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 = {}}
Downloads: 0
{"_id":"X6uT6EZSRpLZqqP7a","bibbaseid":"xu-liu-sun-murphy-freeman-tenenbaum-wu-unsuperviseddiscoveryofpartsstructureanddynamics-2019","authorIDs":[],"author_short":["Xu, Z.","Liu, Z.","Sun, C.","Murphy, K.","Freeman, W. T","Tenenbaum, J. B","Wu, J."],"bibdata":{"bibtype":"article","type":"article","author":[{"propositions":[],"lastnames":["Xu"],"firstnames":["Zhenjia"],"suffixes":[]},{"propositions":[],"lastnames":["Liu"],"firstnames":["Zhijian"],"suffixes":[]},{"propositions":[],"lastnames":["Sun"],"firstnames":["Chen"],"suffixes":[]},{"propositions":[],"lastnames":["Murphy"],"firstnames":["Kevin"],"suffixes":[]},{"propositions":[],"lastnames":["Freeman"],"firstnames":["William","T"],"suffixes":[]},{"propositions":[],"lastnames":["Tenenbaum"],"firstnames":["Joshua","B"],"suffixes":[]},{"propositions":[],"lastnames":["Wu"],"firstnames":["Jiajun"],"suffixes":[]}],"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":"","bibtex":"@Article{Xu2019a,\nauthor = {Xu, Zhenjia and Liu, Zhijian and Sun, Chen and Murphy, Kevin and Freeman, William T and Tenenbaum, Joshua B and Wu, Jiajun}, \ntitle = {Unsupervised Discovery of Parts, Structure, and Dynamics}, \njournal = {}, \nvolume = {}, \nnumber = {}, \npages = {}, \nyear = {2019}, \nabstract = {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.}, \nlocation = {}, \nkeywords = {}}\n\n\n","author_short":["Xu, Z.","Liu, Z.","Sun, C.","Murphy, K.","Freeman, W. T","Tenenbaum, J. B","Wu, J."],"key":"Xu2019a","id":"Xu2019a","bibbaseid":"xu-liu-sun-murphy-freeman-tenenbaum-wu-unsuperviseddiscoveryofpartsstructureanddynamics-2019","role":"author","urls":{},"downloads":0},"bibtype":"article","biburl":"https://gist.githubusercontent.com/stuhlmueller/a37ef2ef4f378ebcb73d249fe0f8377a/raw/6f96f6f779501bd9482896af3e4db4de88c35079/references.bib","creationDate":"2020-01-27T02:13:33.790Z","downloads":0,"keywords":[],"search_terms":["unsupervised","discovery","parts","structure","dynamics","xu","liu","sun","murphy","freeman","tenenbaum","wu"],"title":"Unsupervised Discovery of Parts, Structure, and Dynamics","year":2019,"dataSources":["hEoKh4ygEAWbAZ5iy"]}