparison model, and effectively achieved the generation of highqualityfacial images corresponding to a speaker’s voice.

A Framework Based on the DAO and NFT in Blockchain for Electronic Document Sharing

In the information age,electronic documents(e-documents)have become a popular alternative to paper documents due to their lower costs,higher dissemination rates,and ease of knowledge sharing.However,digital copyright infringements occur frequently due to the ease of copying,which not only infringes on the rights of creators but also weakens their creative enthusiasm.Therefore,it is crucial to establish an e-document sharing system that enforces copyright protection.However,the existing centralized system has outstanding vulnerabilities,and the plagiarism detection algorithm used cannot fully detect the context,semantics,style,and other factors of the text.Digital watermark technology is only used as a means of infringement tracing.This paper proposes a decentralized framework for e-document sharing based on decentralized autonomous organization(DAO)and non-fungible token(NFT)in blockchain.The use of blockchain as a distributed credit base resolves the vulnerabilities inherent in traditional centralized systems.The e-document evaluation and plagiarism detection mechanisms based on the DAO model effectively address challenges in comprehensive text information checks,thereby promoting the enhancement of e-document quality.The mechanism for protecting and circulating e-document copyrights using NFT technology ensures effective safeguarding of users’e-document copyrights and facilitates e-document sharing.Moreover,recognizing the security issues within the DAO governance mechanism,we introduce an innovative optimization solution.Through experimentation,we validate the enhanced security of the optimized governance mechanism,reducing manipulation risks by up to 51%.Additionally,by utilizing evolutionary game analysis to deduce the equilibrium strategies of the framework,we discovered that adjusting the reward and penalty parameters of the incentive mechanism motivates creators to generate superior quality and unique e-documents,while evaluators are more likely to engage in assessments.

An explorative study on document type assignment of review articles in Web of Science,Scopus and journals’websites

Purpose:Accurately assigning the document type of review articles in citation index databases like Web of Science(WoS)and Scopus is important.This study aims to investigate the document type assignation of review articles in Web of Science,Scopus and Publisher’s websites on a large scale.Design/methodology/approach:27,616 papers from 160 journals from 10 review journal series indexed in SCI are analyzed.The document types of these papers labeled on journals’websites,and assigned by WoS and Scopus are retrieved and compared to determine the assigning accuracy and identify the possible reasons for wrongly assigning.For the document type labeled on the website,we further differentiate them into explicit review and implicit review based on whether the website directly indicates it is a review or not.Findings:Overall,WoS and Scopus performed similarly,with an average precision of about 99% and recall of about 80%.However,there were some differences between WoS and Scopus across different journal series and within the same journal series.The assigning accuracy of WoS and Scopus for implicit reviews dropped significantly,especially for Scopus.Research limitations:The document types we used as the gold standard were based on the journal websites’labeling which were not manually validated one by one.We only studied the labeling performance for review articles published during 2017-2018 in review journals.Whether this conclusion can be extended to review articles published in non-review journals and most current situation is not very clear.Practical implications:This study provides a reference for the accuracy of document type assigning of review articles in WoS and Scopus,and the identified pattern for assigning implicit reviews may be helpful to better labeling on websites,WoS and Scopus.Originality/value:This study investigated the assigning accuracy of document type of reviews and identified the some patterns of wrong assignments.

Hybrid Optimization Algorithm for Handwritten Document Enhancement

The Gannet Optimization Algorithm (GOA) and the Whale Optimization Algorithm (WOA) demonstrate strong performance;however, there remains room for improvement in convergence and practical applications. This study introduces a hybrid optimization algorithm, named the adaptive inertia weight whale optimization algorithm and gannet optimization algorithm (AIWGOA), which addresses challenges in enhancing handwritten documents. The hybrid strategy integrates the strengths of both algorithms, significantly enhancing their capabilities, whereas the adaptive parameter strategy mitigates the need for manual parameter setting. By amalgamating the hybrid strategy and parameter-adaptive approach, the Gannet Optimization Algorithm was refined to yield the AIWGOA. Through a performance analysis of the CEC2013 benchmark, the AIWGOA demonstrates notable advantages across various metrics. Subsequently, an evaluation index was employed to assess the enhanced handwritten documents and images, affirming the superior practical application of the AIWGOA compared with other algorithms.

