LIBPMK: A Pyramid Match Toolkit

About | Users | Downloads | Extensions (new!) | Documentation | FAQ | Links | Contact

Latest version: 2.3 (ChangeLog)

About LIBPMK

LIBPMK is a C++ implementation of Grauman and Darrell's Pyramid Match algorithm. This toolkit provides a flexible framework with which you can quickly match sets of image features and run experiments. LIBPMK has a wide range of features, including:

Built-in k-means and hierarchical clustering
Dealing with data sets too large to fit in memory
Building histograms and multi-resolution histograms
Quickly performing pyramid matches
Training SVMs and running experiments with them*

This toolkit is currently being actively maintained; please check back often for updates.

LIBPMK implements the algorithms described in the following papers (Show BibTeX entries):

@inproceedings{grauman-darrell-iccv2005,
  author    = {K. Grauman and T. Darrell},
  title     = {The Pyramid Match Kernel: Discriminative Classification with Sets of Image Features},
  booktitle = {IEEE International Conference on Computer Vision},
  year      = {2005},
  address   = {Beijing, China},
  month     = {October},
}

@inproceedings{grauman-darrell-nips2007,
  author    = {K. Grauman and T. Darrell},
  title     = {Approximate Correspondences in High Dimensions},
  booktitle = {Advances in Neural Information Processing Systems 19},
  editor    = {B. Scholkopf and J.C. Platt and T. Hofmann},
  publisher = {MIT Press},
  address   = {Cambridge, MA},
  year      = {2007},
}

K. Grauman and T. Darrell. The Pyramid Match Kernel: Discriminative Classification with Sets of Image Features. In Proceedings of the IEEE International Conference on Computer Vision (ICCV), Beijing, China, October 2005.
K. Grauman and T. Darrell. Approximate Correspondences in High Dimensions. In Proceedings of Advances in Neural Information Processing Systems 19 (NIPS), 2007.

* This module of the software package includes a version of LIBSVM which handles the running of SVM experiments. For details, please see:

Chih-Chung Chang and Chih-Jen Lin, LIBSVM: a library for support vector machines, 2001. Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm.

When using this code, please cite LIBPMK as follows:

@techreport{libpmk,
  author      = {John J. Lee},
  institution = {MIT Computer Science and Artificial Intelligence Laboratory},
  month       = {April},
  number      = {MIT-CSAIL-TR-2008-17},
  title       = {LIBPMK: A Pyramid Match Toolkit},
  year        = {2008},
  url         = {http://hdl.handle.net/1721.1/41070}
}

Plagiarism warning (2008-02-03)

It recently came to my attention that LIBPMK was plagiarized and posted at www.pudn.com as part of a user's "application" for premium membership on that website. If you found this home page after downloading code from www.pudn.com, please be aware that it possibly infringes on the copyrights of other people whose code is included in this package as well. Please do not download any code from www.pudn.com. More details

www.pudn.com appears to be a database of code. In order to gain access to it, users must either upload 5 pieces of their own source code, or pay $200 USD. It is likely that the user who uploaded LIBPMK to this web site had no interest in using LIBPMK, but rather just wanted access to a large repository of other (possibly plagiarized) code. Unfortunately, this now means that other users are now paying to access code that is freely available to researchers, and possibly using it without regard to the license terms that strictly forbid any non-research use.

LIBPMK and support is provided as a service to the computer vision community. Please do not plagiarize LIBPMK.

Projects that use LIBPMK

Xiaofeng Ren and Matthai Philipose
Egocentric Recognition of Handled Objects: Benchmark and Analysis, CVPR Egocentric Vision Workshop 2009.
Tom Yeh, John J. Lee, and Trevor Darrell
Fast Concurrent Object Localization and Recognition, CVPR 2009.
Haiqiang Zuo, Weiming Hu, Ou Wu, Yunfei Chen, and Guan Luo
Detecting Image Spam Using Local Invariant Features and Pyramid Match Kernel, WWW2009.
Siyao Fu, Zengguang Hou, Zize Liang, Qi Zuo, and Min Tan
Multiple Kernel Learning from Sets of Partially Matching Image Features, UKACC Control 2008.
Tingxin Yan, Deepak Ganesan, and R. Manmatha
Distributed Image Search in Camera Sensor Networks, ACM SenSys 2008.
Shuiwang Ji, Liang Sun, Rong Jin, Sudhir Kumar, and Jieping Ye
Automated Annotation of Drosophila Gene Expression Patterns Using a Controlled Vocabulary, Bioinformatics 2008.
Tom Yeh, John J. Lee, and Trevor Darrell
Photo-based Question Answering, ACM Multimedia 2008.
C. Mario Christoudias, Raquel Urtasun, and Trevor Darrell
Unsupervised Feature Selection via Distributed Coding for Multi-view Object Recognition, CVPR 2008.
Ashish Kapoor, Pradeep Shenoy, Desney Tan
Combining Brain Computer Interfaces with Vision for Object Categorization, CVPR 2008.
Tom Yeh, John J. Lee, and Trevor Darrell
Scalable Classifiers for Internet Vision Tasks, CVPR Internet Vision Workshop 2008.
Kate Saenko, Trevor Darrell
Object Category Recognition Using Probabilistic Fusion of Speech and Image Classifiers, MLMI 2007.
Michael Oltmans
Envisioning Sketch Recognition: A Local Feature Based Approach to Recognizing Informal Sketches, Ph.D. thesis (2007).
Tom Yeh, John J. Lee, and Trevor Darrell
Adaptive Vocabulary Forests for Dynamic Indexing and Categry Learning, ICCV 2007.

This list was made by searching Google for "libpmk"-- if you would like to link to your project from here, please contact me!

Downloads

Source code

Download the latest version (2.3, released 2009-01-21): libpmk-2.3.tar.gz

Older versions are available at http://people.csail.mit.edu/jjl/libpmk/download.

Recent changes (full ChangeLog here):

Fix all compilation problems related to gcc 4.3.

Example code and data

ETH-80 database

Extensions

LIBPMK is extensible and can be used for a variety of tasks. Below are some extension libraries I have written for LIBPMK. They include documentation and the full C++ source code. Each of these packages has a library component and a "tools" component, which shows examples of using the library. If you are interested in just using the code rather than writing your own applications using this library, the tools may be all you need and you will not have to write any code. Please see the included README files for details.

Feature extraction: libpmk_features.tar.gz (requires libpmk-2.2 or above)
Spatial pyramid match of Lazebnik et al.: libpmk_spatial.tar.gz (requires libpmk-2.2 or above)
Implicit shape model of Leibe et al.: libpmk_ism.tar.gz (requires libpmk-2.1 or above)

Documentation

Tutorial: How to install, use, and write new code using libpmk. Includes a FAQ that addresses speed and performance issues.
Version 2.x class reference: Details, code specifications, and class hierarchy diagrams.
Version 1.x class reference: For those using libpmk-1.x.

Links

Pyramid Match project page: http://www.cs.utexas.edu/~grauman/research/projects/pmk/pmk_projectpage.htm
LIBSVM home page: http://www.csie.ntu.edu.tw/~cjlin/libsvm/

Contact

If you have any questions, suggestions, or bug reports about this implementation, please contact John Lee (jjl at csail dot mit dot edu).

To recieve updates about libpmk, please join the extremely low-volume (around once every few months) mailing list.