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.     

Learn decision trees with deep visual primitives

In this paper, we strive to propose a self-interpretable framework, termed PrimitiveTree, that incorporates deep visual primitives condensed from deep features with a conventional decision tree, bridging the gap between deep features extracted from deep neural networks (DNNs) and trees’ transparent decision-making processes. Specifically, we utilize a codebook, which embeds the continuous deep features into a finite discrete space (deep visual primitives) to distill the most common semantic information. The decision tree adopts the spatial location information and the mapped primitives to present the decision-making process of the deep features in a tree hierarchy. Moreover, the trained interpretable PrimitiveTree can inversely explain the constituents of the deep features, highlighting the most critical and semantic-rich image patches attributing to the final predictions of the given DNN. Extensive experiments and visualization results validate the effectiveness and interpretability of our method.     

A general framework to study the price‐color relationship in paintings with an application to Mark Rothko rectangular series

We propose a general framework to study the relationship between the price of a painting and its color‐related attributes. To this end we focus on four key aspects: dominant colors, features of the color palette, color harmony, and color emotions. We demonstrate the usefulness of this approach with an example based on Mark Rothko's post‐1950 paintings (the “rectangular” series), and auction data from the 1994 to 2018 period. We identify two distinct price‐color regimes in Rothko's market: (a) [1994‐2005], a period in which prices are explained mainly by the growing popularity of the artist regardless of the color attributes of the paintings sold; and (b) [2006‐2018], a period in which color‐related attributes explain most of the prices. Furthermore, we find that in this second period, the dominant colors and the diversity of the color palette, are by far the most relevant attributes that influence the price; color harmony and color emotions hold almost no explanatory power during this period. Finally, we propose a new metric based on the Herfindahl Index to describe color diversity; this metric seems to be promising at characterizing the effect of the color palette on the price of a painting.     

Training visual attention in a naturalistic visual environment

The efficiency of training visual attention in the central and peripheral visual field was investigated by means of a visual detection task that was performed in a naturalistic visual environment including numerous, time-varying visual distractors. We investigated the minimum number of repetitions of the training required to obtain the top performance and whether intra-day training improved performance as efficiently as inter-day training. Additionally, our research aimed to find out whether exposure to a demanding task such as a microsurgical intervention may cancel out the effects of training.

Results showed that performance in visual attention peaked within three (for tasks in the central visual field) to seven (for tasks in the periphery) days subsequent to training. Intra-day training had no significant effect on performance. When attention training was administered after exposure to stress, improvement of attentional performance was more pronounced than when training was completed before the exposure. Our findings support the implementation of training in situ at work for more efficient results.

Practitioner Summary: Visual attention is important in an increasing number of workplaces, such as with surveillance, inspection, or driving. This study shows that it is possible to train visual attention efficiently within three to seven days. Because our study was executed in a naturalistic environment, training results are more likely to reflect the effects in the real workplace.     

The Photomontage Activity of Postmodernism

For decades now, Douglas Crimp’s landmark 1980 essay ‘The Photographic Activity of Postmodernism’ has shaped our understanding of modernism’s aftermath, at least as it unfolded in North America and Western Europe. Less remembered, however, is the degree to which the procedures of disjunction, copying, appropriation, and outright theft that he highlighted were epitomised not just by contemporary photography, but by photomontage in particular. This article recovers the debates that led critics such as Crimp, Abigail Solomon-Godeau, Christopher Phillips, Benjamin Buchloh and others to turn to photomontage as one of their principal objects of concern in what became known as the postmodern critique of photography. Why was montage tasked to perform this critical function, particularly by people around the journal October who had not otherwise devoted the balance of their writing to photography’s history? The article suggests that these men and women, along with the contemporary artists they foregrounded, manifested what Mary Anne Doane has called a ‘desire for signification’, a reaction in the late 1970s against the mute theatricality of minimalist and conceptual art. Photomontage reintroduced representation to contemporary art and to the canon of art history. But unlike the reemerging illusionism in painting that also manifested this desire, montage guarded against an uncomplicated realism by highlighting and critiquing operations of representation in a manner that painting no longer could.     

基于查询的新闻多文档自动摘要技术研究

针对新闻文本领域,该文提出一种基于查询的自动文本摘要技术,更加有针对性地满足用户信息需求。根据句子的TF-IDF、与查询句的相似度等要素,计算句子权重,并根据句子指示的时间给定不同的时序权重系数,使得最近发生的新闻内容具有更高的权重,最后使用最大边界相关的方法选择摘要句。通过与基于TF-IDF、Text-Rank、LDA等六种方法的对比,该摘要方法ROUGE评测指标上优于其他方法。从结合评测结果及摘要示例可以看出,该文提出的方法可以有效地从新闻文档集中摘取核心信息,满足用户查询内容的信息需求。     

Ontology-based approach for the provision of simulation knowledge acquired by Data and Text Mining processes

Numerical simulation techniques such as Finite Element Analyses are essential in today's engineering design practices. However, comprehensive knowledge is required for the setup of reliable simulations to verify strength and further product properties. Due to limited capacities, design-accompanying simulations are performed too rarely by experienced simulation engineers. Therefore, product models are not sufficiently verified or the simulations lead to wrong design decisions, if they are applied by less experienced users. This results in belated redesigns of already detailed product models and to highly cost- and time-intensive iterations in product development.Thus, in order to support less experienced simulation users in setting up reliable Finite Element Analyses, a novel ontology-based approach is presented. The knowledge management tools developed on the basis of this approach allow an automated acquisition and target-oriented provision of necessary simulation knowledge. This knowledge is acquired from existing simulation models and text-based documentations from previous product developments by Text and Data Mining. By offering support to less experienced simulation users, the presented approach may finally lead to a more efficient and extensive application of reliable FEA in product development.     

图像分类中基于分类矢量量化的视觉词袋模型

特征表示是图像识别和分类的基础，视觉词袋是一种图像的特征表示方法。分析现有视觉词典构建方法的不足，提出一种新的视觉词典构建方法。首先利用梯度方差把特征矢量分为光滑类和边缘类，然后分别针对不同类别的特征矢量进行视觉词典的构建，最后根据两类视觉词典生成视觉词袋。图像分类实验表明，提出的新方法能提高分类准确率。     

基于深度卷积神经网络的视觉里程计研究

视觉里程计利用视频信息来估计相机运动的位姿参数，实现对智能体的定位。传统视觉里程计方法需要特征提取、特征匹配/跟踪、外点剔除、运动估计、优化等流程，解算非常复杂，因此，提出了基于卷积神经网络的方法来实现端对端的单目视觉里程计。借助卷积神经网络对彩色图片自动学习提取图像帧间变化的全局特征，将用于分类的卷积神经网络转化为帧间时序特征网络，通过三层全连接层输出相机的帧间相对位姿参数。在KITTI数据集上的实验结果表明，提出的Deep-CNN-VO模型可以较准确地估计车辆的运动轨迹，证明了方法的可行性。在简化了复杂模型的基础上，与传统的视觉里程计系统相比，该模型的精度也有所提高。