OpenFace – a state-of-the art tool intended for facial landmark detection, head pose estimation, facial action unit recognition, and eye-gaze estimation.


OpenFace 2.2.0: a facial behavior analysis toolkit

Build Status Build status

Over the past few years, there has been an increased interest in automatic facial behavior analysis and understanding. We present OpenFace – a tool intended for computer vision and machine learning researchers, affective computing community and people interested in building interactive applications based on facial behavior analysis. OpenFace is the first toolkit capable of facial landmark detection, head pose estimation, facial action unit recognition, and eye-gaze estimation with available source code for both running and training the models. The computer vision algorithms which represent the core of OpenFace demonstrate state-of-the-art results in all of the above mentioned tasks. Furthermore, our tool is capable of real-time performance and is able to run from a simple webcam without any specialist hardware.

Multicomp logo

OpenFace was originally developed by Tadas Baltrušaitis in collaboration with CMU MultiComp Lab led by Prof. Louis-Philippe Morency. Some of the original algorithms were created while at Rainbow Group, Cambridge University. The OpenFace library is still actively developed at the CMU MultiComp Lab in collaboration with Tadas Baltršaitis. Special thanks to researcher who helped developing, implementing and testing the algorithms present in OpenFace: Amir Zadeh and Yao Chong Lim on work on the CE-CLM model and Erroll Wood for the gaze estimation work.


For instructions of how to install/compile/use the project please see WIKI


The system is capable of performing a number of facial analysis tasks:

  • Facial Landmark Detection

Sample facial landmark detection image

  • Facial Landmark and head pose tracking (links to YouTube videos)

Multiple Face Tracking Multiple Face Tracking

  • Facial Action Unit Recognition

  • Gaze tracking (image of it in action)

  • Facial Feature Extraction (aligned faces and HOG features)

Sample aligned face and HOG image


If you use any of the resources provided on this page in any of your publications we ask you to cite the following work and the work for a relevant submodule you used.

Overall system

OpenFace 2.0: Facial Behavior Analysis Toolkit Tadas Baltrušaitis, Amir Zadeh, Yao Chong Lim, and Louis-Philippe Morency, IEEE International Conference on Automatic Face and Gesture Recognition, 2018

Facial landmark detection and tracking

Convolutional experts constrained local model for facial landmark detection A. Zadeh, T. Baltrušaitis, and Louis-Philippe Morency. Computer Vision and Pattern Recognition Workshops, 2017

Constrained Local Neural Fields for robust facial landmark detection in the wild Tadas Baltrušaitis, Peter Robinson, and Louis-Philippe Morency. in IEEE Int. Conference on Computer Vision Workshops, 300 Faces in-the-Wild Challenge, 2013.

Eye gaze tracking

Rendering of Eyes for Eye-Shape Registration and Gaze Estimation Erroll Wood, Tadas Baltrušaitis, Xucong Zhang, Yusuke Sugano, Peter Robinson, and Andreas Bulling in IEEE International Conference on Computer Vision (ICCV), 2015

Facial Action Unit detection

Cross-dataset learning and person-specific normalisation for automatic Action Unit detection Tadas Baltrušaitis, Marwa Mahmoud, and Peter Robinson in Facial Expression Recognition and Analysis Challenge, IEEE International Conference on Automatic Face and Gesture Recognition, 2015

Commercial license

For inquiries about the commercial licensing of the OpenFace toolkit please visit

Final remarks

I did my best to make sure that the code runs out of the box but there are always issues and I would be grateful for your understanding that this is research code and a research project. If you encounter any problems/bugs/issues please contact me on github or by emailing me at [email protected] for any bug reports/questions/suggestions. I prefer questions and bug reports on github as that provides visibility to others who might be encountering same issues or who have the same questions.


Copyright can be found in the Copyright.txt

You have to respect dlib, OpenBLAS, and OpenCV licenses.

