ID	原文	译文
56578	本文研究了如何在基于会话的推荐系统中对用户兴趣进行建模.	This paper studies how to model user preferences in session-basedrecommendation systems.
56579	现有的工作或者假设会话之间相互独立,忽略了历史会话中包含的长期用户兴趣信息;	Existing studies have either assumed that sessions are independent from each otherand ignore long-term information from historical sessions, or treat the user’s short-term preferences in a sessionas static, which cannot fully characterize user behavior in practical scenarios.
56580	或者将用户在一个会话中的短期兴趣视为静态不变.这两者都无法充分刻画实际场景中的用户兴趣和行为.	Thus, we propose the recurrentmemory network (RMN), which is an RNN-based framework that unifies the users’ long-term and short-termpreferences in session-based recommendation.
56581	我们提出了循环记忆网络RMN,一种刻画了用户长期和短期兴趣的基于会话的推荐系统.	The key component of the proposed RMN is preference memory,which stores a user’s long-term interests.
56582	RMN基于循环神经网络模型,其核心部分是一个储存了用户长期偏好的兴趣记忆模块.	In addition, in the RMN, we design an intra-session memory readerand inter-session memory writer to facilitate explicit characterization of short-term (i. e.
56583	另外,我们在RMN中设计了一个会话内的记忆读取单元和一个会话间的记忆写入单元,这两个单元分别用于刻画短期(即一个会话内)的用户兴趣波动和长期(即跨越多个会话)的用户兴趣转移.	, within a session) userpreferences variation and long-term (i. e. , cross-session) user preference transfer, respectively.
56584	我们在真实的电影推荐和职位推荐数据集上进行了实验,实验结果表明RMN相比于现有方法而言取得了显著的性能提升.	The results obtainedin extensive experiments on real-world datasets for movie and job recommendations demonstrate that the proposedRMN achieves substantial gains over state-of-the-art baselines.
56585	高精度实时状态估计是无人机安全飞行及执行各种任务的首要条件.多传感器(如视觉、惯性测量单元(IMU)和GPS等)融合可提高状态估计精度,并实现信息冗余,当其中某些传感器出现故障时,仍具有较好的鲁棒性.	Accurate and real-time state estimation is the first step to realize safe flight and operation of un?manned aerial vehicles (UAVs). Multi-sensor fusion, e. g. , vision, IMU, and GPS, can improve the accuracy ofstate estimation and even make it work when some sensor is unavailable.
56586	因此,本文提出结合滤波与优化的无人机多传感器融合方法,从而得到局部高精度、全局无漂移的状态估计.	Thus, this paper proposes a multi-sensorfusion method based on the combination of filtering and optimization to achieve locally accurate and globallydrift-free state estimation.
56587	该方法主要分为卡尔曼(Kalman)滤波和全局优化两部分.	The proposed method has two components, i. e. , the Kalman filter and global opti?mization.