ID 原文 译文
57028 仿真实验表明本文所提算法在主观评价和客观评估方面与已有算法相比具有一定优势. Simulation experiments show that the proposed algorithm is superior to the classical algorithm insubjective and objective evaluation.
57029 传统的区块链结构,由于其固有的响应速度慢,不能适应大规模实时响应的应用场景,本文针对这一问题,提出了一种DAG (directed acyclic graph)区块链理论架构,将传统区块链的链式处理过程转变为并行的处理过程,使得快速响应成为可能. The traditional blockchain structure cannot adapt to large-scale and real-time-application scenar?ios because of its inherently slow response. To solve this problem, a theoretical framework of DAG (directedacyclic graph) blockchain is proposed, transforming the chain processing of a traditional blockchain into parallelprocessing.
57030 在此基础上,面向DAG区块链环境中非独立任务调度问题,提出了基于确定性退火技术的混合分割遗传任务调度算法. On this basis, the non-independent task-scheduling problem in the DAG blockchain environment isstudied, and a fusion-partitioning genetic task-scheduling algorithm based on deterministic annealing technologyin DAG blockchains is proposed.
57031 实验结果显示,该算法能够适应DAG区块链节点的异质性、动态性和广域性,其调度的性能也比传统的调度算法有所改善,在优化任务完成时间的同时,兼顾了负载均衡问题,有效地提高了响应速度,是解决DAG区块链环境中非独立任务调度问题的可行方法. The experimental results show that the algorithm can adapt to the heterogene?ity, dynamism, and wide area of DAG blockchain nodes, and its scheduling performance is better than that ofthe traditional scheduling algorithm. While optimizing the task-completion time, the algorithm takes account ofthe load-balancing problem and effectively improves the response speed. It is a feasible method for solving thenon-independent task-scheduling problem in the DAG blockchain environment.
57032 传统的基于稀疏表示的图像超分辨率重建算法,需要将图像进行分块并列化为向量,这样就破坏了图像块内邻域像素间的相关性. Traditional sparse representation-based super-resolution algorithms need to divide images into patchesand then stack them into columns. This operation ignores the intrinsic 2D structure and spatial correlationinherent in patches.
57033 为了更好地利用图像邻域内的结构信息,本文结合分离字典能从不同方向对图像块进行稀疏表示的特性,提出了基于分离字典的图像超分辨率重建算法. In order to fully exploit 2D spatial correlation in image patches, we combine the sparserepresentation ability of the separable dictionary in both the horizontal and vertical directions, and propose analgorithm for image super-resolution based on a separable dictionary.
57034 实验结果表明,与传统基于稀疏表示的图像超分辨率重建算法相比,本文算法不仅提高了图像重建的速度,而且在PSNR和SSIM两个衡量指标上都优于传统基于稀疏表示的超分辨率重建算法(PSNR提高约0.2 dB, SSIM提高约0.01). The experimental results show that ourproposed algorithm not only improves the efficiency of image super-resolution, but also improves the PSNR andSSIM (i. e. , about 0. 2-dB PSRN better than traditional methods, and 0. 01 SSIM better than existing methods).
57035 判别相关滤波跟踪算法通过对中心目标块(唯一准确正样本)循环移位获取训练集,依赖潜在样本周期延拓假设,使得模型训练和检测可以通过快速傅里叶变换高效完成,然而整个学习过程没有对真正的背景信息进行建模. Discriminant correlation filter-based tracking approaches, which adopt a circular shift operator on the tracking target object (the only accurate positive sample) to obtain training data and rely on the potential sample periodic extension hypothesis that enables model training and detection, can be efficiently accomplished through FFT.
57036 背景感知相关滤波(BACF)跟踪算法利用一个二进制掩码矩阵通过密集采样的方法获取真正的正、负样本对目标外观进行建模,然而BACF算法在学习相关滤波器时并没有考虑滤波器的时间一致性和空间一致性信息,当目标出现外观突变时,学习到的相关滤波器将会偏向背景而发生漂移.为了解决学习到的相关滤波器适应连续帧之间的外观突变问题, However, real background information is not modeled during the total learning process. The background?aware correlation filter (BACF) tracking algorithm uses a binary matrix to acquire real positive and negative samples using a dense sampling method to model the target’s appearance. However, the BACF algorithm does not consider temporal and spatial consistency information, and when a target undergoes an abrupt change, the learned correlation filter will drift to the background.
57037 本文在基准BACF算法框架下引入时间一致性约束项和空间一致性约束项,提出了学习时空一致性相关滤波(TSCF)跟踪算法.时间一致性约束项在时间序列意义上起到平滑多通道相关滤波的作用;空间一致性约束项在空间分布意义上平滑多通道相关滤波,使得学习到的相关滤波能量分布更加均匀. To solve this problem, in this paper, we introduce temporal and spatial consistency constraints into the baseline BACF framework and propose a learning temporal-spatialconsistency correlation filter (TSCF) tracking algorithm. This enables the correlation filter to learn to adapt to the appearance of mutation between successive frames.