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 net...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.展开更多
A global semantics matching and QoS-awareness service selection are proposed when aimed at a web services composition process.Both QoS-aware matching and global semantic matching are considered during the global match...A global semantics matching and QoS-awareness service selection are proposed when aimed at a web services composition process.Both QoS-aware matching and global semantic matching are considered during the global matching.When there are demands for global semantic matching and QoS of service composition,a concrete service set which meets the demands is selected for the whole service composition process and an optimal solution is also achieved.A QoS model is built and the corresponding evaluation method is given for the matching of the service composition process.Based on them,a genetic algorithm is proposed to achieve the maximal global semantic matching degree and fulfill the QoS requirements for the whole service composition process.Experimental results and analysis show that the algorithm is feasible and effective for semantics and QoS-aware service matching.展开更多
随着BIM技术在建筑领域的深度应用,越来越多的建筑设计开始以BIM模型方式进行交付,基于BIM的建筑工程设计自动合规性审查因其客观性、高效性受到理论和实践领域越来越多的关注。文章以基于BIM的自动合规性审查为主题进行综述,在Web of S...随着BIM技术在建筑领域的深度应用,越来越多的建筑设计开始以BIM模型方式进行交付,基于BIM的建筑工程设计自动合规性审查因其客观性、高效性受到理论和实践领域越来越多的关注。文章以基于BIM的自动合规性审查为主题进行综述,在Web of Science核心数据库对建筑领域自动合规性审查相关的研究文献进行全面检索及分析,从基本框架、规范条文信息抽取、BIM模型信息抽取及语义丰富、规范-模型信息匹配、合规性推理等方面对现有基于BIM的自动合规性审查研究进行系统解构,并对未来的研究方向进行讨论。最后,文章指出基于BIM的自动合规性审查在复杂文本信息抽取的性能与深度、模型语义丰富、信息匹配的自动化程度与通用性,以及计算机代码的透明度与灵活性等方面仍面临巨大挑战。展开更多
在信息检索领域,量子干涉理论已应用于文档相关性、次序效应等核心问题的研究中,旨在建模用户认知引起的类量子干涉现象.文中从语言理解的需求出发,利用量子理论的数学工具分析语义组合过程中存在的语义演化现象,提出融合量子干涉信息...在信息检索领域,量子干涉理论已应用于文档相关性、次序效应等核心问题的研究中,旨在建模用户认知引起的类量子干涉现象.文中从语言理解的需求出发,利用量子理论的数学工具分析语义组合过程中存在的语义演化现象,提出融合量子干涉信息的双重特征文本表示模型(Quantum Interference Based Duet-Feature Text Representation Model,QDTM).模型以约化密度矩阵为语言表示的核心组件,有效建模维度级别的语义干涉信息.在此基础上,构建捕获全局特征信息与局部特征信息的模型结构,满足语言理解过程中不同粒度的语义特征需求.在文本分类数据集和问答数据集上的实验表明,QDTM的性能优于量子启发的语言模型和神经网络文本匹配模型.展开更多
针对小样本语义分割中同类别支持图像与查询图像存在外观差异较大的问题,提出融合高斯过程的自支持匹配小样本语义分割模型。提出的模型在自支持匹配小样本语义分割模型的基础上,首先融入高斯过程,对分布在深层特征空间上的复杂外观进...针对小样本语义分割中同类别支持图像与查询图像存在外观差异较大的问题,提出融合高斯过程的自支持匹配小样本语义分割模型。提出的模型在自支持匹配小样本语义分割模型的基础上,首先融入高斯过程,对分布在深层特征空间上的复杂外观进行建模,捕获更多空间细节信息来表示数据分布;随后设计特征增强模块,在空间层对支持特征与查询特征进行信息交互,在通道层进行注意力加权,进一步增强相同类之间的全局相似性,捕获更多目标类别信息;最后利用Gram矩阵量化支持图像和查询图像之间外观差异的大小,从而融合原型匹配的结果,产生更准确的分割图像。实验结果表明:与现有方法相比,所提模型在更强的主干网络下具有较好的分割结果和更少的参数量,在5-shot的设定下,所提模型在PASCAL−5i数据集上平均交并比(mean Intersection over Union,mIoU)达到最优值,提升了0.4%;在COCO−20i数据集上的子集mIoU取得最优值,分别提升了2.2%和1.0%,表明该模型的有效性和先进性。展开更多
社交媒体的普及和信息传播的便捷化使得虚假新闻的传播和影响力不断增加,给社会带来了严重的负面影响。为了应对虚假新闻的干扰,提出了一种基于伪孪生网络的虚假新闻检测方法(Fake news detection method based on Pseudo-Siamese netwo...社交媒体的普及和信息传播的便捷化使得虚假新闻的传播和影响力不断增加,给社会带来了严重的负面影响。为了应对虚假新闻的干扰,提出了一种基于伪孪生网络的虚假新闻检测方法(Fake news detection method based on Pseudo-Siamese network,FNPS)。受计算机视觉领域任务的启发,将虚假新闻的检测视为多模态语义匹配问题,采用双向长短时记忆(Bi-directional long short-term memory,BiLSTM)网络和50层残差网络(50-layer residual nets,ResNet50)分别提取新闻数据的文本特征和图像特征,并将它们从原始空间映射至新的目标空间来衡量文本与图像的语义匹配程度。通过测试微博数据集,FNPS模型可以有效检测跨领域虚假新闻,并优于其他的多模态虚假新闻检测模型。展开更多
文摘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.
