A Caltech Library Service

From Categories to Individuals in Real Time -- A Unified Boosting Approach

Hall, David and Perona, Pietro (2014) From Categories to Individuals in Real Time -- A Unified Boosting Approach. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE , Piscataway, NJ, pp. 176-183. ISBN 978-1-4799-5117-8.

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item:


A method for online, real-time learning of individual-object detectors is presented. Starting with a pre-trained boosted category detector, an individual-object detector is trained with near-zero computational cost. The individual detector is obtained by using the same feature cascade as the category detector along with elementary manipulations of the thresholds of the weak classifiers. This is ideal for online operation on a video stream or for interactive learning. Applications addressed by this technique are reidentification and individual tracking. Experiments on four challenging pedestrian and face datasets indicate that it is indeed possible to learn identity classifiers in real-time, besides being faster-trained, our classifier has better detection rates than previous methods on two of the datasets.

Item Type:Book Section
Related URLs:
URLURL TypeDescription DOIArticle
Perona, Pietro0000-0002-7583-5809
Additional Information:© 2014 IEEE. This work is funded by the ARO/JPL-NASA Stennis grant NAS7.03001 and the ONR MURI Grant N00014-10-1-0933.
Funding AgencyGrant Number
Office of Naval Research (ONR)N00014-10-1-0933
Army Research Office (ARO)UNSPECIFIED
Record Number:CaltechAUTHORS:20151023-144919676
Persistent URL:
Official Citation:Hall, D.; Perona, P., "From Categories to Individuals in Real Time -- A Unified Boosting Approach," in Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on , vol., no., pp.176-183, 23-28 June 2014 doi: 10.1109/CVPR.2014.30
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:61509
Deposited By: Tony Diaz
Deposited On:26 Oct 2015 20:50
Last Modified:03 Oct 2019 09:08

Repository Staff Only: item control page