A Caltech Library Service

Cascaded Pose Regression

Dollár, Piotr and Welinder, Peter and Perona, Pietro (2010) Cascaded Pose Regression. In: 2010 IEEE Conference on Computer Vision and Pattern Recognition. IEEE Conference on Computer Vision and Pattern Recognition . IEEE , New York, pp. 1078-1085. ISBN 978-1-4244-6984-0.

PDF - Published Version
See Usage Policy.


Use this Persistent URL to link to this item:


We present a fast and accurate algorithm for computing the 2D pose of objects in images called cascaded pose regression (CPR). CPR progressively refines a loosely specified initial guess, where each refinement is carried out by a different regressor. Each regressor performs simple image measurements that are dependent on the output of the previous regressors; the entire system is automatically learned from human annotated training examples. CPR is not restricted to rigid transformations: ‘pose’ is any parameterized variation of the object’s appearance such as the degrees of freedom of deformable and articulated objects. We compare CPR against both standard regression techniques and human performance (computed from redundant human annotations). Experiments on three diverse datasets (mice, faces, fish) suggest CPR is fast (2-3ms per pose estimate), accurate (approaching human performance), and easy to train from small amounts of labeled data.

Item Type:Book Section
Related URLs:
URLURL TypeDescription
Perona, Pietro0000-0002-7583-5809
Additional Information:© 2010 IEEE. Issue Date: 13-18 June 2010; Date of Current Version: 05 August 2010. We thank Dayu Lin and David Anderson for the mice data, support and motivation; and Konstantin Startchev and Jacob Engelmann for providing the fish data and helpful discussions. This work was supported by ONR MURI Grant #N00014-06-1-0734 and ONR/Evolution Grant #N00173- 09-C-4005. PD was supported by a Caltech Endowment Award #101240.
Funding AgencyGrant Number
Office of Naval Research (ONR)N00014-06-1-0734
Office of Naval Research (ONR)N00173-09-C-4005
Caltech Endowment Award101240
Other Numbering System:
Other Numbering System NameOther Numbering System ID
INSPEC Accession Number11500451
Series Name:IEEE Conference on Computer Vision and Pattern Recognition
Record Number:CaltechAUTHORS:20110401-112425406
Persistent URL:
Official Citation:Dollár, P.; Welinder, P.; Perona, P.; , "Cascaded pose regression," Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on , vol., no., pp.1078-1085, 13-18 June 2010 doi: 10.1109/CVPR.2010.5540094
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:23201
Deposited By: Jason Perez
Deposited On:04 Apr 2011 20:21
Last Modified:03 Oct 2019 02:44

Repository Staff Only: item control page