ID 原文 译文
57768 在真实数据集上的实验结果表明，算法的模板挖掘匹配度优于基准方法，并且具有良好的泛化性能. Experiments on real data indicated that the algorithm can achieve more stable and accurate template extraction performance than the benchmark method，and it had good generalization per- formance.
57769 为了解决传统彩色铅笔画算法生成结果单一的问题，提出了一种基于卷积神经网络( CNN) 生成彩色铅笔画的算法. In order to optimize the single generation result of traditional color pencil drawing algorithms， a convolution neural network ( CNN) based color pencil drawing generation method is presented.
57770 采用分数阶微分获取原始图像轮廓信息，用卷积神经网络获取艺术家手绘铅笔画风格，利用直方图匹配获取与手绘铅笔画相似的色调，并使用 L-BFGS 优化算法来合成具有铅笔画效果的图像. Frac- tional differentiation is employed to obtain original image contour information，CNN can obtain pencil drawing style，and histogram matching can obtain similar tones. Meanwhile，L-BFGS algorithm is used to synthesize pencil drawing image.
57771 该算法能够生成具有不同风格的彩色铅笔画图像. This can generate color pencil drawing images of different styles.
57772 实验结果表明，该算法生成的图像保留了更多原始图像的细节信息，风格更加灵活多样 Exper- iments show that the images generated can retain more original image detail information，and feature with more flexible and diverse styles.
57773 移动云计算为部署大量移动服务提供了技术支持，但用户在不稳定的通信条件下访问云资源往往需要大量的能耗，制约了移动云计算的广泛应用. The technology of mobile cloud computing is benefit for deploying various mobile applications. However，there is an energy consumption problem to access cloud resources via mobile phone，which needs to establish connections many times under unstable communication conditions.
57774 对此，提出了基于用户交互行为最大化的链路预测方法. To solve this prob- lem，a link prediction method based on maximum user interaction behavior was proposed.
57775 首先在数据预测模型的基础上利用基于互动关系改进的交互度方法对已知用户访问的数据进行预测; Firstly，based on data prediction model，an interaction degree method based on improved interaction relationship is used to predict the data accessed by users.
57776 再结合基于用户行为的社交网络 Friendlink 方法对预测数据进行数据分析筛选，利用数据预存储机制来预存上述预测数据. Then，combined with the friend link method of social network based on user behavior，the prediction data is analyzed and filtered，and the pre-storage mechanism is used to pre-store the above prediction data.
57777 实验结果表明，在保证不涉及用户隐私信息，并提高用户下次访问命中率的情况下，达到了预期的手机节能目的. Experiments show that the expected energy saving of mobile phones can be achieved without involving users’private information and improving the hit rate of users’ next visit.