MMoFusion: Multi-modal Co-Speech Motion Generation with Diffusion Model.
Sen WangJiangning ZhangWeijian CaoXiaobin HuMoran LiXiaozhong JiXin TanMengtian LiZhifeng XieChengjie WangLizhuang MaPublished in: CoRR (2024)
Keyphrases
- multi modal
- diffusion model
- audio visual
- humanoid robot
- anisotropic diffusion
- information diffusion
- diffusion process
- motion analysis
- motion estimation
- multi modality
- motion model
- optical flow
- cross modal
- diffusion tensor
- moving objects
- motion segmentation
- image sequences
- high dimensional
- motion field
- steady state
- image analysis
- three dimensional
- uni modal
- visual cues
- medical images
- higher order
- video search
- multiple modalities