ID	原文	译文
54037	进一步，考虑到视频换脸操作中眼部和口部区域伪造难度更大也更容易留下篡改痕迹的特点，提出基于这两个区域的双流网络结构，最终利用双流输出结果实现协同决策。	Furthermore, considering the characteristics that the forgeries in eye and mouth areas are more complicated and it is easier for these areas to leave tampering artifacts, a two-stream network structure based on these two areas is proposed, and the two-stream output results are finally used to form a collaborative decision.
54038	通过在Celeb-DF、DFDC、DeepFakeDetection、FaceForensics++等目前常用数据集上的广泛实验，结果表明本文提出的方法在检测准确性和效率上较目前最先进的Xception和标准I3D网络均得到显著提升。	Via extensive experiments on commonly used databases including Celeb-DF, DFDC, DeepFakeDetection, and FaceForensics++, the results verify that the detection accuracy and computational efficiency of the method proposed in this paper are substantially improved compared with the state-of-the-art Xception and standard I3D networks.
54039	针对多跳工业无线传感器网络中物理层安全窃听攻击问题，研究了一种反馈Stackelberg博弈功率控制(Feedback Stackelberg Game Power Control，FSPC)方案。	To solve the problem of physical layer security in industrial wireless sensor networks, a feedback Stackelberg game power control(FSPC) scheme is studied.
54040	基于提高一跳内安全速率，通过付费方式激励目的节点提供协同干扰服务，利用Stackelberg博弈模拟发送节点和目的节点的交互行为。	Based on improving the security rate in one hop, encourage the destination node to provide cooperative jamming service by paying, where the Stackelberg game is used to simulate the interaction between the sending node and the destination node.
54041	基于提高多跳主干网安全速率，发送节点效用引入反馈代价函数，以减小跳间安全速率的波动性。	Based on improving the security rate of multi-hop backbone network, the feedback cost function is introduced to reduce the fluctuation of the security rate between connected hops.
54042	仿真结果表明，相比于其他未引入反馈代价函数的博弈功率控制算法，本文方案能更有效地保证数据在主干网中的传输安全性。	The simulation results show, compared with other game power control algorithms without introducing feedback cost function, the proposed FSPC scheme can be more effectively to ensure the security of data transmission in the backbone network.
54043	在多输入多输出(Multiple input multiple output，MIMO)雷达中，针对运动目标所产生的信号变化易受多径效应和杂波环境的影响，导致运动目标检测性能不理想的问题，提出了一种基于时间反演(Time Reversal，TR)的优化方案。	In the multiple input multiple output(MIMO) radar, aiming at the problem that the signal changes caused by moving targets are easily affected by multipath effect and clutter environment, an optimization scheme based on time reversal is proposed.
54044	首先，利用时间反演的空时聚焦性，减少多径效应对目标信号的影响，同时使运动目标产生的信号能量聚焦，不易淹没在杂波环境中;	Firstly, the space-time focusing property of time reversal is used to reduce the influence of multipath effect on the target signal, and the signal energy generated by the moving target is focused, which is not easy to be submerged in the clutter environment;
54045	其次，通过奈曼皮尔逊准则设计检测算法并计算出检测概率的近似计算公式;	secondly, the detection algorithm is designed by the Neyman Pearson criterion and the approximate calculation formula of detection probability is calculated;
54046	最后仿真结果表明：在杂波环境具有相同信噪比情况下，所提方案比传统MIMO的检测方法有较好的性能提升。	finally, the simulation results show that the signal-to-noise ratio is the same in the clutter environment the proposed scheme has better performance than the traditional MIMO detection methods.