Sequential alignment attention model for scene text recognition

Scene text recognition has been a hot research topic in computer vision due to its various applications. The state-of-the-art solutions usually depend on the attention-based encoder-decoder framework that learns the mapping between input images and output sequences in a purely data-driven way. Unfortunately, there often exists severe misalignment between feature areas and text labels in real-world scenarios. To address this problem, this paper proposes a sequential alignment attention model to enhance the alignment between input images and output character sequences. In this model, an attention gated recurrent unit (AGRU) is first devised to distinguish the text and background regions, and further extract the localized features focusing on sequential text regions. Furthermore, CTC guided decoding strategy is integrated into the popular attention-based decoder, which not only helps to boost the convergence of the training but also enhances the well-aligned sequence recognition. Extensive experiments on various benchmarks, including the IIIT5k, SVT, and ICDAR datasets, show that our method substantially outperforms the state-of-the-art methods.     

改进的多层感知机在客户流失预测中的应用

针对在传统的客户流失预测数据预处理中，使用one-hot编码处理离散属性导致数据维度增加及数据过于稀疏的问题，提出了两种基于多层感知机的改进后的客户流失预测模型。其主要思想是分别使用堆叠自编码器和实体嵌入两种方法对多层感知机进行改进，通过将离散属性的高维编码数据向低维空间映射，有效地减少了one-hot编码产生的稀疏数据，增加了离散属性值之间的关联度。在对两份公开的数据集进行交叉验证后的实验结果表明，改进后的模型既有效地提高了预测的准确度，又维持了传统多层感知机模型在并行化计算方面的优势。     

Differences between oculomotor and perceptual artifacts for temporally limited head mounted displays

We used perceptual and oculomotor measures to understand the negative impacts of low (phantom array) and high (motion blur) duty cycles with a high‐speed, AR‐likehead‐mounted display prototype. We observed large intersubject variability for the detection of phantom array artifacts but a highly consistent and systematic effect on saccadic eye movement targeting during low duty cycle presentations. This adverse effect on saccade endpoints was also related to an increased error rate in a perceptual discrimination task, showing a direct effect of display duty cycle on the perceptual quality. For high duty cycles, the probability of detecting motion blur increased during head movements, and this effect was elevated at lower refresh rates. We did not find an impact of the temporal display characteristics on compensatory eye movements during head motion (e.g., VOR). Together, our results allow us to quantify the tradeoff of different negative spatiotemporal impacts of user movements and make subsequent recommendations for optimized temporal HMD parameters.     

加工切割精度对研磨的影响

本文主要介绍了在加工基板边部时,需将控制边部质量放在首。对于边部质量控制的重要环节是切割工序,切割的精度将直接影响到研磨边部的质量,从而影响边部良品率。因此,切割精度是作为控制边部质量的第一要素。     

基于高分一号遥感卫星的渤海湾悬浮泥沙时空分布反演

悬浮泥沙是评价II类水体水质的重要参数之一,近海岸水域悬浮泥沙对重金属、营养盐等具有一定的吸附作用,悬浮泥沙的分布特征在一定程度上反映着污染物的迁移和循环,因此研究悬浮泥沙对渤海湾建设和环境保护具有重要意义。为探究渤海湾水域悬浮泥沙浓度 和分布的变化特征,利用高分一号多光谱卫星影像,通过采用波段组合的方式对悬浮泥沙含量指数反演提取,反演得到2019年9个月的渤海湾悬浮泥沙指数,分析发现渤海湾悬浮泥沙含量在冬季受季风影响较高,春季和夏季的时候渤海湾高浓度悬浮泥沙向近岸收缩,秋季 悬浮泥沙分布格局有正在向冬季过渡的趋势,本文研究可为渤海湾的生态环境保护和工业开发提供重要的科学依据和参考价值。     

