ID 原文 译文
40876 针对当前YOLOv3算法在遥感图像中复杂场景飞机漏检、误检等问题，提出一种基于自适应特征融合及多尺度输出的遥感图像飞机检测算法。 In view of the problems such as missing detection and false detection of complex scene aircraft in remote sensing image by the YOLOv3 algorithm, an aircraft detection algorithm based on adaptive feature fusion and multiscale output is proposed.
40877 该算法首先使用K-means++代替K-means算法对数据集进行聚类，解决了K-means初始聚类中心不稳定性; Firstly, K-means ++ is used to cluster the data set instead of K-means algorithm, which solves the instability of the initial clustering center of k-means.
40878 然后，在YOLOv3网络基础上增加了一个含有分辨率信息的尺度，更有利于检测小目标飞机; Then, on the basis of YOLOv3 network, a scale with resolution information is added, which is more conducive to the detection of small target aircraft.
40879 最后，在网络模型四尺度输出前增加了自适应特征融合层，解决了不同尺度的特征融合不充分以及减少或消除反向传导受到负样本的影响。 Finally, an adaptive feature fusion layer is added before the four scale output of the network model, which solves the problem of insufficient feature fusion at different scales and reduces or eliminates the influence of negative samples on reverse conduction.
40880 实验结果表明，改进的YOLOv3算法在遥感图像上飞机检测精度达到96.17%，比YOLOv3算法精度提高了2.6%。 The experimental results show that the detection accuracy of the improved algorithm reaches 96.17% in the remote sensing image, which is 2.6% higher than that of the algorithm.
40881 传统的社区发现算法中网络节点相似度多以空间距离度量，这种度量往往不容易理解，或者只能从距离的角度予以解释。 In traditional community detection algorithms, the similarity of network nodes is usually measured by spatial distance, which is not easy to understand or can only be explained from the perspective of distance.
40882 本文提出一种基于文本内容相似度的谱聚类方法，它以网络社区用户的文本信息的相似性来度量网络节点的属性相似度，考虑网络结构的同时使节点的属性联系更有意义。 This paper proposes a spectral clustering method based on the similarity of text content, which measures the attribute similarity of network nodes by the similarity of text information of users in the network community, and makes the attribute connection of nodes more meaningful when considering the network structure.
40883 在此基础上使用谱聚类的思想进行社区划分。 On this basis, the idea of spectral clustering is used to divide the community.
40884 本文以实际数据进行实验发现，发现划分结果的模块度和节点平均相似度较高，聚类效果良好。 The experimental results show that the modular degree and the average similarity of nodes are high, and the clustering effect is good.
40885 深度强化学习在各个领域中都展现出了巨大的潜力，但现有的深度强化学习算法需要大量样本才能学习到一个较好的策略，而在实际场景中，深度强化学习样本通常存在数量少、成本高等特性。 Deep reinforcement learning has shown great potential in various fields, but the existing deep reinforcement learning algorithms need a large number of samples to learn a better strategy, while in actual scenes, deep reinforcement learning samples usually have the characteristics of small quantity and high cost.