Enhancing Cross-Lingual Image Description: A Multimodal Approach for Semantic Relevance and Stylistic Alignment

Cross-lingual image description,the task of generating image captions in a target language from images and descriptions in a source language,is addressed in this study through a novel approach that combines neural network models and semantic matching techniques.Experiments conducted on the Flickr8k and AraImg2k benchmark datasets,featuring images and descriptions in English and Arabic,showcase remarkable performance improvements over state-of-the-art methods.Our model,equipped with the Image&Cross-Language Semantic Matching module and the Target Language Domain Evaluation module,significantly enhances the semantic relevance of generated image descriptions.For English-to-Arabic and Arabic-to-English cross-language image descriptions,our approach achieves a CIDEr score for English and Arabic of 87.9%and 81.7%,respectively,emphasizing the substantial contributions of our methodology.Comparative analyses with previous works further affirm the superior performance of our approach,and visual results underscore that our model generates image captions that are both semantically accurate and stylistically consistent with the target language.In summary,this study advances the field of cross-lingual image description,offering an effective solution for generating image captions across languages,with the potential to impact multilingual communication and accessibility.Future research directions include expanding to more languages and incorporating diverse visual and textual data sources.

Description logics for fuzzy ontologies on semantic web

To enable representation and reasoning for fuzzy ontologies with expressive fuzzy knowledge on the semantic web, a new fuzzy extension of description logics called the fuzzy description logics with comparison expressions （FCDLs） is presented. The syntax and semantics of FCDLs are formally defined, and the forms of axioms and assertions in FCDLs knowledge bases are specified. FCDLs combine both fuzzy concepts from the fuzzy description logics （FDLs） and cut concepts from the extended fuzzy description logics （EFDLs） in the same theory. Furthermore, cut concepts are extended into comparison cut concepts in FCDLs to represent comparison expressions between fuzzy membership degrees, which are often used in practice but not supported by the other fuzzy extensions of description logics. FCDLs have more expressive power than FDLs and EFDLs, and are able to represent expressive fuzzy knowledge and to perform reasoning tasks based on them. Therefore, FCDLs can enable representation and reasoning for fuzzy ontologies with expressive fuzzy knowledge on the semantic web.

Clustering analysis algorithm for security supervising data based on semantic description in coal mines

In order to mine production and security information from security supervising data and to ensure security and safety involved in production and decision-making,a clustering analysis algorithm for security supervising data based on a semantic description in coal mines is studied.First,the semantic and numerical-based hybrid description method of security supervising data in coal mines is described.Secondly,the similarity measurement method of semantic and numerical data are separately given and a weight-based hybrid similarity measurement method for the security supervising data based on a semantic description in coal mines is presented.Thirdly,taking the hybrid similarity measurement method as the distance criteria and using a grid methodology for reference,an improved CURE clustering algorithm based on the grid is presented.Finally,the simulation results of a security supervising data set in coal mines validate the efficiency of the algorithm.

Web Service Description and Discovery Based on Semantic Model

A novel semantic model of Web service descrip tion and discovery was proposed through an extension for profile model of Web ontology language for services （OWL-S） in this paper. Similarity matching of Web services was implemented through computing weighted summation of semantic similarity value based on specific domain ontology and dynamical satisfy extent evaluation for quality of service （QoS）. Experiments show that the provided semantic matching model is efficient.

Construction and Resource Locating of Semantic P2P Grid Based on Description Logics

This paper proposes an algorithm applied in se mantic P2P network based on the description logics with the purpose for realizing the concepts distribution of resources, which makes the resources semantic locating easy. With the idea of the consistent hashing in the Chord, our algorithm stores the addresses and resources with the values of the same type to select instance. In addition, each peer has its own ontology, which will be completed by the knowledge distributed over the network during the exchange of CHGs （classification hierarchy graphs）. The hierarchy classification of concepts allows to find matching resource by querying to the upper level concept because the all concepts described in the CHG have the same root.

