A5014854403- Human Pose and Action Recognition
- Human Motion and Animation
- Advanced Neural Network Applications
- Social Robot Interaction and HRI
- 3D Shape Modeling and Analysis
- Muscle activation and electromyography studies
- Video Analysis and Summarization
- Parkinson's Disease Mechanisms and Treatments
- Radiomics and Machine Learning in Medical Imaging
- Persona Design and Applications
- Advanced Sensor and Energy Harvesting Materials
- Technology Use by Older Adults
- Medical Image Segmentation Techniques
- Voice and Speech Disorders
- Neuroscience and Neural Engineering
University of Chinese Academy of Sciences
2021-2024
Group Sense (China)
2023-2024
The Sense Innovation and Research Center
2024
Synthetic data has emerged as a promising source for 3D human research it offers low-cost access to large-scale datasets. To advance the diversity and annotation quality of models, we introduce new synthetic dataset, SynBody, with three appealing features: 1) clothed parametric model that can generate diverse range subjects; 2) layered representation naturally high-quality annotations support multiple tasks; 3) scalable system producing realistic facilitate real-world tasks. The dataset...
Generating natural human motion from a story has the potential to transform landscape of animation, gaming, and film industries. A new challenging task, Story-to-Motion, arises when characters are required move various locations perform specific motions based on long text description. This task demands fusion low-level control (trajectories) high-level (motion semantics). Previous works in character text-to-motion have addressed related aspects, yet comprehensive solution remains elusive:...
Although the needle Electromyography (EMG) is an efficient means for Amyotrophic Lateral Sclerosis (ALS) diagnosis, proper selection of muscles with high sensitivity important issue in clinical application. In this paper, we propose a new deep learning method called Wavelet-based Multi-branch Convolutional Neural Network (WM-CNN) cross-individual ALS disease identification. The proposed uses multi-branch network as framework to learn relationship among EMG samples recording, which each...
Synthetic data has emerged as a promising source for 3D human research it offers low-cost access to large-scale datasets. To advance the diversity and annotation quality of models, we introduce new synthetic dataset, SynBody, with three appealing features: 1) clothed parametric model that can generate diverse range subjects; 2) layered representation naturally high-quality annotations support multiple tasks; 3) scalable system producing realistic facilitate real-world tasks. The dataset...
Generating natural human motion from a story has the potential to transform landscape of animation, gaming, and film industries. A new challenging task, Story-to-Motion, arises when characters are required move various locations perform specific motions based on long text description. This task demands fusion low-level control (trajectories) high-level (motion semantics). Previous works in character text-to-motion have addressed related aspects, yet comprehensive solution remains elusive:...
In this work, we present Digital Life Project, a framework utilizing language as the universal medium to build autonomous 3D characters, who are capable of engaging in social interactions and expressing with articulated body motions, thereby simulating life digital environment. Our comprises two primary components: 1) SocioMind: meticulously crafted brain that models personalities systematic few-shot exemplars, incorporates reflection process based on psychology principles, emulates autonomy...