基金Specialized Research Fund for the Doctoral Program of Higher Education(No.20050288015)Innovation Funds of Nanjing University of Science and Technology
文摘A global semantics matching and QoS-awareness service selection are proposed when aimed at a web services composition process.Both QoS-aware matching and global semantic matching are considered during the global matching.When there are demands for global semantic matching and QoS of service composition,a concrete service set which meets the demands is selected for the whole service composition process and an optimal solution is also achieved.A QoS model is built and the corresponding evaluation method is given for the matching of the service composition process.Based on them,a genetic algorithm is proposed to achieve the maximal global semantic matching degree and fulfill the QoS requirements for the whole service composition process.Experimental results and analysis show that the algorithm is feasible and effective for semantics and QoS-aware service matching.
文摘随着BIM技术在建筑领域的深度应用,越来越多的建筑设计开始以BIM模型方式进行交付,基于BIM的建筑工程设计自动合规性审查因其客观性、高效性受到理论和实践领域越来越多的关注。文章以基于BIM的自动合规性审查为主题进行综述,在Web of Science核心数据库对建筑领域自动合规性审查相关的研究文献进行全面检索及分析,从基本框架、规范条文信息抽取、BIM模型信息抽取及语义丰富、规范-模型信息匹配、合规性推理等方面对现有基于BIM的自动合规性审查研究进行系统解构,并对未来的研究方向进行讨论。最后,文章指出基于BIM的自动合规性审查在复杂文本信息抽取的性能与深度、模型语义丰富、信息匹配的自动化程度与通用性,以及计算机代码的透明度与灵活性等方面仍面临巨大挑战。
文摘在信息检索领域,量子干涉理论已应用于文档相关性、次序效应等核心问题的研究中,旨在建模用户认知引起的类量子干涉现象.文中从语言理解的需求出发,利用量子理论的数学工具分析语义组合过程中存在的语义演化现象,提出融合量子干涉信息的双重特征文本表示模型(Quantum Interference Based Duet-Feature Text Representation Model,QDTM).模型以约化密度矩阵为语言表示的核心组件,有效建模维度级别的语义干涉信息.在此基础上,构建捕获全局特征信息与局部特征信息的模型结构,满足语言理解过程中不同粒度的语义特征需求.在文本分类数据集和问答数据集上的实验表明,QDTM的性能优于量子启发的语言模型和神经网络文本匹配模型.
文摘针对小样本语义分割中同类别支持图像与查询图像存在外观差异较大的问题,提出融合高斯过程的自支持匹配小样本语义分割模型。提出的模型在自支持匹配小样本语义分割模型的基础上,首先融入高斯过程,对分布在深层特征空间上的复杂外观进行建模,捕获更多空间细节信息来表示数据分布;随后设计特征增强模块,在空间层对支持特征与查询特征进行信息交互,在通道层进行注意力加权,进一步增强相同类之间的全局相似性,捕获更多目标类别信息;最后利用Gram矩阵量化支持图像和查询图像之间外观差异的大小,从而融合原型匹配的结果,产生更准确的分割图像。实验结果表明:与现有方法相比,所提模型在更强的主干网络下具有较好的分割结果和更少的参数量,在5-shot的设定下,所提模型在PASCAL−5i数据集上平均交并比(mean Intersection over Union,mIoU)达到最优值,提升了0.4%;在COCO−20i数据集上的子集mIoU取得最优值,分别提升了2.2%和1.0%,表明该模型的有效性和先进性。
文摘社交媒体的普及和信息传播的便捷化使得虚假新闻的传播和影响力不断增加,给社会带来了严重的负面影响。为了应对虚假新闻的干扰,提出了一种基于伪孪生网络的虚假新闻检测方法(Fake news detection method based on Pseudo-Siamese network,FNPS)。受计算机视觉领域任务的启发,将虚假新闻的检测视为多模态语义匹配问题,采用双向长短时记忆(Bi-directional long short-term memory,BiLSTM)网络和50层残差网络(50-layer residual nets,ResNet50)分别提取新闻数据的文本特征和图像特征,并将它们从原始空间映射至新的目标空间来衡量文本与图像的语义匹配程度。通过测试微博数据集,FNPS模型可以有效检测跨领域虚假新闻,并优于其他的多模态虚假新闻检测模型。