ATSP:时态网络可视化的自适应时间片划分方法

现有的时态网络可视化方法大多采用等量时间片来可视化网络的演变，不利于时态模式的快速挖掘和发现。为此，根据时态网络固有的特征提出自适应时间片划分方法（Adaptive Time Slice Partition method，ATSP）。在时态网络的两种表示方式（基于事件的表示方式和基于快照的表示方式）的基础上，构建了ATSP的基础模型，同时提出了一种改进模型用来描述事件间隔时间服从长尾分布的时态网络。为了实现时间片的不等量划分，针对探索任务的不同提出了基于时态模式的ATSP规则和基于中心节点的ATSP规则，并提出了实现算法--层次划分算法（Hierarchical Partition algorithm，HP）和增量划分算法（Incremental Partition algorithm，IP）。实验结果表明，ATSP方法比传统的时间片划分方法更能准确地表示网络的时态特征，且该方法应用于可视化时，能有效归纳并展示网络的特征，明显提高了视觉分析的效率。     

Study of spatial and temporal evolution of Ar and F atoms in SF6/Ar microsecond pulsed discharge by optical emission spectroscopy

The study of sulfur hexafluoride (SF₆) discharge is vital for its application in gas-insulated equipment. Direct current partial discharge (PD) may cause SF₆ decomposition, and the decomposed products of SF₆, such as F atoms, play a dominant role in the breakdown of insulation systems. In this study, the PD caused by metal protrusion defects is simulated by a needle-plate electrode using pulsed high voltage in SF₆/Ar mixtures. The spatial and temporal characteristics of SF6/Ar plasma are analyzed by measuring the emission spectra of F and Ar atoms, which are important for understanding the characteristics of PD. The spatial resolved results show that both F and Ar atom spectral intensities increase first from the plate anode to the needle and then decrease under the conditions of a background pressure of 400 Pa, peak voltage of −1000 V, frequency of 2 kHz, pulse width of 60 μs, and electrode gap of 5–9 mm. However, the distribution characteristics of F and Ar are significantly different. The temporal distribution results show that the spectral intensity of Ar decreases first and then increases slowly, while the spectral intensity of F increases slowly for the duration of the pulsed discharge at the electrode gap of 5 mm and the pulse width of 40–80 μs.     

Extended vertical lists for temporal pattern mining from multivariate time series

In this paper, the problem of mining complex temporal patterns in the context of multivariate time series is considered. A new method called the Fast Temporal Pattern Mining with Extended Vertical Lists is introduced. The method is based on an extension of the level‐wise property, which requires a more complex pattern to start at positions within a record where all of the subpatterns of the pattern start. The approach is built around a novel data structure called the Extended Vertical List that tracks positions of the first state of the pattern inside records and links them to appropriate positions of a specific subpattern of the pattern called the prefix. Extensive computational results indicate that the new method performs significantly faster than the previous version of the algorithm for Temporal Pattern Mining; however, the increase in speed comes at the expense of increased memory usage.     

Evaluation across and within collaborative manufacturing networks: a comparison of manufacturers’ interactions and attributes

Evaluation on collaborative manufacturing network (CMN) structure characteristics has important implications for network operations such as production decision-making, product recovery, creating consensus. Several recent studies suggest that augmenting network structure with nodes’ attributes can provide a more fine-grained understanding of the network. However, there have been few studies to provide a systematic understanding of these effects in a CMN at scale. This gap is bridged using an industrial printing machinery CMN data-set collected on a web-based producing and outsourcing service platform. Novel phenomena with respect to both interaction and attribute metrics across and within the CMNs are observed. Moreover, although many studies employ either interaction or attribute data to study the relative roles of manufacturers in a CMN, relatively little is known about the relationship between these two types of data. This study explores this relationship by comparing two defined metrics (i.e. relational capability and node capability), which evaluate the manufacturers’ interactions and attributes, respectively. We examine to what extent the two metrics of manufacturers correlate with each other, and how possible dissimilarities and similarities can be explained based on the collected industrial CMN data-set. The insights thereby provide a better basis for efficient operations decision-making in CMN.