ID 原文 译文
39016 在深度卷积神经网络中引入高阶注意力模块，通过注意力机制建模和利用复杂和高阶的统计信息，对训练过程中特征图各个部分的权重进行重新分配，从而关注局部细粒度信息，产生有区别性的关注建议，捕获行为之间的细微差异。 A high-order attention module was introduced to a deep convolutional neural network, which modeled and utilized the complex and high-order statistics information in attention mechanism. The goal of attention was to reallocate the weight of each part of the feature map in the process of training, so as to focus on the local fine-grained information, produce the discriminative attention proposals, and capture the subtle differences among behaviors.
39017 在UCF101和HMDB51这两个人体行为数据集上的实验结果表明，与现有方法相比，识别率得到了一定的提升，验证了所提出方法的有效性和鲁棒性，提高了对近似行为的辨别能力。 Extensive experiments had been conducted to validate the superiority of our method for action recognition on two human behavior datasets, including UCF101 and HMDB51. The results showed that the recognition rate has been improved to a certain extent compare with the existing methods, which validated the effectiveness and robustness of the proposed method. The method effectively improves the ability to distinguish approximate behaviors.
39018 为简化联合概率数据关联算法(Joint Probabilistic Data Association， JPDA)的计算复杂度，增强JPDA算法的实时性，设计了一种新的JPDA简化算法。 To simplify the computational complexity of Joint Probabilistic Data Association(JPDA) and enhance the real-time performance of JPDA algorithm, a new simplified JPDA algorithm was proposed in this paper.
39019 首先根据目标航迹与量测之间的关联规则，定义了一种新的计算关联概率的方法，之后分析公共量测对目标的影响，引入公共量测影响因子修正关联概率。 Firstly, according to the association rules between the trajectory and the measurement of the target, a new method to calculate the simple association probability is defined. Then, the influence of the public measurement on the target is analyzed to modify the association probability.
39020 该算法不用进行确认矩阵拆分，有效解决了在密集杂波环境下因回波密度增加而造成的计算上的组合爆炸问题。 The algorithm does not need to split the confirmation matrix, and the problem of combinatorial explosion caused by the increase of echo density in the dense clutter environment can be effectively solved.
39021 仿真结果表明，简化的JPDA算法能够在保持对目标有效跟踪的情况下，大大缩短计算时间，提高算法的实时性。 The simulation results show that the simplified JPDA algorithm can greatly shorten the computation time and improve the real-time performance while keeping effective tracking of the target.
39022 针对量子索引图像在量子计算机信息安全领域中的应用问题，本文提出一种基于分量和(sum of components， SoC)的量子索引图像信息隐藏算法。 Aiming at the application of quantum indexed images in the field of information security on quantum computers, a quantum indexed image information hiding algorithm based on the sum of components(SoC) is proposed in the paper.
39023 量子索引图像包括数据矩阵和调色板2种数据结构。 A quantum indexed image contains 2 data structures: quantum data matrix and quantum palette.
39024 基于SoC的量子索引图像信息隐藏算法首先根据颜色值分量和的奇偶性(1或0)和颜色值距离，为量子调色板中每一个颜色匹配一个符合条件的颜色组成颜色对; In the quantum indexed image SoC information hiding algorithm, first according to the parity of the color value component sum(1 or 0) and distance of the color values, match each color in the quantum palette with a qualified color to form a color pair;
39025 嵌入消息时，根据颜色对和消息比特对量子数据矩阵的像素索引值进行更新; When the message is embedded, the pixel index value in the quantum data matrix is updated according to the color pair and the message bit;