Multi-level Motion Attention for Human Motion Prediction
Date
2021
Authors
Mao, Wei
Liu, Miaomiao
Salzmann, Mathieu
Li, Hongdong
Journal Title
Journal ISSN
Volume Title
Publisher
Springer
Abstract
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.
Description
Keywords
Human motion prediction, Motion attention, Deep learning
Citation
Collections
Source
International Journal of Computer Vision
Type
Journal article
Book Title
Entity type
Access Statement
License Rights
Restricted until
2099-12-31
Downloads
File
Description