A Caltech Library Service

Unsupervised learning of human motion

Song, Yang and Goncalves, Luis and Perona, Pietro (2003) Unsupervised learning of human motion. IEEE Transactions on Pattern Analysis and Machine Intelligence, 25 (7). pp. 814-827. ISSN 0162-8828.

PDF - Published Version
See Usage Policy.


Use this Persistent URL to link to this item:


An unsupervised learning algorithm that can obtain a probabilistic model of an object composed of a collection of parts (a moving human body in our examples) automatically from unlabeled training data is presented. The training data include both useful "foreground" features as well as features that arise from irrelevant background clutter - the correspondence between parts and detected features is unknown. The joint probability density function of the parts is represented by a mixture of decomposable triangulated graphs which allow for fast detection. To learn the model structure as well as model parameters, an EM-like algorithm is developed where the labeling of the data (part assignments) is treated as hidden variables. The unsupervised learning technique is not limited to decomposable triangulated graphs. The efficiency and effectiveness of our algorithm is demonstrated by applying it to generate models of human motion automatically from unlabeled image sequences, and testing the learned models on a variety of sequences.

Item Type:Article
Related URLs:
URLURL TypeDescription
Perona, Pietro0000-0002-7583-5809
Additional Information:© 2003 IEEE. Reprinted with permission. Manuscript received 27 Sept. 2002; revised 2 Mar. 2003; accepted 17 Mar. 2003. [Posted online: 2003-06-20] Recommended for acceptance by V. Pavlovic. Part of the work in this paper was published in the Proceedings of IEEE Conference on Computer Vision and Pattern Recognition ’01 and NIPS ’01. This work was funded by the US National Science Foundation Engineering Research Center for Neuromorphic Systems Engineering (CNSE) at Caltech (NSF9402726), and an Office of Navy Research grant N00014-01-1-0890 under the MURI program. The authors would like to thank Charless Fowlkes for bringing the Chow and Liu paper to their attention.
Funding AgencyGrant Number
Center for Neuromorphic Systems Engineering, CaltechUNSPECIFIED
Office of Naval Research (ONR)N00014-01-1-0890
Subject Keywords:Unsupervised learning, human motion, decomposable triangulated graph, probabilistic models, greedy search, EM algorithm, mixture models
Issue or Number:7
Record Number:CaltechAUTHORS:SONieeetpami03
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:6503
Deposited By: Archive Administrator
Deposited On:11 Dec 2006
Last Modified:26 Nov 2019 00:16

Repository Staff Only: item control page