New method for query answering in semantic web

To promote the efficiency of knowledge base retrieval based on description logic, the concept of assertional graph （AG）, which is directed labeled graph, is defined and a new AG-based retrieval method is put forward. This method converts the knowledge base and query clause into knowledge AG and query AG by making use of the given rules and then makes use of graph traversal to carry out knowledge base retrieval. The experiment indicates that the efficiency of this method exceeds, respectively, the popular RACER and KAON2 system by 0.4% and 3.3%. This method can obviously promote the efficiency of knowledge base retrieval.

Fuzzy description logic based on vague sets

To enable the representation and reasoning for fuzzy ontologies with expressive fuzzy knowledge on the semantic web, a new fuzzy extension of description logics called vague ALC which is based on vague sets is presented. The definition of vague set is introduced and then the syntax and semantics of vague ALC are formally defined. The forms of axioms and assertions in the vague ALC knowledge bases are specified. Finally, the tableau algorithm is developed for the reasoning in the vague ALC. The vague ALC based on vague set uses two degrees of membership instead of a single membership degree in the fuzzy sets and is more accurate in representing the imprecision in the degrees of membership. The vague ALC has more expressive power than ALC and can represent fuzzy knowledge and perform reasoning tasks based on them. Therefore, the vague ALC can enable the representation and reasoning for fuzzy ontologies with expressive fuzzy knowledge on the semantic web.

A Dynamic Fuzzy Description Logic

Fuzzy description logics are considered as the logical infrastructure of fuzzy knowledge representation on the semantic Web. To deal with fuzzy and dynamic knowledge on the semantic Web and its applications, a new fuzzy extension of Attribute Language with Complement based on dynamic fuzzy logic called the dynamic fuzzy description logic （DFALC） is presented. The syntax and semantics of DFALC are formally defined, and the forms of axioms and assertions are specified. The DFALC provides more reasonable logic foundation for the semantic Web, and overcomes the insufficiency of using fuzzy description logic FALC to act as logical foundation for the semantic Web. The extended DFALC is more expressive than the existing fuzzy description logics and present more fuzzy information on the semantic Web.

A Comparison of Paraconsistent Description Logics

Description logics (DLs) are a family of logic-based knowledge representation formalisms with a number of computer science applications. DLs are especially well-known to be valuable for obtaining logical foundations of web ontology languages (e.g., W3C’s ontology language OWL). Paraconsistent (or inconsistency-tolerant) description logics (PDLs) have been studied to cope with inconsistencies which may frequently occur in an open world. In this paper, a comparison and survey of PDLs is presented. It is shown that four existing paraconsistent semantics (i.e., four-valued semantics, quasi-classical semantics, single-interpretation semantics and dual-interpretation semantics) for PDLs are essentially the same semantics. To show this, two generalized and extended new semantics are introduced, and an equivalence between them is proved.

“SEMANTIC” in a Digital Curation Model

Purpose:This study attempts to propose an abstract model by gathering concepts that can focus on resource representation and description in a digital curation model and suggest a conceptual model that emphasizes semantic enrichment in a digital curation model.Design/methodology/approach:This study conducts a literature review to analyze the preceding curation models,DCC CLM,DCC&U,UC3,and DCN.Findings:The concept of semantic enrichment is expressed in a single word,SEMANTIC in this study.The Semantic Enrichment Model,SEMANTIC has elements,subject,extraction,multi-language,authority,network,thing,identity,and connect.Research limitations:This study does not reflect the actual information environment because it focuses on the concepts of the representation of digital objects.Practical implications:This study presents the main considerations for creating and reinforcing the description and representation of digital objects when building and developing digital curation models in specific institutions.Originality/value:This study summarizes the elements that should be emphasized in the representation of digital objects in terms of information organization.

