ID 原文 译文
17135 该文在MSTAR数据集上进行对比实验，实验结果表明所提算法在性能方面取得了提升，且其性能对超参数设置具有一定的鲁棒性。 Experiments on themoving and stationary target acquisition and recognition data show that the proposed method is an effectivetarget recognition method, and the recognition performance is robust to the hyper-parameters.
17136 针对雷达检测无人机这一难题，该文提出了一种时频检测与极化匹配相结合的双极化雷达无人机检测方法。 Radar detection of Unmanned Aerial Vehicle (UAV) is a big problem. To address this problem, adetection method with dual polarization radar is proposed.
17137 首先，雷达降低检测门限，各极化通道分别采用常规的时频2维单元平均恒虚警率检测方法，检测出无人机与杂波虚警； First, radar reduces the detection threshold to make the UAV be detected by using the traditional two dimensional cell averaging constant false alarm probability detector in two polarization channels respectively.However, some false targets caused by clutter are also detected by radar at the same time.
17138 接着，各极化通道分别针对多帧检测结果进行积累，进行2次检测，剔除部分杂波虚警； To eliminate these false targets, the detection results are integrated and the second detection is carried out for the integrated results in two polarization channels respectively.
17139 最后，对两个极化通道双门限检测结果进行匹配，进一步剔除杂波虚警。 Then, the second detection results in two polarization channels are matched to further eliminate the false targets. Outdoor experiment is carried out.
17140 对两型无人机的外场试验数据处理结果表明：该方法能够有效检测出无人机，消除杂波虚警。 The processing results for the real data demonstrate that the second types of UAV can be effectively detected and the false targets caused by clutter can be eliminated at the same time with the proposed method.
17141 针对遥感图像场景分类面临的类内差异性大、类间相似性高导致的部分场景出现分类混淆的问题，该文提出了一种基于双重注意力机制的强鉴别性特征表示方法。 Considering the problem of low classification accuracy caused by large intra-class differences and highinter-class similarity in remote sensing image scene classification, a discriminative feature representation methodbased on dual attention mechanism is proposed.
17142 针对不同通道所代表特征的重要性程度以及不同局部区域的显著性程度不同，在卷积神经网络提取的高层特征基础上，分别设计了一个通道维和空间维注意力模块， Due to the difference in the importance of the featurescontained in different channels and the significance of different local regions, the channel-wise and spatial-wiseattention module are designed, based on the high-level features extracted by the Convolutional NeuralNetworks.
17143 利用循环神经网络的上下文信息提取能力，依次学习、输出不同通道和不同局部区域的重要性权重，更加关注图像中的显著性特征和显著性区域，而忽略非显著性特征和区域，以提高特征表示的鉴别能力。 Relying on the ability to extract contextual information, the Recurrent Neural Network is adopted to learn and output the importance weights of different channels and different local regions, paying more attention to the salient features and salient regions, while ignoring non-salience features and regions, to enhance the discriminative ability of feature representation.
17144 所提双重注意力模块可以与任意卷积神经网络相连，整个网络结构可以端到端训练。 The proposed dual attention module can be connected to thelast convolutional layer of any convolutional neural network, and the network structure can be trained end-to-end.