Long-Term Human Motion Prediction by Modeling Motion Context and Enhancing Motion Dynamic
arXiv:1805.02513
Abstract
Human motion prediction aims at generating future frames of human motion based on an observed sequence of skeletons. Recent methods employ the latest hidden states of a recurrent neural network (RNN) to encode the historical skeletons, which can only address short-term prediction. In this work, we propose a motion context modeling by summarizing the historical human motion with respect to the current prediction. A modified highway unit (MHU) is proposed for efficiently eliminating motionless joints and estimating next pose given the motion context. Furthermore, we enhance the motion dynamic by minimizing the gram matrix loss for long-term motion prediction. Experimental results show that the proposed model can promisingly forecast the human future movements, which yields superior performances over related state-of-the-art approaches. Moreover, specifying the motion context with the activity labels enables our model to perform human motion transfer.
arXiv commentAccepted by IJCAI 2018
References in corpus (1)
Cited by in corpus (12)
- Robust Motion In-betweening
- Pedestrian Models for Autonomous Driving Part I: Low-Level Models, from Sensing to Tracking
- Investigating Pose Representations and Motion Contexts Modeling for 3D Motion Prediction
- A Survey on Deep Learning for Skeleton-Based Human Animation
- PVRED: A Position-Velocity Recurrent Encoder-Decoder for Human Motion Prediction
- Predicting Long-Term Skeletal Motions by a Spatio-Temporal Hierarchical Recurrent Network
- We are More than Our Joints: Predicting how 3D Bodies Move
- DynaNet: Neural Kalman Dynamical Model for Motion Estimation and Prediction
- PISEP^2: Pseudo Image Sequence Evolution based 3D Pose Prediction
- 3D Pose Estimation and Future Motion Prediction from 2D Images
- Adversarial Refinement Network for Human Motion Prediction
- Learning Multiscale Correlations for Human Motion Prediction