Monitoring of Unaccounted for Gas in Energy Domain Using Semantic Web Technologies

Smart Urbanization has increased tremendously over the last few years,and this has exacerbated problems in all areas of life,especially in the energy sector.The Internet of Things(IoT)is providing effective solutions in gas distribution,transmission and billing through very sophisticated sensory devices and software.Billions of heterogeneous devices link to each other in smart urbanization,and this has led to the Semantic interoperability(SI)problem between the connected devices.In the energy field,such as electricity and gas,several devices are interlinked.These devices are competent for their specific operational role but unable to communicate across the operational units as required for accounting and monitoring of gas losses due to heterogeneity in device communication standards.To overcome this problem,we have proposed a model and ontology by applying semantic web technologies and cloud storage to address the tracking of customers to observe Unaccounted for gas(UFG)in the gas domain of energy.Semantization is achieved by replicating heterogeneous devices Sensor Model Language(SenML)data into Resource description framework(RDF)without human interventions.As semantic interoperability is used to efficiently and meaningfully share the information from one location to another.Therefore,the proposed ontology and model focus more efficiently on customer tracking,forecasting,and monitoring to detect UFG in gas networks.This also helps to save Gas Companies from financial gas losses.

Heuristics based semantic annotation of biodiversity documents in Chinese

Purpose: To design an efficient high-performance algorithm for semantic annotation of biodiversity documents in Chinese.Design/methodology/approach: Data set consists of 1,000 randomly selected documents from Flora of China. Comparative evaluation of the proposed approach with the Na ve Bayes algorithm have been developed before for the same purpose.Findings: Experimental results show that the heuristics based algorithm outperformed the Na ve Bayes algorithm. The use of leading words helped improving the annotation performance while prioritizing rule application based on their weights had no significant impact on algorithm performance.Research limitations: The ICTCLAS was used to identify word boundaries off-shelf without optimatization for biodiversity domain. This may have not made the best use of the tool.Practical implications & Originality/value: The performance of heuristics based approach,enhanced by leading words analysis, reached an F value of 0.9216, which is sufficiently accurate for practical use.

A Survey on Deep Learning-based Fine-grained Object Classification and Semantic Segmentation

The deep learning technology has shown impressive performance in various vision tasks such as image classification, object detection and semantic segmentation. In particular, recent advances of deep learning techniques bring encouraging performance to fine-grained image classification which aims to distinguish subordinate-level categories, such as bird species or dog breeds. This task is extremely challenging due to high intra-class and low inter-class variance. In this paper, we review four types of deep learning based fine-grained image classification approaches, including the general convolutional neural networks （CNNs）, part detection based, ensemble of networks based and visual attention based fine-grained image classification approaches. Besides, the deep learning based semantic segmentation approaches are also covered in this paper. The region proposal based and fully convolutional networks based approaches for semantic segmentation are introduced respectively.

Zero-shot Fine-grained Classification by Deep Feature Learning with Semantics

Fine-grained image classification, which aims to distinguish images with subtle distinctions, is a challenging task for two main reasons: lack of sufficient training data for every class and difficulty in learning discriminative features for representation. In this paper, to address the two issues, we propose a two-phase framework for recognizing images from unseen fine-grained classes, i.e., zeroshot fine-grained classification. In the first feature learning phase, we finetune deep convolutional neural networks using hierarchical semantic structure among fine-grained classes to extract discriminative deep visual features. Meanwhile, a domain adaptation structure is induced into deep convolutional neural networks to avoid domain shift from training data to test data. In the second label inference phase, a semantic directed graph is constructed over attributes of fine-grained classes. Based on this graph, we develop a label propagation algorithm to infer the labels of images in the unseen classes. Experimental results on two benchmark datasets demonstrate that our model outperforms the state-of-the-art zero-shot learning models. In addition, the features obtained by our feature learning model also yield significant gains when they are used by other zero-shot learning models, which shows the flexility of our model in zero-shot finegrained classification.

Semantic Description and Verification of Security Policy Based on Ontology

To solve the shortage problem of the semantic descrip- tion scope and verification capability existed in the security policy, a semantic description method for the security policy based on ontology is presented. By defining the basic elements of the security policy, the relationship model between the ontology and the concept of security policy based on the Web ontology language （OWL） is established, so as to construct the semantic description framework of the security policy. Through modeling and reasoning in the Protege, the ontology model of authorization policy is proposed, and the first-order predicate description logic is introduced to the analysis and verification of the model. Results show that the ontology-based semantic description of security policy has better flexibility and practicality.

