ID 原文 译文
15295 对近年来基于卷积神经网络的2D人体姿态估计的方法进行梳理介绍,将现有方法分为人体检测关节点回归融合算法和人体关节点检测聚类算法,同时对当前的主流数据集及其评价准则进行总结,最后对2D人体姿态估计当前所面临的困难以及未来的发展趋势做以阐述,为姿态估计相关研究提供一些参考。 This paper introduces the methods of 2D human pose estimation based on convolutional neural networks in recent years. The existing methods are divided into human body detection combined with joint point regression algorithm and human body joint point detection clustering algorithm.At the same time, the current mainstream datasets and the evaluation criteria are summarized, and finally the current difficulties and future development trends of 2D human pose estimation are explained, which provides some references for related research on pose estimation.
15296 为支持广泛的QoS级别,需要自动调整5G网络以响应网络状况,以保持最佳的性能效率。 In order to support a wide range of QoS levels, 5G networks need to be automatically adjusted to respond to network conditions in order to maintain the best performance efficiency.
15297 5G网络将拥有比前几代蜂窝移动通信网络更多的小区,因此自组织网络(Self-Organizing Network,SON)对于运营商管理复杂的5G网络更为重要。 5G networks will have more cells than previous generations of cel-lular mobile communication networks, so self-organizing networks( SON) are more important for operators to manage complex 5G networks.
15298 介绍了3GPP工作组SA5和RAN针对5G SON的研究工作,并对自动邻居关系、PCI配置、容量和覆盖率优化、负载平衡优化、移动鲁棒性优化、RACH优化等关键优化技术进行详细阐述。 This article introduces the research work of 3 GPP working group SA5 and RAN for 5G SON, and elaborates on key opti-mization technologies such as automatic neighbor relationship, PCI configuration, capacity and coverage optimization, load balancing optimization, mobile robustness optimization, and RACH optimization.
15299 通信技术的普及给人们带来便捷的同时,电信欺诈行为也急剧增加。 While communication technology brings convenience to people, telecom fraud also increases sharply.
15300 由于诈骗行为特征、号码类型等与正常业务具有极高相似性,传统基于统计的电信欺诈检测方法难于筛选。 Traditional detection methods are mainly based on data mining and statistical learning of history data. However, due to the high similarity between fraud behavior and normal business, traditional statistical methods are difficult to screen.
15301 提出将用户通信关系转换为一组拓扑特征,建立通信社交有向图,将具有统计特征的顶点表示用户,具有关系特征的边表示他们之间的活动。 This paper proposes to transform user communi-cation relationship into a set of topological features and establish communication social directed graph, where vertices with statistical characteristics represent users and edges with relational characteristics represent activities between them.
15302 在通信社交图基础上,通过图卷积模块捕获用户的通信行为规律和通信社交关系特征,通过池化读出机制聚合通信社交网络的潜在特征,以识别电信欺诈行为。 On the basis of the commu-nication social graph, the potential characteristics of the communication social network are learned through the graph neural network,and the information characteristics of multiple nodes are aggregated through pooling readout mechanism, in order to identify the tele-com fraud users.
15303 真实通信历史数据验证表明了该方法的有效性。 The validation of real communication history data shows the effectiveness of this method.
15304 随着信息技术的发展,人脸识别在支付、工作和安防系统中应用的越来越多。 With the development of information technology, face recognition is used more and more in payment, work and security system.