Image categorization using a semantic hierarchy model with sparse set of salient regions

Image categorization in massive image database is an important problem. This paper proposes an approach for image categorization, using sparse set of salient semantic information and hierarchy semantic label tree （HSLT） model. First, to provide more critical image semantics, the proposed sparse set of salient regions only at the focuses of visual attention instead of the entire scene was formed by our proposed saliency detection model with incorporating low and high level feature and Shotton＇s semantic texton forests （STFs） method. Second, we also propose a new HSLT model in terms of the sparse regional semantic information to automatically build a semantic image hierarchy, which explicitly encodes a general to specific image relationship. And last, we archived image dataset using image hierarchical semantic, which is help to improve the performance of image organizing and browsing. Extension experimefital results showed that the use of semantic hierarchies as a hierarchical organizing frame- work provides a better image annotation and organization, improves the accuracy and reduces human＇s effort.     

Evaluation of Localized Semantics: Data, Methodology, and Experiments

We present a new data set of 1014 images with manual segmentations and semantic labels for each segment, together with a methodology for using this kind of data for recognition evaluation. The images and segmentations are from the UCB segmentation benchmark database (Martin et al., in International conference on computer vision, vol. II, pp. 416–421, 2001). The database is extended by manually labeling each segment with its most specific semantic concept in WordNet (Miller et al., in Int. J. Lexicogr. 3(4):235–244, 1990). The evaluation methodology establishes protocols for mapping algorithm specific localization (e.g., segmentations) to our data, handling synonyms, scoring matches at different levels of specificity, dealing with vocabularies with sense ambiguity (the usual case), and handling ground truth regions with multiple labels. Given these protocols, we develop two evaluation approaches. The first measures the range of semantics that an algorithm can recognize, and the second measures the frequency that an algorithm recognizes semantics correctly. The data, the image labeling tool, and programs implementing our evaluation strategy are all available on-line (kobus.ca//research/data/IJCV_2007). We apply this infrastructure to evaluate four algorithms which learn to label image regions from weakly labeled data. The algorithms tested include two variants of multiple instance learning (MIL), and two generative multi-modal mixture models. These experiments are on a significantly larger scale than previously reported, especially in the case of MIL methods. More specifically, we used training data sets up to 37,000 images and training vocabularies of up to 650 words. We found that one of the mixture models performed best on image annotation and the frequency correct measure, and that variants of MIL gave the best semantic range performance. We were able to substantively improve the performance of MIL methods on the other tasks (image annotation and frequency correct region labeling) by providing an appropriate prior.     

图学习的区域图像标注方法

近年来,图像标注技术得到广泛关注.提出一种图学习的自动图像标注方法,将图像标注作为多示例学习框架下的半监督学习策略,通过给出适合图像在包空间的有效度量方式,充分利用未标注样本挖掘图像特征的内在规律性,将半监督学习的方法和多示例学习有效结合起来,从而获得更准确的标注结果.实验结果表明,提出的标注方法可行,同时标注结果与传统的标注方法相比得到了明显提高.     

基于Wikipedia的语义元数据生成

语义元数据提供数据的语义信息,在数据的理解、管理、发现和交换中起着极为重要的作用。随着互联网上数据爆炸式的增长,对自动元数据生成技术的需求也就变得更加迫切。获得目标语义元数据及得到足够的训练语料是使用自动生成技术的两个基本问题。由于获得目标语义元数据需要专家知识,而获得足够的训练语料需要大量的手工工作,这也就使得这两个问题在构建一个成功的系统时至关重要。该文基于Wikipedia来解决这两个问题通过分析一个类别中条目的目录表(table-of-contents)来抽取目标语义元数据,通过对分析文档结构和赋予目标结构正确的语义元数据来构建训练语料库。实验结果表明,该文的方法能够有效地解决这两个问题,为进一步的大规模的语义元数据应用系统打下了坚实的基础。     

基于贝叶斯理论的图像标注和检索

图像自动语义标注是基于内容图像检索中很重要且很有挑战性的工作.提出用语义约束的聚类方法对分割后的图像区域进行聚类,在图像标注阶段,使用贪心选择连接(GSJ)算法找出聚类区域的独立子集,然后使用贝叶斯理论进行语义标注.对图像进行标注以后,使用标注的关键字进行检索.在一个包含500幅图像的图像库进行实验,结果表明,提出的方法具有较好的检索性能.     

From tabular data to knowledge graphs: A survey of semantic table interpretation tasks and methods

Tabular data often refers to data that is organized in a table with rows and columns. We observe that this data format is widely used on the Web and within enterprise data repositories. Tables potentially contain rich semantic information that still needs to be interpreted. The process of extracting meaningful information out of tabular data with respect to a semantic artefact, such as an ontology or a knowledge graph, is often referred to as Semantic Table Interpretation (STI) or Semantic Table Annotation. In this survey paper, we aim to provide a comprehensive and up-to-date state-of-the-art review of the different tasks and methods that have been proposed so far to perform STI. First, we propose a new categorization that reflects the heterogeneity of table types that one can encounter, revealing different challenges that need to be addressed. Next, we define five major sub-tasks that STI deals with even if the literature has mostly focused on three sub-tasks so far. We review and group the many approaches that have been proposed into three macro families and we discuss their performance and limitations with respect to the various datasets and benchmarks proposed by the community. Finally, we detail what are the remaining scientific barriers to be able to truly automatically interpret any type of tables that can be found in the wild Web.     

Semi-automatic dynamic auxiliary-tag-aided image annotation

Image annotation is the foundation for many real-world applications. In the age of Web 2.0, image search and browsing are largely based on the tags of images. In this paper, we formulate image annotation as a multi-label learning problem, and develop a semi-automatic image annotation system. The presented system chooses proper words from a vocabulary as tags for a given image, and refines the tags with the help of the user's feedback. The refinement amounts to a novel multi-label learning framework, named Semi-Automatic Dynamic Auxiliary-Tag-Aided (SADATA), in which the classification result for one certain tag (target tag) can be boosted by the classification results of a subset of the other tags (auxiliary tags). The auxiliary tags, which have strong correlations with the target tag, are determined in terms of the normalized mutual information. We only select those tags whose correlations exceed a threshold as the auxiliary tags, so the auxiliary set is sparse. How much an auxiliary tag can contribute is dependent on the image, so we also build a probabilistic model conditioned on the auxiliary tag and the input image to adjust the weight of the auxiliary tag dynamically. For an given image, the user feedback on the tags corrects the outputs of the auxiliary classifiers and SADATA will recommend more proper tags next round. SADATA is evaluated on a large collection of Corel images. The experimental results validate the effectiveness of our dynamic auxiliary-tag-aided method. Furthermore, the performance also benefits from user feedbacks such that the annotation procedure can be significantly speeded up.     

基于CIDOC概念参考模型的Web服务注释

在Web服务所提供的基本功能的基础上,应用语义注释的思想,给出一种对Web服务进行语义说明的方法。应用CIDOC CRM标准对Web数据规范进行注释,可为该规范加入语义信息,反映数据的含义,并揭示出数据之间的层次关系,从而使Web服务使用者更好地理解数据,并将所获取的数据准确地应用到数据处理中。