No-Reference Video Quality Assessment using novel hybrid features and two-stage hybrid regression for score level fusion

This paper presents a novel No-Reference Video Quality Assessment (NR-VQA) model that utilizes proposed 3D steerable wavelet transform-based Natural Video Statistics (NVS) features as well as human perceptual features. Additionally, we proposed a novel two-stage regression scheme that significantly improves the overall performance of quality estimation. In the first stage, transform-based NVS and human perceptual features are separately passed through the proposed hybrid regression scheme: Support Vector Regression (SVR) followed by Polynomial curve fitting. The two visual quality scores predicted from the first stage are then used as features for the similar second stage. This predicts the final quality scores of distorted videos by achieving score level fusion. Extensive experiments were conducted using five authentic and four synthetic distortion databases. Experimental results demonstrate that the proposed method outperforms other published state-of-the-art benchmark methods on synthetic distortion databases and is among the top performers on authentic distortion databases. The source code is available at https://github.com/anishVNIT/two-stage-vqa.     

SOINN-Based Abnormal Trajectory Detection for Efficient Video Condensation

With the evolution of video surveillance systems, the requirement of video storage grows rapidly; in addition, safe guards and forensic officers spend a great deal of time observing surveillance videos to find abnormal events. As most of the scene in the surveillance video are redundant and contains no information needs attention, we propose a video condensation method to summarize the abnormal events in the video by rearranging the moving trajectory and sort them by the degree of anomaly. Our goal is to improve the condensation rate to reduce more storage size, and increase the accuracy in abnormal detection. As the trajectory feature is the key to both goals, in this paper, a new method for feature extraction of moving object trajectory is proposed, and we use the SOINN (Self-Organizing Incremental Neural Network) method to accomplish a high accuracy abnormal detection. In the results, our method is able to shirk the video size to 10% storage size of the original video, and achieves 95% accuracy of abnormal event detection, which shows our method is useful and applicable to the surveillance industry.     

视频侦查中人像智能分析应用及算法优化

人像智能分析指的是对视频或录像中的人像进行结构化和可视化分析,对目标人物进行性别、年龄、发型等特征的智能识别,这项技术在视频侦查中有极高的应用价值。人像识别早期的算法是通过人工提取特征,通过学习低级视觉特征来针对不同属性进行分类学习,这种基于传统方法的模型表现常常不尽如人意。在计算机视觉领域,通过海量图像数据学习的神经网络比传统方法有更丰富的信息量和特征可以被提取。文章尝试通过深度学习技术训练神经网络模型对行人进行检测和识别,对于衣着不同的行人进行智能识别,具有更好的鲁棒性,提升了视频人像识别的准确率,拓展了人工智能技术在身份识别领域的应用。     

Economic Indicators

Currency exchanges rates – updated monthly. Economic indicators of industrial production. Countries included: France, Germany, Italy, the United Kingdom, the United States, Canada, Japan (Total G-7), Eurozone and Total EU-28 (Total OECD). Updated monthly. Economic indicators of car registration in the United States, Canada, France, Germany, Italy, Poland, Spain, Turkey, the United Kingdom, Japan, Republic of Korea and Other OECD (Total OECD-30). Updated monthly. Monthly averages of crude steel production in thousand metric tons for the United States, Canada, Brazil, Mexico, Austria, Belgium, Czech Republic, France, Germany, Italy, Netherlands, Poland, Spain, Sweden, Turkey, the United Kingdom, Russia, Ukraine, South Africa, Iran, China, India, Japan, Republic of Korea, Taiwan and Australia.     

伪标签置信选择的半监督集成学习视频语义检测

在视频语义检测中，有标记样本不足会严重影响检测的性能，而且伪标签样本中的噪声也会导致集成学习基分类器性能提升不足。为此，提出一种伪标签置信选择的半监督集成学习算法。首先，在三个不同的特征空间上训练出三个基分类器，得到基分类器的标签矢量；然后，引入加权融合样本所属某个类别的最大概率与次大概率的误差和样本所属某个类别的最大概率与样本所属其他各类别的平均概率的误差，作为基分类器的标签置信度，并融合标签矢量和标签置信度得到样本的伪标签和集成置信度；接着，选择集成置信度高的样本加入到有标签的样本集，迭代训练基分类器；最后，采用训练好的基分类器集成协作检测视频语义概念。该算法在实验数据集UCF11上的平均准确率到达了83.48%，与Co-KNN-SVM算法相比，平均准确率提高了3.48个百分点。该算法选择的伪标签能体现样本所属类别与其他类别的总体差异性，又能体现所属类别的唯一性，可减少利用伪标签样本的风险，有效提高视频语义概念检测的准确率。     

Gamers,Surfers, Social Media Users: Unpacking the role of interest in English

Across stages of acquisition, second language (L2) competencies are contingent on the variation among individuals learning the language, in both informal and formal learning contexts. This study investigates a group of outliers whose extreme test scores serve as a foundation to examine them as individuals. The study addresses the outliers' characteristics as good L2 readers but poor first language (L1) readers. Combining quantitative (test results, survey, and language logs) and qualitative (focus groups and interviews) data among 21 adolescents in Norway (aged 16–17 years), the study identifies dimensions of individual language use in L1 Norwegian and L2 English. Findings revealed that they explained their English proficiency by the role of interest and their extensive use of English technology and tools outside school. In‐depth analysis identified three profiles: the Gamer, who spends up to 8 hr daily playing online games while using English mainly; the Surfer, who spends hours on the Internet, searching for authentic language situations, commonly involving English; and the Social Media User, who produces and consumes information in English through social media. Additionally, the Gamers read printed novels voluntarily outside the classroom. This study offers unique perspectives and new directions for future L2 research.     

