A Caltech Library Service

Hierarchical Cascade of Classifiers for Efficient Poselet Evaluation

Chen, Bo and Perona, Pietro and Bourdev, Lubomir (2014) Hierarchical Cascade of Classifiers for Efficient Poselet Evaluation. In: Proceedings of the British Machine Vision Conference 2014. BMVA Press , Durham, UK, Art. No. 96. ISBN 1901725529.

[img] PDF - Published Version
See Usage Policy.


Use this Persistent URL to link to this item:


Poselets have been used in a variety of computer vision tasks, such as detection, segmentation, action classification, pose estimation and action recognition, often achieving state-of-the-art performance. Poselet evaluation, however, is computationally intensive as it involves running thousands of scanning window classifiers. We present an algorithm for training a hierarchical cascade of part-based detectors and apply it to speed up poselet evaluation. Our cascade hierarchy leverages common components shared across poselets. We generate a family of cascade hierarchies, including trees that grow logarithmically on the number of poselet classifiers. Our algorithm, under some reasonable assumptions, finds the optimal tree structure that maximizes speed for a given target detection rate. We test our system on the PASCAL dataset and show an order of magnitude speedup at less than 1% loss in AP.

Item Type:Book Section
Related URLs:
URLURL TypeDescription
Chen, Bo0000-0001-5566-7361
Perona, Pietro0000-0002-7583-5809
Additional Information:© 2014. The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms.
Record Number:CaltechAUTHORS:20190327-125836326
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:94218
Deposited By: George Porter
Deposited On:27 Mar 2019 20:35
Last Modified:03 Oct 2019 21:01

Repository Staff Only: item control page