Skip to content

Instantly share code, notes, and snippets.

@iacopomasi

iacopomasi/PAMs.md Secret

Created July 22, 2016 06:04
Show Gist options
  • Star 27 You must be signed in to star a gist
  • Fork 15 You must be signed in to fork a gist
  • Save iacopomasi/0c52aaa4ef778ad81b7b6f4ab860a237 to your computer and use it in GitHub Desktop.
Save iacopomasi/0c52aaa4ef778ad81b7b6f4ab860a237 to your computer and use it in GitHub Desktop.
Download ZIP
Webpage for the Pose-Aware Models for Face Recognition presented in CVPR 2016
Raw
PAMs.md

Pose-Aware Models

We provide the Pose-Aware CNN Models from the paper I. Masi, S. Rawls, G. Medioni, P. Natarajan "Pose-Aware Face Recognition in the Wild", in Proc. of CVPR 2016 [1] along with some more data.

In particular, we provide the following:

  1. PAMs CNN Models for AlexNet and VGGNet.
  2. Yaw estimates from our 3D pose estimation module on IJB-A [3].

You can try to generare your own rendered images using the code provided by [2].

Download Pose-Aware Models (PAMs)

Each CNN model is represented with the average image computed in the training set. For out-of-plane rotation, a 3D generic model is displayed to clarify that the alignment is 3D-aided but the CNN is trained only on RGB data.

Each model contains Caffe CNN parameters, a deploy file and the average face computed over the training set. Download the PAMs from the links below.

PAM 2D in-plane frontal

alt text [ AlexNet | VGGNet ]

PAM 2D in-plane profile

alt text [ AlexNet | VGGNet ]

PAM 3D out-of-plane frontal (0 degree)

alt text [ AlexNet | VGGNet ]

PAM 3D out-of-plane half-profile (-40 degree)

alt text [ AlexNet | VGGNet ]

PAM 3D out-of-plane full-profile (-75 degree)

alt text [ AlexNet | VGGNet ]

Yaw Estimates on IJB-A

Pose Variations IJB-A

We provide our own pose estimation in IJB-A [3] dataset in terms of yaw angles. The tar can be downloaded here:

Download the yaw estimation in IJB-A (MATLAB)

The tar contains the yaw angles and a main MATLAB file to see how to use the data. Each image maps to a yaw angle using the filename and subject id as a key to index the image.

The key is built as <subjectID>_<filename> removing the extension from the filename and replacing '/' with '-'.

E.g. 1673,img/8580.jpg becomes 1673_img-8580

Citation

Please cite our paper with the following bibtex if you use our PAMs or our dataset:

@INPROCEEDINGS{masi2016cvpr, 
    author={Iacopo Masi and Stephen Rawls and G{\'e}rard Medioni and Prem Natarajan}, 
    booktitle={CVPR}, 
    title={Pose-{A}ware {F}ace {R}ecognition in the {W}ild}, 
    year={2016}
    }

References

[1] I. Masi, S. Rawls, G. Medioni, P. Natarajan "Pose-Aware Face Recognition in the Wild", CVPR 2016

[2] T. Hassner, S. Harel, E. Paz and R. Enbar "Effective Face Frontalization in Unconstrained Images", CVPR 2015

[3] Brendan F. Klare, Ben Klein, Emma Taborsky, Austin Blanton, Jordan Cheney, Kristen Allen, Patrick Grother, Alan Mah, Anil K. Jain, "Pushing the Frontiers of Unconstrained Face Detection and Recognition: IARPA Janus Benchmark A", CVPR 2015

Changelog

  • July 2016, First Release

Disclaimer

The SOFTWARE PACKAGE provided in this page is provided "as is", without any guarantee made as to its suitability or fitness for any particular use. It may contain bugs, so use of this tool is at your own risk. We take no responsibility for any damage of any sort that may unintentionally be caused through its use.

Contacts

If you have any questions, drop an email to iacopo.masi@usc.edu and srawls@isi.edu or leave a message below with GitHub (log-in is needed).

@stereomatchingkiss
Copy link

Thanks for sharing the models. Are these models eligible for commercial use?

@matteosal
Copy link

What is the licensing information for these models?

@Mypathissional
Copy link

Mypathissional commented Jan 16, 2020 •
edited

Hey, can you comment on the licensing information and also it seems like the emails you have posted are not active?

Thanks

@iacopomasi
Copy link
Author

Hi @Mypathissional,
yes, the project is very old thus some email addresses may be outdated. Regarding the license, the new one is the following:

The Software is made available for academic or non-commercial purposes only. The license is for a copy of the program for an unlimited term. Individuals requesting a license for commercial use must pay for a commercial license.

USC Stevens Institute for Innovation 
University of Southern California 
1150 S. Olive Street, Suite 2300 
Los Angeles, CA 90115, USA 
ATTN: Accounting

DISCLAIMER. USC MAKES NO EXPRESS OR IMPLIED WARRANTIES, EITHER IN FACT OR BY OPERATION OF LAW, BY STATUTE OR OTHERWISE, AND USC SPECIFICALLY AND EXPRESSLY DISCLAIMS ANY EXPRESS OR IMPLIED WARRANTY OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, VALIDITY OF THE SOFTWARE OR ANY OTHER INTELLECTUAL PROPERTY RIGHTS OR NON-INFRINGEMENT OF THE INTELLECTUAL PROPERTY OR OTHER RIGHTS OF ANY THIRD PARTY. SOFTWARE IS MADE AVAILABLE AS-IS. LIMITATION OF LIABILITY. TO THE MAXIMUM EXTENT PERMITTED BY LAW, IN NO EVENT WILL USC BE LIABLE TO ANY USER OF THIS CODE FOR ANY INCIDENTAL, CONSEQUENTIAL, EXEMPLARY OR PUNITIVE DAMAGES OF ANY KIND, LOST GOODWILL, LOST PROFITS, LOST BUSINESS AND/OR ANY INDIRECT ECONOMIC DAMAGES WHATSOEVER, REGARDLESS OF WHETHER SUCH DAMAGES ARISE FROM CLAIMS BASED UPON CONTRACT, NEGLIGENCE, TORT (INCLUDING STRICT LIABILITY OR OTHER LEGAL THEORY), A BREACH OF ANY WARRANTY OR TERM OF THIS AGREEMENT, AND REGARDLESS OF WHETHER USC WAS ADVISED OR HAD REASON TO KNOW OF THE POSSIBILITY OF INCURRING SUCH DAMAGES IN ADVANCE.

For commercial license pricing and annual commercial update and support pricing, please contact:


Rakesh Pandit USC Stevens Institute for Innovation 
University of Southern California 
1150 S. Olive Street, Suite 2300
Los Angeles, CA 90115, USA 

Tel: +1 213-821-3552
Fax: +1 213-821-5001 
Email: rakeshvp@usc.edu and ccto: accounting@stevens.usc.edu

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment