ID 原文 译文
17645 仿真结果表明，所提的算法可以满足异构任务的多样化计算需求，并在保证网络稳定性的前提下降低系统的平均时延。 Simulation results show that the proposed algorithm can meet the diverse computingneeds of heterogeneous tasks and reduce the average delay of the system while ensuring network stability.
17646 为减轻行人图片中的背景干扰，使网络着重于行人前景并且提高前景中人体部位的利用率，该文提出引入语义部位约束(SPC)的行人再识别网络。 In order to alleviate the background clutter in pedestrian images, and make the network focus onpedestrian foreground to improve the utilization of human body parts in the foreground. In this paper, a personre-identification network is proposed that introduces Semantic Part Constraint(SPC).
17647 在训练阶段，首先将行人图片同时输入主干网络和语义部位分割网络，分别得到行人特征图和部位分割图； Firstly, the pedestrian image is input into the backbone network and the semantic part segmentation network at the same time, and the pedestrian feature map and the part segmentation label are obtained respectively.
17648 然后，将部位分割图与行人特征图融合，得到语义部位特征； Secondly, the partsegmentation label and the pedestrian feature maps are merged to obtain the semantic part feature.
17649 接着，对行人特征图进行池化得到全局特征； Thirdly,the pedestrian feature map is obtained and the global average pooling is used to gain global features.
17650 最后，同时使用身份约束和语义部位约束训练网络。 Finally,the network is trained using both identity constraint and semantic part constraint.
17651 在测试阶段，由于语义部位约束使得全局特征拥有部位信息，因此测试时仅使用主干网络提取行人的全局信息即可。 Since the semantic partconstraint makes the global features obtain the part information, only the backbone network can be used toextract the features of the pedestrian during the test.
17652 在大规模公开数据集上的实验结果表明，语义部位约束能有效使得网络提高辨别行人身份的能力并且缩减推断网络的计算花费。 Experiments on large-scale datasets show that semanticpart constraints can effectively make the network improve the ability to identify pedestrians and reduce thecomputational cost of inferring networks.
17653 与现有方法比较，该文网络能更好地抵抗背景干扰，提高行人再识别性能。 Compared with the state of art, the proposed network can betterresist background clutter and improve person re-identification performance.
17654 全球卫星导航系统(GNSS)空间信号(SIS)质量直接影响了用户使用性能。 The Signal-In-Space (SIS) quality affects directly the user performance of Global Navigation SatelliteSystem (GNSS).