Human motion prediction aims to automatically predict the future motion sequence based on an observed human motion sequence. In this paper, we propose a novel skip-attention encoder–decoder (SAED) framework to model human motion dependences in spatiotemporal space, by utilizing the encoder and decoder to encode the observed motions, and decode the predicted motions, respectively. Overall, this framework has two main insights. First, we design a new self-renewing ConvGRU as the unit of encoder and decoder to effectively capture temporal and spatial skeleton-motion dependencies. Second, we present a new skip-attention mechanism (SAM) to aggregate the motion information of all layers based on their importance. In experiments, quantitative and qualitative results on the Human3.6M and CMU motion capture datasets show the effectiveness of the proposed SAED compared with the related methods.

人体运动预测旨在根据观察到的人体运动序列自动预测未来的运动序列。在本文中，我们提出了一种新颖的跳过注意编码器 - 解码器（SAED）框架，通过利用编码器和解码器分别对观察到的运动进行编码和对预测的运动进行解码，来对时空空间中的人体运动依赖性进行建模。总的来说，这个框架有两个主要见解。首先，我们设计了一个新的自我更新的 ConvGRU 作为编码器和解码器的单元，以有效捕获时间和空间的骨架运动依赖性。其次，我们提出了一种新的跳过注意机制（SAM），根据它们的重要性聚合所有层的运动信息。在实验中，Human3 的定量和定性结果。