Adaptive Locomotion of Soft Microrobots
Networked Control and Communication
Controller Learning using Bayesian Optimization
Event-based Wireless Control of Cyber-physical Systems
Model-based Reinforcement Learning for PID Control
Learning Probabilistic Dynamics Models
Gaussian Filtering as Variational Inference
Perceiving Systems
Publications
Website
The BEAT2 dataset [
] provides 60 hours of high-quality motion capture data in SMPL-X format together with audio of speakers and a wide range of emotions. BEAT2 enables training of models that infer full-body face and gestures from audio.
BEAT2 Dataset for Holistic Co-Speech Gesture Generation
] provides 60 hours of high-quality motion capture data in SMPL-X format together with audio of speakers and a wide range of emotions. BEAT2 enables training of models that infer full-body face and gestures from audio.
Publications
Perceiving Systems
Conference Paper
EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture Modeling
Liu, H., Zhu, Z., Becherini, G., Peng, Y., Su, M., Zhou, Y., Zhe, X., Iwamoto, N., Zheng, B., Black, M. J.
In IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), :1144-1154, CVPR, June 2024 (Published)
arXiv
project
dataset
code
gradio
colab
video
DOI
URL
BibTeX