ID 原文 译文
22665 同时引入积分图像进行快速计算，以满足实时性要求。 Integral images are also introduced for fast computation to meet the real-time application requirements.
22666 实验结果表明，该方法在主观视觉感知和客观评价指标方面都要略优于现有的方法。 Experimental results demonstrate that the proposed method is competitive with or even outperforms the state-of-the-art methods in terms of both subjective visual perception and objective evaluation metrics.
22667 该文以经典的对称旅行商问题(Symmetric Traveling Salesman Problem, STSP)为基础，求解时间最优的旅行商问题(Time Optimal TSP, TOTSP)，将拟合函数引入到混合蛙跳遗传算法(SFLA-GA)的适应度函数来反映景点客流量随时间的变化，旨在旅游旺季为游客提供一条游览时间最短的路径推送服务。 In order to provide a recommended-path service for tourists with the shortest traveling time in the peak-season, the Time Optimal Traveling Salesman Problem (TOTSP) is further studied and the fit function is introduced into the fitness function of the hybrid Shuffled Frog Leaping Algorithm-Genetic Algorithm (SFLA-GA) to reflect the change of traffic over time, which is based on the classic and Symmetrical Traveling Salesman Problem (STSP).
22668 实验结果表明：相对于随机游览路径，SFLA-GA 混合算法得到的游览路径明显节省了游览时间； The experimental results show that compared with the random tour path, the tour path significantly saves the tour time which is obtained by the hybrid SFLA-GA.
22669 与 SFLA 和混合粒子群遗传算法(PSO-GA)相比较，SFLA-GA 混合算法具有计算量少、收敛速度快、对初始种群依赖性低以及全局性更好等优点，在求解TOTSP 上搜索性能更强、时间更优。 Compared with SFLA and hybrid Particle Swarm Optimization-Genetic Algorithm (PSO-GA), the hybrid SFLA-GA has some advantages, such as less amount of calculation, fast speed of convergence, low dependency on initial population, good global superiority and so on. The hybrid SFLA-GA has stronger search capability and less search time in solving the TOTSP.
22670 基于大量训练样本生成高置信度图像的生成对抗网络研究已经取得一些成果，但是现有的研究只针对已知训练样本进行图像生成，而未将训练的参数用于训练样本之外的图像生成。 Based on a large number of training samples to generate high confidence images, generative adversarial nets achieve good results, but the existing network of image generation in the training sample basis, the training parameters can not be used to generate images outside of training samples.
22671 该文设计了一种改进的生成对抗网络模型，在已有网络的基础上增加一个还原层，使得测试图像可以通过改进的对抗网络生成对应的高置信度图像。 In this paper, an improved generative adversarial nets model is proposed, and a reduction layer is added on the basis of the existing network, so that the test image can generate the corresponding high confidence image through the improved generative adversarial nets.
22672 实验结果表明，改进的生成对抗网络参数可以应用到训练集之外的普通样本。 The experimental results show that the improved generative adversarial nets parameters can be applied to the common samples outside the training set.
22673 同时本文改进了生成模型的损失算法，极大地缩短了网络的收敛时间。 At the same time, this paper improves the loss algorithm of the generated model, which greatly shortens the convergence time of the network.
22674 针对静态表情特征缺乏时间信息，不能充分体现表情的细微变化，该文提出一种针对非特定人的动态表情识别方法：基于动态时间规整(Dynamic Time Warping, DTW)和主动外观模型(Active Appearance Model, AAM)的动态表情识别。 To overcome the deficiency of static expression feature, which lacks time information and can not reflect the subtle changes of expression adequately, a dynamic expression recognition method is proposed for non-specific face: the dynamic expression recognition based on Dynamic Time Warping (DTW) and Active Appearance Model (AAM).