TED Expressive

TED Expressive is a recent English-based dataset for co-speech gesture generation. Different from TED Gesture dataset that only contains body skeletons, TED Expressive extracts 30 finger joints using ExPose for each frame to harvest diverse and detailed gesture representation.

Data and Resources

Cite this as

Longbin Ji, Pengfei Wei, Yi Ren, Jinglin Liu, Chen Zhang, Xiang Yin (2024). Dataset: TED Expressive. https://doi.org/10.57702/uz95i7cs

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2308.15016
Author Longbin Ji
More Authors
Pengfei Wei
Yi Ren
Jinglin Liu
Chen Zhang
Xiang Yin