ID 原文 译文
23615 同时，利用共享特征来学习属性排序函数，得到基于共享特征的相对属性模型，解决了相对属性学习过程中丢失属性与类别关系的问题。 Inspired by the success of shared features, a novel relative attributes model based on shared features is proposed to promote the performance of the relationship between attributes and classes, in which the ranking function per attribute is learned by using shared features.
23616 另外，将基于共享特征的相对属性模型用于零样本图像分类中，有效提高了零样本图像分类的识别率。 In addition, the novel relative attributes model based on shared features is applied to zero-shot image classification, which yields high accuracy due to the shared features included.
23617 实验数据集上的结果表明，该方法具有较高的相对属性学习性能和零样本图像分类精度。 Experimental results demonstrate that the proposed method can achieve high relative attributes learning efficiency and zero-shot image classification accuracy.
23618 相位成像的关键是相位恢复。 The key issue in phase imaging is phase retrieval.
23619 由于相位信息的丢失，相位恢复通常是不适定的，如何利用合适的先验信息进行相位恢复是一个重要问题。 Due to the loss of the phase information, the phase retrieval problem is usually ill-posed. How to realize the phase retrieval by using appropriate prior information is an important problem.
23620 该文在 SPICA 成像系统下提出了基于结构稀疏性的单次曝光相位成像算法。 In this work, based on single-shot phase imaging with a coded aperture, a single-shot phase imaging algorithm, which uses the structural sparsity, is proposed.
23621 该算法利用图像全变差的重叠组结构稀疏性，将重叠的结构稀疏正则项以卷积形式表示，使求解过程更简单，并利用最速下降法求解相应的优化问题。 The proposed algorithm exploits the overlapping structural sparsity of the total variation, and represents the structural sparsity in the form of convolution, making the problem easy to solve. Moreover, the steepest descent method is utilized to solve the corresponding optimization problem.
23622 实验结果表明，该算法在有噪声的情况下能够有效地实现对复图像的重构。 The experiment results show that the complex amplitude can be reconstructed from noisy diffraction pattern using the proposed algorithm.
23623 斜视 TOPSAR(Terrain Observation by Progressive scans SAR)成像模式中，场景内各点目标多普勒中心频率的差异导致方位向信号欠采样并加剧频谱的耦合。 In the squint Terrain Observation by Progressive scabs (TOPSAR) mode, the different azimuth scatters have different Doppler center frequencies, which causes azimuth under-sampling problem and increase the coupling between range and azimuth.
23624 针对 TOPSAR 的回波特点，该文提出一种新的 TOPSAR全孔径成像算法：首先引入高阶视向速度补偿消除回波信号的频域模糊； Considering at the characteristics of squint TOPSAR echo, this article proposes a new full aperture imaging algorithm: first, the azimuth signal aliasing is removed by introducing the nonlinear walk correction;