Constructing Human Motion Manifold with Sequential Networks

• Published in: arXiv.org
• Main Authors: Jang, Deok-Kyeong, Lee, Sung-Hee
• Format: Paper Journal Article
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 29.05.2020
• Subjects: Computer Science - Graphics; Decoders; Human motion; Interpolation; Kinematics; Manifolds; Motion capture; Position errors; Random sampling; Recurrent neural networks; Regularization

This paper presents a novel recurrent neural network-based method to construct a latent motion manifold that can represent a wide range of human motions in a long sequence. We introduce several new components to increase the spatial and temporal coverage in motion space while retaining the details o...