A Caltech Library Service

Unsupervised learning of human motion models

Song, Yang and Goncalves, Luis and Perona, Pietro (2002) Unsupervised learning of human motion models. In: Advances in Neural Information Processing Systems. Advances in Neural Information Processing Systems . Vol.14. No.2. MIT Press , Cambridge, MA, pp. 1287-1294. ISBN 0-262-04208-8.

PDF - Published Version
See Usage Policy.


Use this Persistent URL to link to this item:


This paper presents an unsupervised learning algorithm that can derive the probabilistic dependence structure of parts of an object (a moving human body in our examples) automatically from unlabeled data. The distinguished part of this work is that it is based on unlabeled data, i.e., the training features include both useful foreground parts and background clutter and the correspondence between the parts and detected features are unknown. We use decomposable triangulated graphs to depict the probabilistic independence of parts, but the unsupervised technique is not limited to this type of graph. In the new approach, labeling of the data (part assignments) is taken as hidden variables and the EM algorithm is applied. A greedy algorithm is developed to select parts and to search for the optimal structure based on the differential entropy of these variables. The success of our algorithm is demonstrated by applying it to generate models of human motion automatically from unlabeled real image sequences.

Item Type:Book Section
Related URLs:
URLURL TypeDescription
Perona, Pietro0000-0002-7583-5809
Additional Information:Funded by the NSF Engineering Research Center for Neuromorphic Systems Engineering (CNSE) at Caltech (NSF9402726), and by an NSF National Young Investigator Award to PP (NSF9457618). We thank Charless Fowlkes for bringing the Chow and Liu’s paper to our attention. We thank Xiaolin Feng for providing the real image sequences.
Funding AgencyGrant Number
Center for Neuromorphic Systems Engineering, CaltechUNSPECIFIED
Series Name:Advances in Neural Information Processing Systems
Issue or Number:2
Record Number:CaltechAUTHORS:20140730-101719911
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:47619
Deposited By: Caroline Murphy
Deposited On:19 Aug 2014 21:00
Last Modified:26 Nov 2019 00:17

Repository Staff Only: item control page