Multimodal Deep Neural Networks for Digitized Document Classification

As digital technologies have advanced more rapidly,the number of paper documents recently converted into a digital format has exponentially increased.To respond to the urgent need to categorize the growing number of digitized documents,the classification of digitized documents in real time has been identified as the primary goal of our study.A paper classification is the first stage in automating document control and efficient knowledge discovery with no or little human involvement.Artificial intelligence methods such as Deep Learning are now combined with segmentation to study and interpret those traits,which were not conceivable ten years ago.Deep learning aids in comprehending input patterns so that object classes may be predicted.The segmentation process divides the input image into separate segments for a more thorough image study.This study proposes a deep learning-enabled framework for automated document classification,which can be implemented in higher education.To further this goal,a dataset was developed that includes seven categories:Diplomas,Personal documents,Journal of Accounting of higher education diplomas,Service letters,Orders,Production orders,and Student orders.Subsequently,a deep learning model based on Conv2D layers is proposed for the document classification process.In the final part of this research,the proposed model is evaluated and compared with other machine-learning techniques.The results demonstrate that the proposed deep learning model shows high results in document categorization overtaking the other machine learning models by reaching 94.84%,94.79%,94.62%,94.43%,94.07%in accuracy,precision,recall,F-score,and AUC-ROC,respectively.The achieved results prove that the proposed deep model is acceptable to use in practice as an assistant to an office worker.

Impact of Laboratory Value Flowsheet in Electronic Health Record (EHR) Documentation Time

Research on the use of EHR is contradictory since it presents contradicting results regarding the time spent documenting. There is research that supports the use of electronic records as a tool to speed documentation;and research that found that it is time consuming. The purpose of this quantitative retrospective before-after project was to measure the impact of using the laboratory value flowsheet within the EHR on documentation time. The research question was: “Does the use of a laboratory value flowsheet in the EHR impact documentation time by primary care providers (PCPs)?” The theoretical framework utilized in this project was the Donabedian Model. The population in this research was the two PCPs in a small primary care clinic in the northwest of Puerto Rico. The sample was composed of all the encounters during the months of October 2019 and December 2019. The data was obtained through data mining and analyzed using SPSS 27. The evaluative outcome of this project is that there is a decrease in documentation time after implementation of the use of the laboratory value flowsheet in the EHR. However, patients per day increase therefore having an impact on the number of patients seen per day/week/month. The implications for clinical practice include the use of templates to improve workflow and documentation as well as decreasing documentation time while also increasing the number of patients seen per day. .

Pre-training transformer with dual-branch context content module for table detection in document images

Background Document images such as statistical reports and scientific journals are widely used in information technology.Accurate detection of table areas in document images is an essential prerequisite for tasks such as information extraction.However,because of the diversity in the shapes and sizes of tables,existing table detection methods adapted from general object detection algorithms,have not yet achieved satisfactory results.Incorrect detection results might lead to the loss of critical information.Methods Therefore,we propose a novel end-to-end trainable deep network combined with a self-supervised pretraining transformer for feature extraction to minimize incorrect detections.To better deal with table areas of different shapes and sizes,we added a dual-branch context content attention module(DCCAM)to high-dimensional features to extract context content information,thereby enhancing the network's ability to learn shape features.For feature fusion at different scales,we replaced the original 3×3 convolution with a multilayer residual module,which contains enhanced gradient flow information to improve the feature representation and extraction capability.Results We evaluated our method on public document datasets and compared it with previous methods,which achieved state-of-the-art results in terms of evaluation metrics such as recall and F1-score.

