A Caltech Library Service

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

Hall, David C. and Perona, Pietro (2014) From Categories to Individuals in Real Time — A Unified Boosting Approach. In: CVPR 2014, June 23-28, 2014, Columbus, OH. (Submitted)

PDF - Submitted Version
See Usage Policy.


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:Conference or Workshop Item (Paper)
Related URLs:
URLURL TypeDescription Website website
Perona, Pietro0000-0002-7583-5809
Additional Information: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
ARO/JPL-NASA StennisNAS7.03001
Record Number:CaltechAUTHORS:20140506-142707012
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:45540
Deposited By: David Hall
Deposited On:06 May 2014 23:16
Last Modified:03 Oct 2019 06:32

Repository Staff Only: item control page