Furthermore you have to respect the licenses of the datasets used for model training -

  • integration openface in other projects

    integration openface in other projects


    Emotion detection is one of the tasks in my prj that i decided to do it by openface (thanks for lots of time saving). Then in second step i need the outputs of openface, so how can i call (or integrate) openface in my own prj? I'm going to use docker for implementing different modules

    other info: i'm using libfreenect2 on ubuntu 14.04 with c++ ,

    Thanks in advance

    opened by elahia 23
  • make error in ubuntu 14.04 instalation

    make error in ubuntu 14.04 instalation

    Hi, I checked in other issues, there was not such an error so i create a new one,

    i tried to install openface on my ubuntu 14,04 by running ./ and ./

    every thing goes well but in making time i got two errors (see attache please),

    So how can i fix it? Regards, screenshot from 2018-05-25 14 10 43

    opened by elahia 20
  • Qt5 cross platform gui

    Qt5 cross platform gui

    Builds on OSX with

    and run the binary openface-cross-platform-gui from within the build/bin directory. Adapt as needed for Windows or Linux (I might add another commit to build on linux as well).

    screen shot 2018-05-23 at 10 51 36 am
    opened by fxfactorial 20
  • compile for arm

    compile for arm

    Hello Tadas, I want to transplant Openface to ARM, I have cross compiled OpenCV, Boost and DLIB. But there is a problem with compiling TBB. Is there a way to replace TBB, or do not use TBB. Looking forward to your reply.

    opened by XHuaSheng 20
  • Android integration

    Android integration

    Hello ! I was thinking to integrate OpenFace with Android but I saw it uses about 100mb ram on ubuntu and 200 mb ram on windows which is too much for a device but seeing this difference in os I'm thinking weather it will work on Android where 50/100 mb is about the maximum you can get. Do you think it can handle it ? Also, do you have any suggestions on how one should proceed with the integration ? I'm not sure if I should generate .a or .so files and if it will work out of the box like this.

    opened by tudor-pop 20
  • Movement on Python API?

    Movement on Python API?

    Looks like there are two open PRs

    for adding a python API.

    @TadasBaltrusaitis is there a reason for delay? I can also do the python bindings as a fresh PR if need be.

    opened by fxfactorial 19
  • Real-time use of FeatureExtraction

    Real-time use of FeatureExtraction

    Is there a built-in way to run FeatureExtraction in real-time? According to the wiki there seems like no way to specify a webcam from which to read the images.

    opened by rishubjain 19
  • Compiling for an ARM architecture

    Compiling for an ARM architecture

    Hi, I wanted to see what the performance is like on an ARM architecture, I wanted to test it on an Intel computer stick, I have compiled OpenCV from source for ARM and have changed the dependencies accordingly, I am still running into issues, is there any good guides out there for building projects for ARM architecture. Also, will I have to recompile dlib for ARM too?

    opened by WajWaraich 18
  • Opencv fails with long video.

    Opencv fails with long video.

    I found the OpenFace 2.0 works properly with small video, but crashes repeatedly during a big (1GB, 30min) video in similar point. below is the error messages.

    I am afraid the OpenCV version is too high and the bug related to it, or some size restriction in buffer/temporary folder...

    20% Face too small for landmark detection
    Face too small for landmark detection
    Face too small for landmark detection
    Face too small for landmark detection
    OpenCV(3.4.1) Error: Assertion failed (0 <= roi.x && 0 <= roi.width && roi.x + roi.width <= m.cols && 0 <= roi.y && 0 <= roi.height && roi.y + roi.height <= m.rows) in Mat, file /tmp/opencv-20180307-19209-1d8dn7a/opencv-3.4.1/modules/core/src/matrix.cpp, line 464
    libc++abi.dylib: terminating with uncaught exception of type cv::Exception: OpenCV(3.4.1) /tmp/opencv-20180307-19209-1d8dn7a/opencv-3.4.1/modules/core/src/matrix.cpp:464: error: (-215) 0 <= roi.x && 0 <= roi.width && roi.x + roi.width <= m.cols && 0 <= roi.y && 0 <= roi.height && roi.y + roi.height <= m.rows in function Mat
    opened by iPsych 17
  • compiling issue on Ubuntu 18.04

    compiling issue on Ubuntu 18.04

    I'm running on Ubuntu 18.04 and have the following compiling problem ... any ideas on what I made wrong or how to find out the root cause?

