| ID | 原文 | 译文 |
| 2463 | 本文提出了一种基于加权 Schatten p 范数最小化(Weighted Schatten p-Norm Minimization，WSNM)的磁共振图像重构算法，该方法利用磁共振图像的非局部自相似性，并结合 Schatten p 范数和不同秩元素重要性的加权因子，实现磁共振图像重构过程的低秩约束。 | In this paper, the weighted Schatten p-norm minimization (WSNM )method is proposed to implement magnetic resonance imaging (MRI)reconstruction. The nonlocal self-similarity of magnetic resonance images, Schatten p-norm and the weighting factors of the importance of different rank elements are integrated together as the low rank constraint to regularize the MRI reconstruction. |
| 2464 | 此外，采用交替方向乘子算法(Alternating Direction Method of Multipliers，ADMM)来求解基于 WSNM 磁共振图像重构的非凸最小化问题。 | In addition, the Alternating Direction Method of Multipliers (ADMM )algorithm isused to solve the non-convex minimization problem of MRI reconstruction based WSNM. |
| 2465 | 实验结果表明，相比于最近的磁共振重构算法，基于WSNM 的磁共振图像重构方法具有更好的重建效果，可获得更高的峰值信噪比(Peak Signal to Noise Ratio，PSNR)和更好的结构相似性(Structural Similarity，SSIM)。 | Compared with other state-of-the-art methods in numerical experiments, the proposed method achieves a higher reconstruction quality with higher peak signal to noise ratio (PSNR)and better structural similarity (SSIM)index. |
| 2466 | 近年来，基于深度学习的场景文字检测技术取得重要进展。 | In recent years, deep learning based scene text detection have achieved significant progress. |
| 2467 | 本文综述了该技术在 2014 ～ 2018 年间的最新工作，将其分为传统区域建议方法、文字建议网络方法、基于分割的方法以及文字建议网络与分割的混合方法，并对各类方法的优劣进行分析。 | The paper re-views state-of-the-art methods in the field from 2014-2018. We categorize existing methods into traditional Region Proposalbased method, Text Proposal Network method, segmentation based method and hybrid method based on Text Proposal Net-work and segmentation with detailed analysis of pros and cons for the four methods. |
| 2468 | 本文还展望了未来发展趋势，指出未来研究热点。 | Finally, we point out research trends andfocuses in this field. |
| 2469 | 视频中的人体动作识别是计算机视觉领域内一个充满挑战的课题。 | Human action recognition in videos is a challenging topic in the field of computer vision. |
| 2470 | 不论是在视频信息检索、日常生活安全、公共视频监控，还是人机交互、科学认知等领域都有广泛的应用。 | It is widely notonly used in video information retrieval, daily life security, public video surveillance, but also human-computer interaction, scientific cognition and other fields. |
| 2471 | 本文首先简单介绍了动作识别的研究背景、意义及其难点， | First, the research background, research significance and difficulties of action recognition are briefly introduced, |
| 2472 | 接着从模型输入信号的类型和数量、是否结合了传统特征提取方法、模型预训练三个维度详细综述了基于深度学习的动作识别方法， | and then the deep learning model based action recognition methods are comprehensively reviewed from three different aspects:the types and numbers of input signals, the combination with traditional feature extraction meth-ods, and the pre-trained datasets. |