Generating Human Motion from Textual Descriptions with Discrete Representations.
Jianrong ZhangYangsong ZhangXiaodong CunYong ZhangHongwei ZhaoHongtao LuXi ShenShan YingPublished in: CVPR (2023)
Keyphrases
- human motion
- textual descriptions
- human body
- motion capture
- image sequences
- video sequences
- spatio temporal
- motion recognition
- web images
- metadata
- motion capture data
- higher level
- semantic information
- machine learning
- multi modal
- relevance feedback
- semantic concepts
- keywords
- face recognition
- multimedia
- image processing