基于深度学习的视频跟踪研究进展综述

近年来深度学习迅猛发展，颠覆了语音识别、图像分类、文本理解等领域的算法设计思路。深度学习因其具备强大的特征提取能力，在图像识别领域的成绩尤为突出。然而深度学习与视频监控领域的结合并不多，由于深度模型具有多层网络结构，算法复杂度大，训练和更新模型时比较耗时，很难满足实时性要求。回顾了深度学习的发展史，介绍了最近10年来国内外深度学习主要模型，论述了基于深度学习的目标跟踪算法，指出了各算法的优缺点，最后对当前该领域存在的问题和发展前景进行了总结和展望。     

基于Marr小波改进的SIFT算法的遥感影像配准

〖HTH〗通讯作者〖HTSS〗:[ZK（]金〓燕(1991-)，女，山东济宁人，硕士研究生，主要从事图形图像处理，图像与视觉信息计算方面的研究。E\|mail:jyan0529@163.com。[ZK）] 〖ZW)〗〖HT〗 〖AM〗〖HT5SS〗〖MM(〗〖ZZ(S〗〖HT5”〗〖SX(B〗第34卷〓第3期〖〗2019年6月〖SX)〗[KG0.2mm]〖KG7*3〗〖HT〗〖SX(B〗遥〓感〓技〓术〓与〓应〓用〖〗〖WT5，6〗REMOTE SENSING TECHNOLOGY AND APPLICATION〖SX)〗〓〓〓〓〖KG6*2〗〖WT5”BX〗〖SX(B〗Vol.34〓No.3〖〗Jun.2019〖WT〗〖SX)〗〖ZZ)〗〖MM)〗〖HT〗 〖HT2H〗〖JZ(〗〖WTHZ〗〖STHZ〗 基于Marr小波改进的SIFT算法的遥感影像配准 〖STBZ〗〖WTBZ〗〖HT4K〗 张海涛，金〓燕，刘万军 〖HT5K〗 (辽宁工程技术大学 软件学院，辽宁 葫芦岛〓125105) 〖JZ)〗〖ＨＴ５Ｈ〗〖GK2!2〗摘要〖HTK〗: [KG(0.1mm]针对遥感图像配准方法中错误匹配点对过多、配准效率低和其他性能，提出了一种基于小波的遥感图像配准方法。首先，利用尺度空间理论下的Marr小波对参考图像和待配准图像进行特征提取，然后利用欧氏距离对参考图像和待配准图像的特征点进行初配准，再根据随机采样一致法，对初配准结果进行精配准。为了验证方法的有效性，选择无人机实时航拍图像、不同时相变化遥感图像以及遥感不同高度的遥感图像。实验结果表明：该方法与SIFT(Scale Invariant Feature Transform)算法以及其他改进SIFT算法相比可以有效剔除错误匹配点对，提高了配准精度，同时提高配准效率两倍以上。该方法可以应用于不同遥感数据源，能够有效地提高配准精度，降低配准时间。[KG)] 〖ＨＴＨ〗关〓键〓词〖ＨＴ５Ｋ〗: 遥感图像配准;Marr小波;欧氏距离;随机采样一致法 〖ＨＴＨ〗中图分类号〖HTSS〗:TP79〓〓〖HTH〗文献标志码〖HTSS〗:A〓〓〖HTH〗文章编号〖HTSS〗:1004 0323(2019)03 0622 08 〖HK〗〖HT5SS〗     

Can video games change attitudes towards history? Results from a laboratory experiment measuring short- and long-term effects

This study investigates a video game's effects on implicit and explicit attitudes towards depicted historical events in the short- and long-term on a sample of 148 young adults. We used, as an intervention tool, a serious game Czechoslovakia 38–89: Borderlands that deals with the expulsion of the Sudeten Germans from the former Czechoslovakia after the WWII. Results showed more negative pretest-posttest explicit attitude changes towards the expulsion on a general level (d = −0.34) and a specific level (d = −0.53) compared to the control group. Over the long-term, group differences in attitude change remained significant for the specific level (d = −0.44), but not for general one (d = −0.16). Exploratory analysis on the item level indicated that especially attitudes towards the expulsion's (un)fairness were affected by the game. However, no significant changes were found in implicit attitudes in the experimental group. This study is the first of such scale to empirically investigate video games' effects on a society's historical awareness.     

Controllable Image‐Based Transfer of Flow Phenomena

Modelling flow phenomena and their related weathering effects is often cumbersome due their dependence on the environment, materials and geometric properties of objects in the scene. Example‐based modelling provides many advantages for reproducing real textures, but little effort has been devoted to reproducing and transferring complex phenomena. In order to produce realistic flow effects, it is possible to take advantage of the widespread availability of flow images on the Internet, which can be used to gather key information about the flow. In this paper, we present a technique that allows the transfer of flow phenomena between photographs, adapting the flow to the target image and giving the user flexibility and control through specifically tailored parameters. This is done through two types of control curves: a fitted theoretical curve to control the mass of deposited material, and an extended colour map for properly adapting to the target appearance. In addition, our method filters and warps the input flow in order to account for the geometric details of the target surface. This leads to a fast and intuitive approach to easily transfer phenomena between images, providing a set of simple and intuitive parameters to control the process.