ID	原文	译文
1243	最后融合联合域对齐，动态分布对齐和图适配，通过联合优化求解获得共享子空间表示。	Final-ly, the joint domain alignment, dynamic distributed alignment and graph adaptation are fused, and the joint optimization is u-tilized to obtain the feature representation.
1244	几个公共的跨域数据集上的大量实验结果表明了本文方法优于其它主流的迁移学习方法，验证了本文方法的有效性。	Extensive experiments on several common cross-domain datasets show that the proposed method outperforms the state-of-the-art on the tasks of transfer learning and the effectiveness of the proposed meth-od is verified.
1245	人们常用均匀背景、多目标和杂波边缘 3 种典型背景来衡量雷达目标检测器的性能，	The performance evaluation of radar target detector is often carried out in 3 typical environments of homo-geneous background, multiple targets situation and clutter edge.
1246	但在现有文献中缺乏量化秩(Rank Quantization，RQ)非参数检测器在杂波边缘中虚警概率的理论模型，缺乏 RQ 非参数检测器与经典的参量型检测器在杂波边缘中虚警控制能力的比较。	However, there is a lack of the mathematical model of thefalse alarm rate for the rank quantization (RQ)nonparametric detector at clutter boundaries, and lack of a comparison of theability for the RQ detector to control the rise of the false alarm rate at clutter edges to that of the conventional parametricCFAR schemes.
1247	本文给出了 RQ 检测器在杂波边缘中虚警概率的解析表达式，并比较了它与非相干积累 CA (Cell Averaging)，GO (Greatest Of)，OS (Ordered Statistic)恒虚警方法在杂波边缘中的虚警控制能力。	The analytic expression of the false alarm rate Pfafor the RQ nonparametric detector at clutter edges was de-rived in this paper, and the ability of the RQ nonparametric detector to control the rise of the false alarm rate at clutter edgeswas compared to that of the cell averaging (CA)CFAR, the greatest of (GO)CFAR and the ordered statistic (OS)CFARwith incoherent integration.
1248	可以看出，采用高秩量化门限的 RQ 检测器的虚警控制能力要优于低秩量化门限的情况，在瑞利分布杂波边缘情况下，RQ 检测器的虚警控制能力与非相干积累 OS 方法接近。	It is shown that a high rank quantization threshold results in a low rise of the false alarm rate atclutter edges, and the rise of the RQ nonparametric detector at clutter edges is close to that of the OS-CFAR with incoherent integration in the Rayleigh distributed clutter environment.
1249	但是当强杂波变为长拖尾分布的非高斯杂波时，非相干积累 CA，GO 和 OS 参量型检测方法的虚警概率产生了 3 个数量级以上的上升，且不能降回到原始设定的虚警概率。	However, when a non-Gaussian distributed clutter with a long tailmoves into the reference window, the rise of the CA-CFAR, the GO-CFAR and the OS-CFAR with incoherent integrationreaches a peak of more than 3 orders of magnitude, and can not return to the pre-designed Pfain Rayleigh noise situation.
1250	而 RQ 检测器显示出了非参量检测器的优势，即当杂波背景的分布类型发生变化后，它仍然可以保持虚警概率的恒定。	Butthe RQ nonparametric detector exhibits its inherent advantage in such situation, it can maintain constant false alarm rate eventhe distribution type of clutter changes to a different one.
1251	面对复杂场景下异常事件检测的准确率偏低的情况，本文提出一种基于深度学习的异常事件检测方法，并将此方法扩展为异常事件分类方法。	Faced with low accuracy of abnormal event detection in complex scenarios, this paper proposes an abnor-mal event detection based on deep learning in various public scenes and multiple types of anomalies, and the method has been extended to an abnormal event classification method.
1252	利用神经网络模型提取特征，将群体发散聚集事件，群体密集聚集事件，群体逃散事件和追赶事件这 4 种异常事件进行检测和分类。	The neural network model is used to extract features, and the fourkinds of abnormal events, such as group divergence aggregation events, group intensive aggregation events, group escape e-vents and catch-up events, are detected and classified.