ID 原文 译文
40486 本文从体系结构的角度阐明了冯·诺伊曼架构所引起的"功耗墙"和"存储墙"问题，并给出了存内计算技术的兴起原因. This paper clarifies the problems of "power wall" and "storage wall" caused by the von Neumann architecture from the perspective of architecture, and gives the reasons for the rise of in-memory computing.
40487 文章围绕近几年国内外关于SRAM存内计算架构的研究，以其中几种经典架构为例描述了各类SRAM存内计算的工作机理、优缺点及意义， The paper focuses on the research of SRAM-based in-memory computing architectures in recent years, and describes the working mechanism, advantages and disadvantages and significance of various SRAM-based in-memory computing architectures by taking several classical architectures as examples.
40488 并从器件级、电路级和架构级的角度分别概述了目前关于SRAM存内计算技术的关键影响因素.SRAM存内计算技术潜力巨大，用途广泛，将会给机器学习应用，图计算应用和基因工程提供高效低能耗的系统结构支持， And from the perspective of device level, circuit level and architecture level, the key factors of current SRAM-based in-memory computing technology are summarized respectively. The SRAM-based in-memory computing technology is a promising and versatile technology that will provide efficient and low-energy system architectures for machine learning applications, graph computing applications and genetic engineering.
40489 最后展望了未来几年内SRAM存内计算技术在器件、电路和架构方面的发展情况. The paper looks forward to the development of SRAM-based in-memory computing technology in devices, circuits and architectures in the coming year
40490 针对目标跟踪算法在运动目标中存在的背景干扰和鲁棒性问题，提出一种基于Siamese RPN++改进的非对称残差注意网络算法. In order to solve the background interference and robustness problems of object tracking algorithm in moving targets, an asymmetric residual attention network algorithm based on Siamese RPN++ was proposed.
40491 通过在模板分支对应的网络中添加非对称残差注意力结构，从而提取出采样图像的共同特征，形成较为稳定的目标轮廓，解决了目标运动背景发生变化的问题; First, aAsymmetric residual attention structure is added to the network corresponding to the template branch, so as to extract the common features of the sampled images, form a relatively stable target contour, and solve the problem that the target moving background changes.
40492 采用自适应权值更新的方法融合不同区域候选网络模块输出的特征，得到更为鲁棒性的尺度变化特征表达，解决了目标形变的问题. The adaptive weight updating method is adopted to fuse the output features of candidate network modules in different regions to obtain more robust expression of scale change features and solve the problem of target deformation.
40493 实验结果表明:提出的改进算法在具有挑战的跟踪测试视频上取得了良好的跟踪精度，且具有较好的鲁棒性，能够较好地应对运动背景变化、尺度变化等问题. The experimental results show that the proposed improved algorithm has good tracking accuracy and robustness in challenging tracking test videos, and can deal with the changes of moving background and scale.
40494 针对高光谱数据样本标签标注困难问题，以及多数特征提取算法仅考虑光谱特征信息，而忽略了空间信息的问题.提出了一种在无监督场景下的空谱协同竞争保持图嵌入(SCPGE)高光谱图像特征提取方法. Aiming at the difficulty of labeling hyperspectral image samples and the problem that most feature extraction algorithms only consider spectral feature information but ignore spatial information, a new feature extraction of hyperspectral image with spatial-spectral collaboration-competition preserving graph embedding(SCPGE) in unsupervised scenes was proposed.
40495 利用协同表示揭示全局流形结构，配合基于空间近邻信息和光谱近邻信息的局部约束特性来计算出该像元的表示系数，继而利用表示系数矩阵构建图的权重矩阵，通过施加正则项的图嵌入目标函数获得最佳投影矩阵. The collaborative representation is used to characterize the global manifold structure, combined with locality-constrained property based on spatial information and spectral information to calculate the representation coefficient of the pixel. Used the weight matrix of the graph drawn by the coefficient matrix, and the objective function with regular term to obtain the projection matrix.