Research and Analysis of Grammatical Error Correction Technology for Chinese Documents

With the widespread use of Chinese globally, the number of Chinese learners has been increasing, leading to various grammatical errors among beginners. Additionally, as domestic efforts to develop industrial information grow, electronic documents have also proliferated. When dealing with numerous electronic documents and texts written by Chinese beginners, manually written texts often contain hidden grammatical errors, posing a significant challenge to traditional manual proofreading. Correcting these grammatical errors is crucial to ensure fluency and readability. However, certain special types of text grammar or logical errors can have a huge impact, and manually proofreading a large number of texts individually is clearly impractical. Consequently, research on text error correction techniques has garnered significant attention in recent years. The advent and advancement of deep learning have paved the way for sequence-to-sequence learning methods to be extensively applied to the task of text error correction. This paper presents a comprehensive analysis of Chinese text grammar error correction technology, elaborates on its current research status, discusses existing problems, proposes preliminary solutions, and conducts experiments using judicial documents as an example. The aim is to provide a feasible research approach for Chinese text error correction technology.

Camilla Guerrieri’s Portrait of Guidobaldo II della Rovere:Symbols of Honor and Power

The Altomani&Sons Collection owns a remarkable newly discovered portrait of Guidobaldo II della Rovere,Duke of Urbino(1514-1574),a historical military figure who was a condottiere,ruler of Urbino,Commander-in-chief of the Papal Estate,and Perfect of Rome,as well as a collector and patron of the Fine Arts.Camilla Guerrieri Nati(1628-1694),a seventeenth-century Italian painter from Fossombrone(in the province of Pesaro and Urbino),portrayed this heroic personage surrounded by emblems associated with his military courage and leadership,including his plumed burgonet helmet,metal gilded armor,a necklace with the golden fleece,and batons of secular and religious dominions.This oil painting on copper-considered a precious metal at the time-emphasizes the importance of the commission.The material and technique also reveals a unique artistic achievement in that it provides the painting with a smooth,reflective surface and vibrant coloration,symbolizing precious imagery.

Trust evaluation model of power terminal based on equipment portrait

As the number of power terminals continues to increase and their usage becomes more widespread,the security of power systems is under great threat.In response to the lack of effective trust evaluation methods for terminals,we propose a trust evaluation model based on equipment portraits for power terminals.First,we propose an exception evaluation method based on the network flow order and evaluate anomalous terminals by monitoring the external characteristics of network traffic.Second,we propose an exception evaluation method based on syntax and semantics.The key fields of each message are extracted,and the frequency of keywords in the message is statistically analyzed to obtain the keyword frequency and time-slot threshold for evaluating the status of the terminal.Thus,by combining the network flow order,syntax,and semantic analysis,an equipment portrait can be constructed to guarantee security of the power network terminals.We then propose a trust evaluation method based on an equipment portrait to calculate the trust values in real time.Finally,the experimental results of terminal anomaly detection show that the proposed model has a higher detection rate and lower false detection rate,as well as a higher real-time performance,which is more suitable for power terminals.

Semantic Document Layout Analysis of Handwritten Manuscripts

A document layout can be more informative than merely a document’s visual and structural appearance.Thus,document layout analysis(DLA)is considered a necessary prerequisite for advanced processing and detailed document image analysis to be further used in several applications and different objectives.This research extends the traditional approaches of DLA and introduces the concept of semantic document layout analysis(SDLA)by proposing a novel framework for semantic layout analysis and characterization of handwritten manuscripts.The proposed SDLA approach enables the derivation of implicit information and semantic characteristics,which can be effectively utilized in dozens of practical applications for various purposes,in a way bridging the semantic gap and providingmore understandable high-level document image analysis and more invariant characterization via absolute and relative labeling.This approach is validated and evaluated on a large dataset ofArabic handwrittenmanuscripts comprising complex layouts.The experimental work shows promising results in terms of accurate and effective semantic characteristic-based clustering and retrieval of handwritten manuscripts.It also indicates the expected efficacy of using the capabilities of the proposed approach in automating and facilitating many functional,reallife tasks such as effort estimation and pricing of transcription or typing of such complex manuscripts.

