Unsupervised Discovery of Parts, Structure, and Dynamics. Xu, Z., Liu, Z., Sun, C., Murphy, K., Freeman, W. T, Tenenbaum, J. B, & Wu, J. , 2019. abstract bibtex Humans easily recognize object parts and their hierarchical structure by watching how they move; they can then predict how each part moves in the future. In this paper, we propose a novel formulation that simultaneously learns a hierarchical, disentangled object representation and a dynamics model for object parts from unlabeled videos. Our Parts, Structure, and Dynamics (PSD) model learns to, first, recognize the object parts via a layered image representation; second, predict hierarchy via a structural descriptor that composes low-level concepts into a hierarchical structure; and third, model the system dynamics by predicting the future. Experiments on multiple real and synthetic datasets demonstrate that our PSD model works well on all three tasks: segmenting object parts, building their hierarchical structure, and capturing their motion distributions.
@Article{Xu2019a,
author = {Xu, Zhenjia and Liu, Zhijian and Sun, Chen and Murphy, Kevin and Freeman, William T and Tenenbaum, Joshua B and Wu, Jiajun},
title = {Unsupervised Discovery of Parts, Structure, and Dynamics},
journal = {},
volume = {},
number = {},
pages = {},
year = {2019},
abstract = {Humans easily recognize object parts and their hierarchical structure by watching how they move; they can then predict how each part moves in the future. In this paper, we propose a novel formulation that simultaneously learns a hierarchical, disentangled object representation and a dynamics model for object parts from unlabeled videos. Our Parts, Structure, and Dynamics (PSD) model learns to, first, recognize the object parts via a layered image representation; second, predict hierarchy via a structural descriptor that composes low-level concepts into a hierarchical structure; and third, model the system dynamics by predicting the future. Experiments on multiple real and synthetic datasets demonstrate that our PSD model works well on all three tasks: segmenting object parts, building their hierarchical structure, and capturing their motion distributions.},
location = {},
keywords = {}}