Neural Marionette: Unsupervised Learning of Motion Skeleton and Latent Dynamics from Volumetric Video
Published in AAAI Conference on Artifitial Intelligence, 2022, Oral
Jinseok Bae, Hojun Jang, Cheol-Hui Min, Hyungun Choi, and Young Min Kim
This work is to extract skeletal structure from volumetric observations and to learn motion dynamics from the detected skeletal motions in a fully unsupervised manner.
@inproceedings{bae2022neural,
title = {Neural marionette: Unsupervised learning of motion skeleton and latent dynamics from volumetric video},
author = {Bae, Jinseok and Jang, Hojun and Min, Cheol-Hui and Choi, Hyungun and Kim, Young Min},
booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
volume = {36},
number = {1},
pages = {86--94},
year = {2022},
}