An Early Warning Model of Telecommunication Network Fraud Based on User Portrait

With the frequent occurrence of telecommunications and networkfraud crimes in recent years, new frauds have emerged one after another whichhas caused huge losses to the people. However, due to the lack of an effectivepreventive mechanism, the police are often in a passive position. Usingtechnologies such as web crawlers, feature engineering, deep learning, andartificial intelligence, this paper proposes a user portrait fraudwarning schemebased on Weibo public data. First, we perform preliminary screening andcleaning based on the keyword “defrauded” to obtain valid fraudulent userIdentity Documents (IDs). The basic information and account information ofthese users is user-labeled to achieve the purpose of distinguishing the typesof fraud. Secondly, through feature engineering technologies such as avatarrecognition, Artificial Intelligence (AI) sentiment analysis, data screening,and follower blogger type analysis, these pictures and texts will be abstractedinto user preferences and personality characteristics which integrate multidimensionalinformation to build user portraits. Third, deep neural networktraining is performed on the cube. 80% percent of the data is predicted basedon the N-way K-shot problem and used to train the model, and the remaining20% is used for model accuracy evaluation. Experiments have shown thatFew-short learning has higher accuracy compared with Long Short TermMemory (LSTM), Recurrent Neural Networks (RNN) and ConvolutionalNeural Network (CNN). On this basis, this paper develops a WeChat smallprogram for early warning of telecommunications network fraud based onuser portraits. When the user enters some personal information on the frontend, the back-end database can perform correlation analysis by itself, so as tomatch the most likely fraud types and give relevant early warning information.The fraud warning model is highly scaleable. The data of other Applications(APPs) can be extended to further improve the efficiency of anti-fraud whichhas extremely high public welfare value.

Local-to-Global Causal Reasoning for Cross-Document Relation Extraction

Cross-document relation extraction(RE),as an extension of information extraction,requires integrating information from multiple documents retrieved from open domains with a large number of irrelevant or confusing noisy texts.Previous studies focus on the attention mechanism to construct the connection between different text features through semantic similarity.However,similarity-based methods cannot distinguish valid information from highly similar retrieved documents well.How to design an effective algorithm to implement aggregated reasoning in confusing information with similar features still remains an open issue.To address this problem,we design a novel local-toglobal causal reasoning(LGCR)network for cross-document RE,which enables efficient distinguishing,filtering and global reasoning on complex information from a causal perspective.Specifically,we propose a local causal estimation algorithm to estimate the causal effect,which is the first trial to use the causal reasoning independent of feature similarity to distinguish between confusing and valid information in cross-document RE.Furthermore,based on the causal effect,we propose a causality guided global reasoning algorithm to filter the confusing information and achieve global reasoning.Experimental results under the closed and the open settings of the large-scale dataset Cod RED demonstrate our LGCR network significantly outperforms the state-ofthe-art methods and validate the effectiveness of causal reasoning in confusing information processing.

PP-GAN:Style Transfer from Korean Portraits to ID Photos Using Landmark Extractor with GAN

The objective of style transfer is to maintain the content of an image while transferring the style of another image.However,conventional methods face challenges in preserving facial features,especially in Korean portraits where elements like the“Gat”(a traditional Korean hat)are prevalent.This paper proposes a deep learning network designed to perform style transfer that includes the“Gat”while preserving the identity of the face.Unlike traditional style transfer techniques,the proposed method aims to preserve the texture,attire,and the“Gat”in the style image by employing image sharpening and face landmark,with the GAN.The color,texture,and intensity were extracted differently based on the characteristics of each block and layer of the pre-trained VGG-16,and only the necessary elements during training were preserved using a facial landmark mask.The head area was presented using the eyebrow area to transfer the“Gat”.Furthermore,the identity of the face was retained,and style correlation was considered based on the Gram matrix.To evaluate performance,we introduced a metric using PSNR and SSIM,with an emphasis on median values through new weightings for style transfer in Korean portraits.Additionally,we have conducted a survey that evaluated the content,style,and naturalness of the transferred results,and based on the assessment,we can confidently conclude that our method to maintain the integrity of content surpasses the previous research.Our approach,enriched by landmarks preservation and diverse loss functions,including those related to“Gat”,outperformed previous researches in facial identity preservation.

