Code release for sparselet release 1
Switch branches/tags
Nothing to show
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Failed to load latest commit information.
VOC2007 hos: initial commit Jun 16, 2014
bin hos dirs Jul 3, 2014
data hos: initial commit Jun 16, 2014
features hos: initial commit Jun 16, 2014
gdetect hos dirs Jul 3, 2014
model hos: initial commit Jun 16, 2014
sparselets hos dirs Jul 3, 2014
test hos dirs Jul 3, 2014
utils hos: initial commit Jun 16, 2014
vis hos: initial commit Jun 16, 2014
000313.jpg hos: initial commit Jun 16, 2014
000358.jpg hos: initial commit Jun 16, 2014
001998.jpg hos: initial commit Jun 16, 2014
004637.jpg hos: initial commit Jun 16, 2014
LICENSE hos Jul 3, 2014
README.md hos Jul 3, 2014
compile.m hos Jul 3, 2014
convolution_data.mat hos: initial commit Jun 16, 2014
demo_detection.m hos: initial commit Jun 16, 2014
demo_saved_feb18.m hos: initial commit Jun 16, 2014
startup.m hos Jul 3, 2014
voc_config.m hos: initial commit Jun 16, 2014

README.md

README for sparselet code

Introduction

Citing sparselets

If you find sparselet detection code useful in your research, please cite:

@inproceedings{Song-TPAMI2014,
	title = "Generalized Sparselet Models for Real-Time Multiclass Object Recognition",
	booktitle = "IEEE Transactions on Pattern Analysis and Machine Intelligence",
	year = "2014",
	author = "Hyun Oh Song and Ross Girshick and Stefan Zickler and Christopher Geyer and Pedro Felzenszwalb and Trevor Darrell",
}

@inproceedings{Song-ICML2013,
	title = "Discriminatively Activated Sparselets",
	booktitle = "International Conference on Machine Learning (ICML)",
	year = "2013", 
	author = "Ross Girshick and Hyun Oh Song and Trevor Darrell",
}

@inproceedings {Song-ECCV2012,
	title = "Sparselet Models for Efficient Multiclass Object Detection",
	booktitle = "European Conference on Computer Vision (ECCV)",
	year = "2012",
	author = "Hyun Oh Song and Stefan Zickler and Tim Althoff and Ross Girshick and Mario Fritz and Christopher Geyer and Pedro Felzenszwalb and Trevor Darrell",
}

License

Sparselet is released under the Simplified BSD License (refer to the LICENSE file for details).

System Requirements

Install instructions

  1. Download and install Intel® C++ Composer XE from the link above.
  2. Unpack the sparselet code.
  3. Download and install SPAMS toolbox in the same directory level as in the sparselet code.
  4. On a terminal run $python sparselets/compile_blas_singleTH_MAC.py (for OS X) or $python sparselets/compile_blas_singleTH.py (for Linux)
  5. Start matlab.
  6. Run the 'compile' function to compile the helper functions. (you may need to edit compile.m to use a different convolution routine depending on your system)
  7. Use 'demo_detection' code for a demo usage of the sparselet code for multiclass object detection.