ID 原文 译文
18475 实验结果表明，与其它机器学习算法相比，随机森林回归算法在CPU密集型基准测试，内存密集型基准测试和网络密集型基准测试上针对检查点性能的预测具有误差低，准确率高和运行高效的优点。 Compared with other machinelearning algorithms, the experimental results illustrat that the Random Forest (RF) has lower errors, higheraccuracy and faster execution on CPU intensive benchmark, memory intensive benchmark and networkintensive benchmark.
18476 遮挡是行人检测任务中导致漏检发生的主要原因之一，对检测器性能造成了不利影响。 Pedestrian detector performance is damaged because occlusion often leads to missed detection.
18477 为了增强检测器对于遮挡行人目标的检测能力，该文提出一种基于特征引导注意机制的单级行人检测方法。 In order to improve the detector's ability to detect pedestrian, a single-stage detector based on feature-guided attention mechanism is proposed.
18478 首先，设计一种特征引导注意模块，在保持特征通道间的关联性的同时保留了特征图的空间信息，引导模型关注遮挡目标可视区域； Firstly, a feature attention module is designed, which preserves theassociation between the feature channels while retaining spatial information, and guides the model to focus onvisible region.
18479 然后，通过注意模块融合浅层和深层特征，从而提取到行人的高层语义特征； Secondly, the attention module is used to fuse shallow and deep features, then high-levelsemantic features of pedestrians are extracted.
18480 最后，将行人检测作为一种高层语义特征检测问题，通过激活图的形式预测得到行人位置和尺度，并生成最终的预测边界框，避免了基于先验框的预测方式所带来的额外参数设置。 Finally, pedestrian detection is treated as a high-level semanticfeature detection problem. Pedestrian location and scale are obtained through heat map prediction, then thefinal prediction bounding box is generated.
18481 所提方法在CityPersons数据集上进行了测试，并在Caltech数据集上进行了跨数据集实验。 This way, the proposed method avoids the extra parameter settings of the traditional anchor-based method.
18482 结果表明该方法对于遮挡目标检测准确度优于其他对比算法。 Experiments show that the proposed method is superior to other comparison algorithms for the accuracy of occlusion target detection on CityPersons and Caltech pedestriandatabase.
18483 同时该方法实现了较快的检测速度，取得了检测准确度和速度的平衡。 At the same time, the proposed method achieves a faster detection speed and a better balance between detection accuracy and speed.
18484 Hilbert曲线是高维降到1维的重要方法，具有较好的空间聚集和空间连续性，在地理信息系统、空间数据库、信息检索等方面有广泛的应用。 Hilbert curve is an important method for high-dimensional reduction to one-dimensional. It has goodcharacteristics of spatial aggregation and spatial continuity and is widely used in geographic informationsystem, spatial databases and information retrieval.