GHOST: Grounded Human Motion Generation with Open Vocabulary Scene-and-Text Contexts

Author: 
Z. Milacski, K. Niinuma, R. Kawamura, F. de la Torre, L. Jeni
Image publication: 
Published by: 
IEEE/CVF Winter Conference on Applications of Computer Vision, 2025
Link: 

http://humansensing.cs.cmu.edu/node/601#overlay-context=node/616