Human motion prediction aims to forecast future human poses given a historical motion. Whether based on recurrent or feed-forward neural networks, existing learning based methods fail to model the observation that human motion tends to repeat itself, even for complex sports actions and cooking activities. Here, we introduce an attention based feed-forward network that explicitly leverages this observation. In particular, instead of modeling frame-wise attention via pose similarity, we propose to extract motion attention to capture the similarity between the current motion context and the historical motion sub-sequences. In this context, we study the use of different types of attention, computed at joint, body part, and full pose levels. Aggregating the relevant past motions and processing the result with a graph convolutional network allows us to effectively exploit motion patterns from the long-term history to predict the future poses. Our experiments on Human3.6M, AMASS and 3DPW validate the benefits of our approach for both periodical and non-periodical actions. Thanks to our attention model, it yields state-of-the-art results on all three datasets. Our code is available at https://github.com/wei-mao-2019/HisRepItself.

人体运动预测旨在根据历史运动预测未来的人体姿势。无论是基于循环神经网络还是前馈神经网络，现有的基于学习的方法都无法对人类运动倾向于重复自身的观察进行建模，即使对于复杂的运动动作和烹饪活动也是如此。在这里，我们引入了一个基于注意力的前馈网络，它明确地利用了这一观察结果。特别是，我们建议提取运动注意力，而不是通过姿势相似度对逐帧注意力进行建模捕捉当前运动上下文和历史运动子序列之间的相似性。在这种情况下，我们研究了在关节、身体部位和完整姿势级别计算的不同类型注意力的使用。聚合相关的过去运动并使用图形卷积网络处理结果，使我们能够有效地利用长期历史中的运动模式来预测未来的姿势。我们在 Human3.6M、AMASS 和 3DPW 上的实验验证了我们的方法对周期性和非周期性动作的好处。由于我们的注意力模型，它在所有三个数据集上都产生了最先进的结果。我们的代码可在 https://github.com/wei-mao-2019/HisRepItself 获得。