Restoration of Folk Document Covers from the Qing Dynasty to the Republic of China

The covers of booklets and books in folk documents primarily serve to protect the pages.Owing to long-term storage limitations,a considerable number of book covers have suffered varying degrees of damage.Following the principles of restoration,a comparative analysis and restoration of folk document covers were conducted,selecting four different types of carriers from the Taihang Mountain Documents,ranging from the Qing dynasty to the Republican Era.These carriers included hemp,mulberry bark,and machinemade paper,and cotton blue cloth.Each cover type was matched with an appropriate restoration paper,and different methods were employed during the restoration process.Through restoration,the previously damaged document covers can continue to fulfill their role in protecting the books,thereby extending the lifespan of these four folk documents.

基于用户画像的高校采购评审专家推荐算法

该文设计了一种可调参的混合推荐算法,融合AUC-MF算法与基于专家画像及项目画像的抽取算法,以提高高校随机抽取评审专家的专业匹配度,解决数据稀疏和冷启动问题。该文以某高校近6年政府采购项目历史评审数据以及项目文本信息构建数据集,对算法进行验证,该算法可有效缓解高校自选评审专家过程中的数据稀疏和冷启动问题,提高随机抽取专家的专业匹配度。

Functions of Karez to Xinjiang Agriculture in the Qing Dynasty from the Perspective of Historical Documents

Desertification is increasingly serious in Xinjiang,and the construction of water conservancy is a precondition for the development of agriculture.The main project for the development of agriculture and water conservancy in Xinjiang is to build Karez,which played a vital role in the development of Xinjiang agriculture in the Qing Dynasty.It has been recorded many times in historical documents of the Qing Dynasty,such as Lin Zexu s Diary,Tao Baolian s Diary,Xinjiang Atlas and Zuo Zongtang s Memorial to the Emperor,etc.,which recorded the situation and historical origin of Karez.Karez made a significant contribution to the development of agriculture in the Qing Dynasty.It increased the cultivated land in Xinjiang at that time,and increased the types and yields of crops.It is conducive to the stability and development of Xinjiang s economy.Until today,Karez is still an important water source for agricultural irrigation in Xinjiang.

基于画像技术的教师研修路径智能推荐研究

教师是教育的第一资源,研修是促进教师专业发展的重要方式。在大数据、数字画像等新技术赋能下,优化教师研修路径以提升教师发展质量变得尤为重要。文章构建了多模态数据和画像技术支持的教师研修路径智能推荐模型,包括数据伴随式采集分类与预处理、教师画像生成、研修路径算法三个模块,实现教师研修特征与优质研修资源的智能匹配。在教师研修路径动态优化方面,模型通过提供基于画像的个性化导研服务、基于知识图谱的资源关联推荐、基于群体智能的群体路径发现、基于目标导向的过程评价和基于研修行为的智能预警,满足教师的个性化研修需求,为发掘研修数据潜能、促进教师智能研修模式创新提供参考。

Human Rights in Civil Judicial Documents:Conception and Function

Traditional human rights theory tends to hold that human rights should be aimed at defending public authority and that the legal issue of human rights is a matter of public law.However,the development of human rights concepts and practices is not just confined to this.A textual search shows that the term“human rights”exists widely in China’s civil judicial documents.Among the 3,412 civil judicial documents we researched,the concept of“human rights”penetrates all kinds of disputes in lawsuits,ranging from property rights,contracts,labor,and torts to marital property,which is embedded in both the claims of the parties concerned and the reasoning of judges.Human rights have become the discourse and yardstick for understanding and evaluating social behavior.The widespread use of the term“human rights”in civil judicial documents reflects at least three concepts related to human rights:first,the rights to subsistence and development are the primary basic human rights;second,the judicial protection of human rights is a bottom-line guarantee;third,the protection of human rights aims to achieve equal rights.Today,judges quote the theory of human rights in judicial judgments from time to time,evidencing that human rights have a practical function in judicial adjudication activities,and in practice this is mainly manifested in declaring righteous values and strengthening arguments with the values and ideas related to human rights,using the provisions concerning human rights in the Constitution to interpret the constitutionality,and using the principles of human rights to interpret blurred rules and rank the importance of different rights.