AttentiveFP 2020 Motivations 1、The gap between what these neural networks learn and what human beings can comprehend is growing 2、Graph-based representations take only the information concerning th
论文地址:AID: Pushing the Performance Boundary of Human Pose Estimation with Information Dropping Augmentation 论文总结 本文没有提出新的方法,主要是探索了信息丢失数据增强手段的应用中存在的问题,以及能带来的提升。 之前的论文要不就是没有使用信息丢失的数据增强手段,要不就是验证了信息