ID	原文	译文
16495	最近，存算一体(IMC)架构引起了广泛关注，并被认为有望成为突破冯诺依曼瓶颈的新型计算机架构，特别是在数据密集型(data-intensive)计算中能够带来显著的性能和功耗优势。	In-Memory Computing (IMC) architectures have aroused much attention recently, and are regardedas promising candidates to break the von Neumann bottleneck. IMC architectures can bring significant performance and energy-efficiency improvement especially in data-intensive computation.
16496	其中，基于SRAM的IMC架构方案也被大量研究与应用。	Among those emerging IMC architectures, SRAM-based ones have also been extensively researched and applied to many scenarios.
16497	该文在一款基于SRAM的通用存算一体架构平台——DM-IMCA的基础上，探索IMC架构在物联网领域中的应用价值。	In this paper, IoT applications are explored based on a SRAM-based generic IMC architectureplatform named DM-IMCA.
16498	具体来说，该文选取了物联网中包括信息安全、二值神经网络和图像处理在内的多个轻量级数据密集型应用，对算法进行分析或拆分，并将关键算法映射到DM-IMCA中的SRAM中，以达到加速应用计算的目的。	To be specific, the algorithms of several lightweight data-intensive applications inIoT area including information security, Binary Neural Networks (BNN) and image processing are analyzed, decomposed and then mapped to SRAM macros of DM-IMCA, so as to accelerate the computation of these applications.
16499	实验结果显示，与基于传统冯诺依曼架构的基准系统相比，利用DM-IMCA来实现物联网中的轻量级计算密集型应用，可获得高达24倍的计算加速比。	Experimental results indicate that DM-IMCA can offer up to 24 times performance speed-up, compared to a baseline system with conventional von Neumann architecture, in terms of realizing light weight data-intensive applications in IoT.
16500	人群计数研究普遍使用欧几里得损失函数，易造成图像局部相关性缺失，且现有研究方法未能充分提取人群图像中连续变化的尺度特征，影响了人群计数模型的性能。	The performance of the crowd counting methods is degraded due to the commonly used Euclideanloss ignoring the local correlation of images and the limited ability of the model to cope with multi-scale information.
16501	针对上述问题，该文提出一种基于多尺度增强网络的人群计数模型(MSEN)。	A crowd counting method based on Multi-Scale Enhanced Network(MSEN) is proposed to addressthe above problems.
16502	首先，在多分支结构生成网络中引入区域性判别网络，将二者组合形成嵌入式GAN模块，以增强生成图像的局部相关性；	Firstly, an embedded GAN module with a multi-branch generator and a regional discriminator is designed to initially generate crowd density maps and optimize their local correlation.
16503	之后，基于金字塔池化结构设计了尺度增强模块，将该模块连接在嵌入式GAN模块之后，进一步从不同区域提取不同尺度的局部特征，以最大程度地应对人群图像局部尺度连续变化的问题，从而增强整体模型的泛化能力。	Then, a well-designed scale enhancement module is connected after the embedded GAN module to extract further local features of different scales from different regions, which will strengthen the generalization ability of the model.
16504	最后，在3个具有挑战性的人群计数公共数据集上进行了广泛的实验。实验结果表明，该文所述模型可有效提升人群计数问题的准确性和鲁棒性。	Extensive experimental results on three challenging public datasets demonstrate that the performance of the proposed method can effectively improve the accuracy and robustness of the prediction.