论文标题
在风车上倾斜：深度姿势估计的数据增强无助于阻塞
Tilting at windmills: Data augmentation for deep pose estimation does not help with occlusions
论文作者
论文摘要
闭塞会降低人姿势估计的性能。在本文中，我们介绍了目标关键和身体部位遮挡攻击。攻击的影响是对最佳性能方法的系统分析。此外，我们建议针对关键点和零件攻击的遮挡特定的数据增强技术。我们广泛的实验表明，人类姿势估计方法对遮挡不健壮，数据增强不能解决遮挡问题。
Occlusion degrades the performance of human pose estimation. In this paper, we introduce targeted keypoint and body part occlusion attacks. The effects of the attacks are systematically analyzed on the best performing methods. In addition, we propose occlusion specific data augmentation techniques against keypoint and part attacks. Our extensive experiments show that human pose estimation methods are not robust to occlusion and data augmentation does not solve the occlusion problems.
