Coupling-and-decoupling: A hierarchical model for occlusion-free object detection

Handling occlusion is a very challenging problem in object detection. This paper presents a method of learning a hierarchical model for X-to-X occlusion-free object detection (e.g., car-to-car and person-to-person occlusions in our experiments). The proposed method is motivated by an intuitive coupling-and-decoupling strategy. In the learning stage, the pair of occluding X?s (e.g., car pairs or person pairs) is represented directly and jointly by a hierarchical And–Or directed acyclic graph (AOG) which accounts for the statistically significant co-occurrence (i.e., coupling). The structure and the parameters of the AOG are learned using the latent structural SVM (LSSVM) framework. In detection, a dynamic programming (DP) algorithm is utilized to find the best parse trees for all sliding windows with detection scores being greater than the learned threshold. Then, the two single X?s are decoupled from the declared detections of X-to-X occluding pairs together with some non-maximum suppression (NMS) post-processing. In experiments, our method is tested on both a roadside-car dataset collected by ourselves (which will be released with this paper) and two public person datasets, the MPII-2Person dataset and the TUD-Crossing dataset. Our method is compared with state-of-the-art deformable part-based methods, and obtains comparable or better detection performance.     

基于随机游走模型的维基百科语义关系研究

运用随机游走模型提出了一种基于维基百科的语义相关度的计算方法。维基百科中包含了丰富的链接结构,这些链接结构一定程度上能够反应词条之间概念上的相关性,以内容链接和外部链接关系来计算基于维基百科的语义相关度,并在WS-353数据集上进行了实验,取得了较好的准确性。     

基于本体的语义虚拟环境查询与推理模型

当前将本体引入到语义虚拟环境的研究,只是将领域本体的可视化信息用本体表示,并未发挥本体本身具有的优势。为此,提出一种基于本体的语义虚拟环境查询与推理模型。利用OWL语言统一描述虚拟场景图形内容与语义信息,并分别对两者进行查询,在图形内容查询过程中引入本体的推理方法推理出隐含的图形内容信息,然后查询需要的信息。在语义信息查询时引入语义搜索方法,利用基于语义距离计算本体概念相似度的方法计算语义虚拟环境本体中类之间的相似度,搜索与被查询实例语义相似度最大的实例,并借助推理找出其间的关系。对语义虚拟家具商店进行本体的查询与推理,结果证明了该模型的可行性。     

带隐变量的回归模型EM算法

带有隐变量的回归模型具有非常广泛的应用场合,隐回归模型的参数求解问题依赖于自变量的分布假设。基于自变量的beta分布的假设条件,给出了隐回归模型的EM算法,详细地推导了模型中的参数求解过程,给出了使用牛顿法求解beta分布参数的算法,并提出一个合适的初值选择算法。在模拟数据和真实数据的基础上进行了详细的比较性试验,结果表明,对具有不同分布特征的因变量观察值,EM算法能够有效地求解隐回归模型的参数。     

基于语义分类的比较句识别与比较要素抽取研究

比较是人们常用的评估不同事物优劣、异同的表达方式,利用机器识别比较句并进一步抽取比较要素是语言信息处理领域一项新颖又有实用价值的课题。该文依据比较句与比较要素之间是一种“你中有我,我中有你”的共生关系,将比较句识别与比较要素抽取两个任务合二为一完成;根据词意分类,构建由领域词典、情感词典、标记词典、普通词典构成的词典系统;根据汉语比较句句义分类,构建比较句识别与比较要素抽取规则库。以第四届中文倾向性评测(COAE2012)发布的测试语料为实验对象,该系统取得了较好的实验(评测)结果。     

基于规则的汉语名名组合的自动释义研究

该文以现代汉语(特别是网络搜索词)中的名名组合为主要研究对象,探索一种基于规则的汉语名名组合的自动释义方法。其研究步骤为: (1)利用《现代汉语语义词典》中名词的语义类别,来建立名名组合的语义类组合模式;(2)在“生成词库论”中物性角色思想的指导下,用名名组合中某个名词的施成角色或功能角色作为释义动词,来揭示这两个名词之间的语义关系;(3)以语义类组合模式为单位构建名名组合的释义模板,并汇集成名名搭配数据库;(4)利用《知网》资源,来获取具体名词的施成角色和功能角色,建立汉语名词知识库。在这两个数据库的基础上,我们初步实现了一个汉语名名组合的自动释义程序。     

基于加权语义网和有效信息的个性化用户兴趣建模*

为了提高个性化用户兴趣建模的准确率,对用户建模过程进行了优化。在计算文档相似度时,综合考虑特征词的语义关系以及在文档中的分布情况,引入加权语义网,提高了文档相似度计算精度;在计算兴趣度权值时,引入有效信息的概念及量化方法,以解决用户兴趣类权值计算过于主观的问题,并提出具体权值算法,提高了权值计算的准确性。实验结果表明,改进的方法在用户兴趣聚类和兴趣类别权值计算的准确率上都较以往方法有较大提高。     

Exploiting Ontology for Software License Agreements

Software end-users need to sign licenses to seal an agreement with the product providers. Habitually, users agree with the license (i.e. terms and conditions) without fully understanding the agreement. To address this issue, an ontological model is developed to formulate the user requirements and license agreements formally. This paper, introduces ontological model that includes the abstract license ontology of common features found in di?erent license agreements. The abstract license ontology is then extended to a few real world license agreements. The resulting model can be used for di?erent purposes such as querying the appropriate licenses for a speciˉc requirement or checking the license terms and conditions with user requirements.     

OpenCOPI: middleware integration for Ubiquitous Computing

In this paper, we present OpenCOPI (Open COntext Platform Integration), a Service-Oriented Architecture-based middleware platform that supports the integration of services provided by distinct sources, ranging from services offered by simple systems to more complex services provided by context-provision middleware. OpenCOPI offers selection and composition mechanisms to, respectively, select and compose services provided by different sources, considering applications of both Quality of Service and Quality of Context requirements. It also offers an adaptation mechanism that enables to adapt the application execution due to service failures, service quality fluctuation and user mobility. OpenCOPI allows the definition of applications in a higher abstraction level by the specification of a semantic workflow that contains abstract activities. This paper illustrates the use of OpenCOPI in an application from the Gas & Oil Industry and it also shows the evaluation of the main mechanisms of OpenCOPI: the service selection, composition, adaptation and workflow execution.     

一种基于决策树和词义相似度的N1+N2结构语法关系判定方法

设计了一种基于决策树算法的N1+N2结构语法关系判定方法.首先建立了该结构的语料库,对每条语料都标注构建特征集所需的词性、《同义词词林》语义编码、语法关系和词义相似度等信息;然后为证明相似度在判断语法关系中的合理性,根据语言学原理研究了N1+N2结构两个名词间语义相似度与语法关系之间的内在规律:①从语法关系的角度比较两个名词间的语义相似度结果为:并列关系>复指关系>定中关系>主谓关系;②从语言功能焦点的角度比较两个名词间的语义相似度结果为:并焦型短语>后焦型短语.最后以此为基础构建了特征集,运用决策树C4.5算法建立了自动判定N1+N2结构语法关系的方法.运用该算法在自建语料库的测试集中进行测试,正确率为89.39％.