    Scanning dependencies of target FaceLandmarkImg
    [ 92%] Building CXX object exe/FaceLandmarkImg/CMakeFiles/FaceLandmarkImg.dir/FaceLandmarkImg.cpp.o
    [ 93%] Linking CXX executable ../../bin/FaceLandmarkImg
    /usr/bin/ld: /usr/local/lib/libopencv_core.a(ocl.cpp.o): undefined reference to symbol '_ZNSo9_M_insertIdEERSoT_@@GLIBCXX_3.4.9'
    //usr/lib/x86_64-linux-gnu/ error adding symbols: DSO missing from command line
    clang: error: linker command failed with exit code 1 (use -v to see invocation)
    exe/FaceLandmarkImg/CMakeFiles/FaceLandmarkImg.dir/build.make:154: recipe for target 'bin/FaceLandmarkImg' failed
    make[2]: *** [bin/FaceLandmarkImg] Error 1
    CMakeFiles/Makefile2:364: recipe for target 'exe/FaceLandmarkImg/CMakeFiles/FaceLandmarkImg.dir/all' failed
    make[1]: *** [exe/FaceLandmarkImg/CMakeFiles/FaceLandmarkImg.dir/all] Error 2
    Makefile:129: recipe for target 'all' failed
    make: *** [all] Error 2
    $ apt list | grep libstdc
    WARNING: apt does not have a stable CLI interface. Use with caution in scripts.
    libstdc++-4.8-dev/bionic 4.8.5-4ubuntu8 amd64
    libstdc++-4.8-doc/bionic,bionic 4.8.5-4ubuntu8 all
    libstdc++-4.8-pic/bionic 4.8.5-4ubuntu8 amd64
    libstdc++-5-dev/bionic 5.5.0-12ubuntu1 amd64
    libstdc++-5-dev-alpha-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++-5-dev-arm64-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++-5-dev-armel-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++-5-dev-armhf-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++-5-dev-i386-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++-5-dev-m68k-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++-5-dev-mips-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++-5-dev-mips64-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++-5-dev-mips64el-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++-5-dev-mipsel-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++-5-dev-powerpc-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++-5-dev-powerpcspe-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++-5-dev-ppc64-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++-5-dev-ppc64el-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++-5-dev-s390x-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++-5-dev-sh4-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++-5-dev-sparc64-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++-5-dev-x32-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++-5-doc/bionic,bionic 5.5.0-12ubuntu1 all
    libstdc++-5-pic/bionic 5.5.0-12ubuntu1 amd64
    libstdc++-5-pic-alpha-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++-5-pic-arm64-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++-5-pic-armel-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++-5-pic-armhf-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++-5-pic-i386-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++-5-pic-m68k-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++-5-pic-mips-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++-5-pic-mips64-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++-5-pic-mips64el-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++-5-pic-mipsel-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++-5-pic-powerpc-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++-5-pic-powerpcspe-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++-5-pic-ppc64-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++-5-pic-ppc64el-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++-5-pic-s390x-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++-5-pic-sh4-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++-5-pic-sparc64-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++-5-pic-x32-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++-6-dev/bionic 6.4.0-17ubuntu1 amd64
    libstdc++-6-dev-alpha-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++-6-dev-amd64-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++-6-dev-arm64-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++-6-dev-armel-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++-6-dev-armhf-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++-6-dev-hppa-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++-6-dev-i386-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++-6-dev-m68k-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++-6-dev-mips-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++-6-dev-mips64-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++-6-dev-mips64el-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++-6-dev-mipsel-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++-6-dev-powerpc-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++-6-dev-powerpcspe-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++-6-dev-ppc64-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++-6-dev-ppc64el-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++-6-dev-s390x-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++-6-dev-sh4-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++-6-dev-sparc64-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++-6-dev-x32-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++-6-doc/bionic,bionic 6.4.0-17ubuntu1 all
    libstdc++-6-pic/bionic 6.4.0-17ubuntu1 amd64
    libstdc++-6-pic-alpha-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++-6-pic-amd64-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++-6-pic-arm64-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++-6-pic-armel-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++-6-pic-armhf-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++-6-pic-hppa-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++-6-pic-i386-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++-6-pic-m68k-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++-6-pic-mips-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++-6-pic-mips64-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++-6-pic-mips64el-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++-6-pic-mipsel-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++-6-pic-powerpc-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++-6-pic-powerpcspe-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++-6-pic-ppc64-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++-6-pic-ppc64el-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++-6-pic-s390x-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++-6-pic-sh4-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++-6-pic-sparc64-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++-6-pic-x32-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++-7-dev/bionic,now 7.3.0-16ubuntu3 amd64 [installed,automatic]