基于Transformer网络多模态融合的密集视频描述方法

针对目前的密集视频描述模型大多使用两阶段的方法存在效率较低、忽略音频及语义信息,描述结果不全面的问题。提出了一种基于Transformer网络多模态和语义信息融合的密集视频描述方法。提取自适应R(2+1)D网络提取视觉特征,设计了语义探测器生成语义信息,加入音频特征进行补充,建立了多尺度可变形注意力模块,应用并行的预测头,加快模型收敛速度,提高模型精度。实验结果表明:模型在2个基准数据集上性能均有很好的表现,评价指标BLEU4上达到了2.17。

语义增强图像-文本预训练模型的零样本三维模型分类

目前,基于对比学习的图像-文本预训练模型(CLIP)在零样本3维模型分类任务上表现出了巨大潜力,然而3维模型和文本之间存在巨大的模态鸿沟,影响了分类准确率的进一步提高。针对以上问题,该文提出一种语义增强CLIP的零样本3维模型分类方法。该方法首先将3维模型表示成多视图;然后为了增强零样本学习对未知类别的识别能力,通过视觉语言生成模型获得每张视图及其类别的语义描述性文本,并将其作为视图和类别提示文本之间的语义桥梁,语义描述性文本采用图像字幕和视觉问答两种方式获取;最后微调语义编码器将语义描述性文本具化为类别的语义描述,其拥有丰富的语义信息和较好的可解释性,有效减小了视图和类别提示文本的语义鸿沟。实验表明,该文方法在ModelNet10和ModelNet40数据集上的分类性能优于现有的零样本分类方法。

国外档案关联数据项目的建设概览与本土启示

论文对国外近十年档案关联数据项目的建设现状进行全面梳理,总结其建设特点及应用场景,为我国档案领域加快应用关联数据、推进档案数字化转型提供启示。本文通过网络调查法、案例研究法和内容分析法,从项目背景、项目环节和项目成果三个维度分析了国外档案关联数据项目特点,总结了关联数据应用场景包括的语义描述、资源整合和知识服务三个方面,提出了国外档案关联数据项目对本土的启示,即加快构建档案关联数据集、树立需求导向的开发理念、促进跨领域的对话与合作。

面向语义出版的图书馆馆藏数字资源描述框架研究

语义出版作为一项新兴技术,对图书馆馆藏数字资源建设产生了重要影响。文章利用面向语义出版的数字资源聚合框架对馆藏数字资源进行描述,从元数据层、本体层、数据关联层和应用层设计了面向语义出版的图书馆馆藏数字资源描述框架模型,并以专利馆藏数字资源为例进行了案例分析,旨在不断提高图书馆的知识服务水平和能力。

基于多通道多步融合的生成式视觉对话模型

当前视觉对话任务在多模态信息融合和推理方面取得了较大进展,但是,在回答一些涉及具有比较明确语义属性和位置空间关系的问题时,主流模型的能力依然有限。比较少的主流模型在正式响应之前能够显式地提供有关图像内容的、语义充分的细粒度表达。视觉特征表示与对话历史、当前问句等文本语义之间缺少必要的、缓解语义鸿沟的桥梁,因此提出一种基于多通道多步融合的视觉对话模型MCMI。该模型显式提供一组关于视觉内容的细粒度语义描述信息,并通过“视觉−语义−对话”历史三者相互作用和多步融合,能够丰富问题的语义表示,实现较为准确的答案解码。在VisDial v0.9/VisDial v1.0数据集中,MCMI模型较基准模型双通道多跳推理模型(DMRM),平均倒数排名(MRR)分别提升了1.95和2.12个百分点,召回率(R@1)分别提升了2.62和3.09个百分点,正确答案平均排名(Mean)分别提升了0.88和0.99;在VisDial v1.0数据集中,较最新模型UTC(Unified Transformer Contrastive learning model),MRR、R@1、Mean分别提升了0.06百分点,0.68百分点和1.47。为了进一步评估生成对话的质量,提出类图灵测试响应通过比例M1和对话质量分数(五分制)M2两个人工评价指标。在VisDial v0.9数据集中,相较于基准模型DMRM,MCMI模型的M1和M2指标分别提高了9.00百分点和0.70。