ID 原文 译文
25825 但现有的标准卷积神经网络方法，通常会造成颜色差异过大和图像纹理缺失与失真的问题。 However, the existing standard convolutional neural network approaches often cause problems with excessive color discrepancy, image texture loss and distortion．
25826 本文提出了一种新型图像修复深度网络模型，该模型由两个相互独立的生成对抗式网络模块组成。 A deep network based image inpainting model is proposed in this paper, consisting of two generative adversarial network modules.
25827 其中，图像修复网络模块旨在解决图像缺失区域的修复问题，其生成器基于部分卷积网络;图像优化网络模块旨在解决修复后图像存在局部色差的问题，其生成器基于深度残差网络。 One of the modules is used to inpaint the missing area of the image, where the generator is constituted with partial convolutions. The other module is the image optimization network, which is applied to solve the problem of local chromatic aberration after image restoration, and in which the generator is originated from the depth residual network．
25828 通过两个网络模块的协同作用，图像的视觉效果与图像质量得到提高。 These two modules cooperated to improve the visual effect and image quality of inpainted images.
25829 与其他先进方法进行定性和定量比较的实验结果表明，本文提出的方法在图像修复质量上表现更好。 Using MOS, SSIM and PSＲN as the evaluation criteria, the experimental results of qualitative and quantitative comparisons with other state-of-the-art methods have shown that the proposed model performed better.
25830 密文策略属性加密方案适用于云环境中密文数据的访问控制。 Ciphertext-policy attribute-based encryption scheme is suitable for access control of ciphertext data incloud environment．
25831 已有的支持算术张成程序的属性加密方案多是密钥访问策略的方案，且公开参数规模较大。 Most of the existing attribute-based encryption schemes supporting arithmetic span programs are key-policy schemes with large public parameter scale．
25832 本文利用双对偶向量空间( Dual Pair Vector Space，DPVS) 技术，提出了一个公开参数长度固定、支持算术张成程序的密文策略属性加密方案。 By exploiting the double Dual Pair Vector Space( DPVS) technique, aciphertext-policy attribute-based encryption scheme which has a fixed length of public parameters and supports arithmetic span programs is proposed in this paper．
25833 在新方案中，将密文相关的访问控制向量与随机矩阵结合，密钥相关的属性分量与熵扩张引理中的公开参量结合，设计方法对应了熵扩张引理中给出的密文和密钥分量的形式。 In this scheme, the ciphertext-related access control vector is combined with the random matrix, and the key-related attribute components are combined with the public parameters in the entropy expansion Lemma. The method is designed according to the form of ciphertext and key components given in the entropy expansion Lemma．
25834 最后，基于素数阶双线性熵扩张引理和 k-Lin 困难假设，证明了该方案具有适应安全性。 Finally, the adaptive security of the scheme is proved based on the prime order bilinear entropy extension Lemmaand k-Lin difficult assumption．