Improving image tags by exploiting web search results

Automatic image tagging automatically assigns image with semantic keywords called tags, which significantly facilitates image search and organization. Most of present image tagging approaches are constrained by the training model learned from the training dataset, and moreover they have no exploitation on other type of web resource (e.g., web text documents). In this paper, we proposed a search based image tagging algorithm (CTSTag), in which the result tags are derived from web search result. Specifically, it assigns the query image with a more comprehensive tag set derived from both web images and web text documents. First, a content-based image search technology is used to retrieve a set of visually similar images which are ranked by the semantic consistency values. Then, a set of relevant tags are derived from these top ranked images as the initial tag set. Second, a text-based search is used to retrieve other relevant web resources by using the initial tag set as the query. After the denoising process, the initial tag set is expanded with other tags mined from the text-based search result. Then, an probability flow measure method is proposed to estimate the probabilities of the expanded tags. Finally, all the tags are refined using the Random Walk with Restart (RWR) method and the top ones are assigned to the query images. Experiments on NUS-WIDE dataset show not only the performance of the proposed algorithm but also the advantage of image retrieval and organization based on the result tags.     

Tagging image by merging multiple features in a integrated manner

Image tagging is a task that automatically assigns the query image with semantic keywords called tags, which significantly facilitates image search and organization. Since tags and image visual content are represented in different feature space, how to merge the multiple features by their correlation to tag the query image is an important problem. However, most of existing approaches merge the features by using a relatively simple mechanism rather than fully exploiting the correlations between different features. In this paper, we propose a new approach to fusing different features and their correlation simultaneously for image tagging. Specifically, we employ a Feature Correlation Graph to capture the correlations between different features in an integrated manner, which take features as nodes and their correlations as edges. Then, a revised probabilistic model based on Markov Random Field is used to describe the graph for evaluating tag??s relevance to query image. Based on that, we design an image tagging algorithm for large scale web image dataset. We evaluate our approach using two large real-life corpuses collected from Flickr, and the experimental results indicate the superiority of our proposed approach over state-of-the-art techniques.     

灾难恢复系统中基于行为分析的自我防护技术

传统灾难恢复系统存在着对入侵行为反应迟钝、自我保护能力差等问题,文章提出了一种基于行为分析的方法,使灾难恢复系统能自我防护进而解决系统漏洞问题。该方法根据灾难恢复系统收集的数据,把不同类型的安全事件进行关联,确定某种入侵或攻击所采用的手段、攻击数据的特征和涉及到的系统文件、进程等,选用适当的防护策略,并立即通知防火墙、IDS等安全设施与灾难恢复系统进行联动,对出现的漏洞进行自动的防护,防止类似的安全事件再次发生。     

罗家地区井间地震方法与效果

井间地震是将震源与检波器都置入井中进行地震波观测的一种物探新方法,胜利油田与Tomoseis公司合作,在罗家地区进行了成功的井间地震试验,在取得高质量原始资料的基础上,进行了直达波旅行反演处理与反射波成像处理,最终获得较高分辨率的井间速度层析剖面与反射波成像剖面,最高视频率达500Hz,可分辨的最小地震厚度为3－5m,成果剖面经综合解释,对井间储集层的横向分布与连通性,火成岩蚀变带,小断层,砂泥岩薄互层等复杂的地质现象有了清晰明确的认识,井间地震资料不仅可直接服务于油气田的开发,而且也可以标定三维地震资料。     

一种基于线索化二叉排序树的数据流挖掘的决策树分类新算法

数据流具有数据持续到达、到达速度快、数据规模巨大等特点,这些都给数据流挖掘领域研究工作带来了新挑战,而其中分类算法更是当前的研究热点. Domingos等人在VFDT中利用Hoeffding不等式很好地解决了在数据流上进行单遍扫描获取高精度决策树的问题. Gama等人对VFDT进行扩展并实现了VFDTc,使系统能够处理连续属性,并在叶节点采用了贝叶斯分类算法使分类精度更高.基于VFDT和VFDTc,设计并实现了一种基于线索化二叉排序树的决策树分类新算法VFDTt,其主要贡献有如下3点:1)第1次设计并实现了数据流上的基于线索化二叉排序树(TBST)的连续属性处理方法.相比VFDT,VFDTt的样本插入时间复杂度由O(n2)降低到O(nlogn).当新样本到达时,VFDTc需要更新O(logn)个属性节点,而VFDTt只需要更新相应的一个节点即可. 2)改进了VFDTc连续属性的最佳划分节点选取的计算方法,使其时间复杂度由O(nlogn)降低到O(n). 3)相比VFDTc,VFDTt只需从更少的备选划分节点中选取最佳节点,备选划分节点数由O(n)降低到O(logn).     

Q2SM: 基于BERT的多领域任务型对话系统状态跟踪算法

基于管道的方法是目前任务型对话系统的主要构建方式,在工业界具有广泛应用,而对话状态跟踪(dialogue state tracking,DST)是任务型对话系统中的核心任务。面对传统的方法在多领域场景下表现较差的问题,该文结合语言模型预训练的最新研究成果,该文提出了一种基于BERT的对话状态跟踪算法Q2SM(query to state model)。该模型的上游使用了基于BERT的句子表征与相似度交互的槽判定模块,下游使用了一种面向对话状态跟踪任务的自定义RNN: DST-RNN。在WOZ 2.0和MultiWOZ 2.0两个数据集上的实验表明,Q2SM相比于之前的最好模型,分别在联合准确率和状态F₁值两个评价指标上提升了1.09%和2.38%。此外,模型消融实验验证了,DST-RNN相比于传统的RNN或LSTM,不仅可以提升评价指标值,还可以加快模型的收敛速度。     

High hydrogen uptake capacity of mesoporous nitrogen-doped carbons activated using potassium hydroxide

Mesoporous nitrogen-doped carbons activated using potassium hydroxide have large surface areas and high pore volumes, are studied for their hydrogen storage properties. The activated material can store 6.84 wt.% of hydrogen at 77 K under a pressure of 20 bar, which is estimated to correspond to a maximum capacity of 8.24 wt.% based on the Langmuir simulation. The hydrogen adsorption values show linear relationships with the volumes of micropores and small mesopores under those conditions, which indicates that the small mesopores between the sizes 2 and 3 nm also make contributions to the hydrogen adsorption at high pressure.     

TELSEIS STAR采集站特殊故障两例

本文对采集站的两例故障:Load,Fire无反应;通讯监控仪上有载波而无调制信号,作了具体的分析,并给出了正确的检修思路。     

推出试件中剪力钉剪切刚度实测与计算方法

剪力钉的剪切刚度是钢-混凝土结构设计和计算中的一个重要参数,一般通过分析剪力钉模型试验的实测结果得到.剪力钉的剪切刚度是个综合且复杂的量,缺乏统一的取值标准和计算方法.根据剪力钉推出试验的测试结果,综合欧洲规范4条文和学者推荐的计算方法,分析得到了φ22×200剪力钉在界面无摩擦组合结构中纯剪下的剪切刚度值,并对相关影...