基于贝叶斯通用背景模型的图像标注

在高斯图特征提取过程中,通用背景模型(Universal background model, UBM) 方法常用于根据总体分布估计每一幅图像中特征点分布的高斯混合模型(Gaussian mixture model, GMM)参数. 然而UBM估计的GMM权重参数中有很多接近零的数值,它们所对应的高斯分量对分布估计贡献小却又都参与了计算, 因此UBM的时间复杂度较高. 为解决这个问题,本文提出Bayes UBM方法. 通过引入受限的对称Dirichlet分布来描述GMM权重参数的先验分布,利用Bayes最大后验概率对GMM参数集进行估计. 实验表明Bayes UBM方法不仅有效地降低了时间复杂度,而且提高了Corel数据集上的图像标注精度.     

通过语义控制改进运动合成

运动相似性度量是基于运动图的人体运动合成技术的关键.现有方法主要使用运动捕捉数据姿态数值特征进行相似性度量与合成控制,很难处理语义描述上同类型运动数据集中的不同运动实现版本间的时间与空间特征分布变化的问题.提出了引入用户语义控制来改进基于运动图的人体运动合成方法.使用关系特征作为高层语义描述,刻画同类型运动的空间变化特征;通过自学习过程,获得运动类模板,作为同类型运动的空-时特征语义描述;通过将运动类模板数据与人体运动序列文件进行匹配,实现运动类型识别和自动语义信息标注;借助关系特征语义描述及运动序列文件的语义标注信息,实现在基于运动图的运动合成中引入用户直观的高层语义控制.运动合成实验结果显示了该方法的有效性,为获得高质量人体运动合成数据提供途径.     

基于情感感知的面料图像数据库系统的设计与实现

在面料图像数据库系统中,为了让计算机对面料图像的情感语义进行自动感知,帮助用户用情感语义浏览或挑选所需的面料,并对其描述进行数值标注,文章针对面料图像本身表述的情感语义进行研究,进而实现基于情感语义的图像检索。在利用支持向量机等技术通过VC++编程实现面料图像情感语义识别的基础上,通过动态链接库技术将情感识别功能应用到采用NET编程开发的面料图像数据库系统中,在面料数据库系统中实现了计算机对面料图像情感语义的自动感知和识别,并进行情感语义的标注,从而实现了基于情感语义的面料图像检索。经过测试,该系统达到了较好的识别和分类效果。     

图像检索中语义映射方法综述

"语义鸿沟"已成为基于内容图像检索的瓶颈,解决这个问题需要建立从图像的低层特征到高层语义的映射.对当前语义映射研究进行了综述,首先给出一个结合语义的图像检索框架,并分析了图像内容的层次模型及图像语义的表示方法;然后根据算法的特点,将现有的语义映射方法和技术分为4大类,重点阐述了各类方法提出的思路、模型.并讨论各自的优势和局限性;最后以图像检索实际应用的需要为依据,提出在图像语义检索相关领域的重要课题和研究方向.     

基于运动分析的视频检索方法

提出了一种新的压缩视频中对主要运动进行定性分析算法,该算法主要应用于视频信息检索。依据运动矢量的方向分布特性和运动矢量之间的相对关系来判断主要运动类型,可以直接用于有运动矢量信息的压缩视频流检索上。     

基于图正则化与非负组稀疏的自动图像标注

设计一个稳健的自动图像标注系统的重要环节是提取能够有效描述图像语义的视觉特征。由于颜色、纹理和形状等异构视觉特征在表示特定图像语义时所起作用的重要程度不同且同一类特征之间具有一定的相关性,该文提出了一种图正则化约束下的非负组稀疏(Graph Regularized Non-negative Group Sparsity, GRNGS)模型来实现图像标注,并通过一种非负矩阵分解方法来计算其模型参数。该模型结合了图正则化与l2,1-范数约束,使得标注过程中所选的组群特征能体现一定的视觉相似性和语义相关性。在Corel5K和ESP Game等图像数据集上的实验结果表明：相较于一些最新的图像标注模型,GRNGS模型的鲁棒性更强,标注结果更精确。     

互联网跨媒体分析与检索:理论与算法

互联网信息不仅规模巨大,而且存在着十分广泛、错综复杂的交叉关联,呈现跨媒体特性.实现互联网中跨媒体数据的精确挖掘与检索是高效利用互联网资源迫切需要解决问题.文中对该领域所涉及的人脑认知跨媒体特性、多媒体检索标注与语义理解、跨媒体表达与识别、互联网跨媒体搜索以及海量数据处理机制等几个方面进行了综述,讨论了该领域目前存在问题和今后的发展趋势.     

An ontology-based approach for formalisation and semantic organisation of conformance requirements in construction

This paper presents an ontology-based method for the formalisation and application of construction conformance requirements for effective code checking. This research continues our work on the development of a generic model automating the conformance checking of construction projects against building codes. We start from the analysis of the related research on the formalisation and organisation of building codes that allows us to formulate our approach for semantic annotation and scheduling of conformance requirements for conformance checking task. Our approach comprises 5 main steps: formalisation, semantic annotation, classification, context-based scheduling and semantic search of conformance requirements. They are implemented as corresponding key components of the C3R (Conformance Checking in Construction — Reasoning) prototype that we have developed to model the conformance checking process in construction. Finally, we discuss the ongoing work and perspectives of our research: the validation of our model by construction practices and the enrichment of our approach by usage-based knowledge.     

Semantic content-based image retrieval: A comprehensive study

The complexity of multimedia contents is significantly increasing in the current digital world. This yields an exigent demand for developing highly effective retrieval systems to satisfy human needs. Recently, extensive research efforts have been presented and conducted in the field of content-based image retrieval (CBIR). The majority of these efforts have been concentrated on reducing the semantic gap that exists between low-level image features represented by digital machines and the profusion of high-level human perception used to perceive images. Based on the growing research in the recent years, this paper provides a comprehensive review on the state-of-the-art in the field of CBIR. Additionally, this study presents a detailed overview of the CBIR framework and improvements achieved; including image preprocessing, feature extraction and indexing, system learning, benchmarking datasets, similarity matching, relevance feedback, performance evaluation, and visualization. Finally, promising research trends, challenges, and our insights are provided to inspire further research efforts.     

A Novel Auto-Annotation Technique for Aspect Level Sentiment Analysis

In machine learning, sentiment analysis is a technique to find and analyze the sentiments hidden in the text. For sentiment analysis, annotated data is a basic requirement. Generally, this data is manually annotated. Manual annotation is time consuming, costly and laborious process. To overcome these resource constraints this research has proposed a fully automated annotation technique for aspect level sentiment analysis. Dataset is created from the reviews of ten most popular songs on YouTube. Reviews of five aspects—voice, video, music, lyrics and song, are extracted. An N-Gram based technique is proposed. Complete dataset consists of 369436 reviews that took 173.53 s to annotate using the proposed technique while this dataset might have taken approximately 2.07 million seconds (575 h) if it was annotated manually. For the validation of the proposed technique, a sub-dataset—Voice, is annotated manually as well as with the proposed technique. Cohen's Kappa statistics is used to evaluate the degree of agreement between the two annotations. The high Kappa value (i.e., 0.9571%) shows the high level of agreement between the two. This validates that the quality of annotation of the proposed technique is as good as manual annotation even with far less computational cost. This research also contributes in consolidating the guidelines for the manual annotation process.