Adaptive reversible data hiding for JPEG images with multiple two-dimensional histograms

Joint photographic experts group (JPEG) can provide good quality with small file size but also eliminate extensively the redundancies of images. Therefore, hiding data into JPEG images in terms of maintaining high visual quality at small file sizes has been a great challenge for researchers. In this paper, an adaptive reversible data hiding method for JPEG images containing multiple two-dimensional (2D) histograms is proposed. Adaptability is mainly reflected in three aspects. The first one is to preferentially select sharper histograms for data embedding after $K$ histograms are established by constructing the $k$th ($k\in \{1,2,\dots ,K\}$) histogram using the $k$th non-zero alternating current (AC) coefficient of all the quantized discrete cosine transform blocks. On the other hand, to fully exploit the strong correlation between coefficients of one histogram, the smoothness of each coefficient is estimated by a block smoothness estimator so that a sharply-distributed 2D-histogram is constructed by combining two coefficients with similar smoothness into a pair. The pair corresponding to low complexity is selected priorly for data embedding, leading to high embedding performance while maintaining low file size. Besides, we design multiple embedding strategies to adaptively select the embedding strategy for each 2D histogram. Experimental results demonstrate that the proposed method can achieve higher rate–distortion performance which maintaining lower file storage space, compared with previous studies.     

Techno-economic assessment of hydrogen refueling station: A case study in Croatia

Hydrogen refueling station (HRS) capacity and location depend on the users, which makes it difficult to select the most favorable option before potential users are actually identified. As in Croatia, at least for now, there are no hydrogen users, this study considers a wide range of HRS capacities and their different configurations. These include hydrogen production and charging station within one existing wind farm in Croatia or both nearby the users, the hydrogen production within the wind farm and the charging station nearby the users, while hydrogen is delivered to the station with a tube trailer, and configuration of hydrogen production within the wind farm with a mobile charging station in case of several users in different locations. Each HRS configuration is evaluated by the obtained levelized cost of hydrogen depending on the capital, and operation and maintenance costs within the HRS techno-economic analysis provided.     

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.     

Korean automatic spacing using pretrained transformer encoder and analysis

Automatic spacing in Korean is used to correct spacing units in a given input sentence. The demand for automatic spacing has been increasing owing to frequent incorrect spacing in recent media, such as the Internet and mobile networks. Therefore, herein, we propose a transformer encoder that reads a sentence bidirectionally and can be pretrained using an out-of-task corpus. Notably, our model exhibited the highest character accuracy (98.42%) among the existing automatic spacing models for Korean. We experimentally validated the effectiveness of bidirectional encoding and pretraining for automatic spacing in Korean. Moreover, we conclude that pretraining is more important than fine-tuning and data size.     

多机器人体间动态碰撞检测方法仿真研究

当前多结合包围求碰撞检测法、Average-Case法、K-DOPs法等实现多机器人体间动态碰撞的检测,均存在寻优性能较差、检测效率较低的问题。为此提出一种基于动态粒子群的多机器人体间动态碰撞检测方法。采用OBB层次包围盒方法,缩小多机器人之间需要动态碰撞检测的区域,同时把动态碰撞检测问题转换为物体特征对间距离机制的非线性优化问题,进而构建层次拓扑框架进行局部碰撞检测,将机器人体引入到粒子群算法中建立混合进化算法,找到动态碰撞检测的最优解,实现多机器人体间动态碰撞检测。仿真结果证明,所提方法的检测效率高达96%,且具有较高的寻优性能。     

结合预训练模型和语言知识库的文本匹配方法

针对文本匹配任务,该文提出一种大规模预训练模型融合外部语言知识库的方法。该方法在大规模预训练模型的基础上,通过生成基于WordNet的同义—反义词汇知识学习任务和词组—搭配知识学习任务引入外部语言学知识。进而,与MT-DNN多任务学习模型进行联合训练,以进一步提高模型性能。最后利用文本匹配标注数据进行微调。在MRPC和QQP两个公开数据集的实验结果显示,该方法可以在大规模预训练模型和微调的框架基础上,通过引入外部语言知识进行联合训练有效提升文本匹配性能。     

面向智能客服系统的情感分析技术

该文以阿里小蜜为例,对智能客服系统中的情感分析技术进行比较全面的介绍,包括情感分析算法模型的原理及其在智能客服系统的多个应用场景中的实际落地使用方式和效果分析。智能客服在解决客户高频业务问题的同时,也需要给客户提供多维度的、具有类人能力的助理、导购、语聊和娱乐等服务,提高客户对智能客服机器人的整体满意度。在此过程中,情感分析技术在机器人类人能力建设中起到了至关重要的作用。该文围绕智能客服系统中人机结合的服务形式,从六个维度总结和介绍了情感分析技术在智能客服系统中的应用场景,包括用户情感检测、用户情感安抚、情感生成式语聊、客服服务质检、会话满意度预估和智能人工入口。     

基于虚拟现实的复杂场景加载优化算法

目前大规模场景模型生成的需求量日益增加, 现提出了一种基于区域的自动 LOD (Levels Of Details)构建算法. 该算法基于动态网格简化算法, 在游戏设计制作的过程中, 游戏开发人员会经常需要对美工部门人员提供的模型进行优化. 为了可以使模型的面数得到简化, 并且不改变模型的外观. 当今流行的 LOD技术非常擅于处理这种情况, 判断模型与摄像机的距离如果超过一定范围之后, 自动调取不同层次的模型, 当模型距离摄像机很远的情况下使用面数低的模型替换高模, 这样可以提高帧率并且降低摄像机前的三角面以及顶点数从而减少渲染压力. 一般模型的简化分为静态和动态模型的简化.大部分情况下, 程序员会让美工部门提供几套不同面数的模型或者通过模型简化工具对高模进行减面并存成多个Mesh, 并在程序运行的时候, 根据模型与摄像机的距离远近动态的替换Mesh. 这是一种静态的方法.这里将尝试使用一种动态的网格简化和LOD技术相结合的方法. 这种新型算法的大大的简化了操作流程, 美术人员只需要提供一个模型, 程序员可以使用这种方法生成量级不同的低模, 根据摄像机与模型的远近自动的调取不同精度的模型.     

Constructing γ-MnO2 hollow spheres with tunable microwave absorption properties

Hollow γ-MnO₂ sphere was obtained by annealing the precursor at 400 °C with different holding time. The influences of different holding time on the morphology and crystalline structure of final products have been discussed in detail, and the microwave absorption properties of the as-products were also investigated. The results exhibited that finer crystalline feature of the γ-MnO₂ and larger pore size in the hollow γ-MnO₂ sphere could be obtained with the extended holding time. The MnO₂/paraffin composites (50 wt% loading) present extraordinary microwave absorption performance, and the minimum reflection loss (RL) values is −51.3 dB at 4.9 GHz with the thickness of 3.5 mm. The excellent electromagnetic absorption properties can be ascribed to the hollow structure, perfect impedance matching behavior and the multiple interface polarization effect.     

基于机器视觉的机车齿轮毂全自动双轴拧紧机的设计和应用

设计了基于机器视觉的机车齿轮毂全自动双轴拧紧机,根据拧紧工艺和扭矩控制原理实现对螺栓拧紧力矩的控制;通过丝杠变径机构,实现不同规格齿轮毂螺栓拧紧;利用机器视觉实现螺栓位置的识别以及初始位置的确定;讨论了自动拧紧机控制系统的硬件组成和软件系统配置,并介绍了防错、防漏功能的设计流程。螺栓自动拧紧机可提高装配精度和操作效率,降低工人的劳动强度。