Yu Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Yu Chen has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Congyi Wang
Xmov, Shanghai 200030, China
1 shared publication - Hujun Bao
State Key Lab of CAD&CG Zhejiang University
1 shared publication - Jinxiang Chai
Xmov, Shanghai 200030, China
1 shared publication - Shuaiying Hou
State Key Lab of CADCG, Zhejiang University, Hangzhou 310058, China
1 shared publication - Weiwei Xu
State Key Lab of CAD and CG, Zhejiang University, Zhejiang, China
1 shared publication - Wenlin Zhuang
Southeast University
1 shared publication
Latest Publications
- Open Access
- 1 February 2024
- Published by Tsinghua University Press in Computational Visual Media
- Vol. 10 (1) , 45-59
A causal convolutional neural network for multi-subject motion modeling and generation
Inspired by the success of WaveNet in multi-subject speech synthesis, we propose a novel neural network based on causal convolutions for multi-subject motion modeling and generation. The network can capture the intrinsic characteristics of the motion of different subjects, such as the influence of skeleton scale variation on motion style. Moreover, after fine-tuning the network using a small motion dataset for a novel skeleton that is not included in the training dataset, it is able to synthesize high-quality motions with a personalized style for the novel skeleton. The experimental results demonstrate that our network can model the intrinsic characteristics of motions well and can be applied to various motion modeling and synthesis tasks.
- 1 February 2024
- Published by Tsinghua University Press in Computational Visual Media
- Vol. 10 (1) , 45-59
Open AccessA causal convolutional neural network for multi-subject motion modeling and generation
Inspired by the success of WaveNet in multi-subject speech synthesis, we propose a novel neural network based on causal convolutions for multi-subject motion modeling and generation. The network can capture the intrinsic characteristics of the motion of different subjects, such as the influence of skeleton scale variation on motion style. Moreover, after fine-tuning the network using a small motion dataset for a novel skeleton that is not included in the training dataset, it is able to synthesize high-quality motions with a personalized style for the novel skeleton. The experimental results demonstrate that our network can model the intrinsic characteristics of motions well and can be applied to various motion modeling and synthesis tasks.