    libstdc++-7-dev-alpha-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++-7-dev-amd64-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++-7-dev-arm64-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++-7-dev-armel-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++-7-dev-armhf-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++-7-dev-hppa-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++-7-dev-i386-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++-7-dev-m68k-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++-7-dev-mips-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++-7-dev-mips64-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++-7-dev-mips64el-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++-7-dev-mipsel-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++-7-dev-powerpc-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++-7-dev-powerpcspe-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++-7-dev-ppc64-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++-7-dev-ppc64el-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++-7-dev-riscv64-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++-7-dev-s390x-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++-7-dev-sh4-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++-7-dev-sparc64-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++-7-dev-x32-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++-7-doc/bionic,bionic 7.3.0-16ubuntu3 all
    libstdc++-7-pic/bionic 7.3.0-16ubuntu3 amd64
    libstdc++-7-pic-alpha-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++-7-pic-amd64-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++-7-pic-arm64-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++-7-pic-armel-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++-7-pic-armhf-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++-7-pic-hppa-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++-7-pic-i386-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++-7-pic-m68k-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++-7-pic-mips-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++-7-pic-mips64-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++-7-pic-mips64el-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++-7-pic-mipsel-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++-7-pic-powerpc-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++-7-pic-powerpcspe-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++-7-pic-ppc64-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++-7-pic-ppc64el-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++-7-pic-riscv64-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++-7-pic-s390x-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++-7-pic-sh4-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++-7-pic-sparc64-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++-7-pic-x32-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++-8-dev/bionic 8-20180414-1ubuntu2 amd64
    libstdc++-8-dev-alpha-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++-8-dev-amd64-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++-8-dev-arm64-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++-8-dev-armel-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++-8-dev-armhf-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++-8-dev-hppa-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++-8-dev-i386-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++-8-dev-m68k-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++-8-dev-mips-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++-8-dev-mips64-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++-8-dev-mips64el-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++-8-dev-mipsel-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++-8-dev-powerpc-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++-8-dev-powerpcspe-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++-8-dev-ppc64-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++-8-dev-ppc64el-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++-8-dev-riscv64-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++-8-dev-s390x-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++-8-dev-sh4-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++-8-dev-sparc64-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++-8-dev-x32-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++-8-doc/bionic,bionic 8-20180414-1ubuntu2 all
    libstdc++-8-pic/bionic 8-20180414-1ubuntu2 amd64
    libstdc++-8-pic-alpha-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++-8-pic-amd64-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++-8-pic-arm64-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++-8-pic-armel-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++-8-pic-armhf-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++-8-pic-hppa-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++-8-pic-i386-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++-8-pic-m68k-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++-8-pic-mips-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++-8-pic-mips64-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++-8-pic-mips64el-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++-8-pic-mipsel-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++-8-pic-powerpc-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++-8-pic-powerpcspe-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++-8-pic-ppc64-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++-8-pic-ppc64el-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++-8-pic-riscv64-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++-8-pic-s390x-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++-8-pic-sh4-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++-8-pic-sparc64-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++-8-pic-x32-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++-arm-none-eabi-newlib/bionic,bionic 15:6.3.1+svn253039-1+10 all
    libstdc++5/bionic 1:3.3.6-30 amd64
    libstdc++6/bionic,now 8-20180414-1ubuntu2 amd64 [installed]
    libstdc++6-4.8-dbg/bionic 4.8.5-4ubuntu8 amd64
    libstdc++6-5-dbg/bionic 5.5.0-12ubuntu1 amd64
    libstdc++6-5-dbg-alpha-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++6-5-dbg-arm64-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++6-5-dbg-armel-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++6-5-dbg-armhf-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++6-5-dbg-i386-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++6-5-dbg-m68k-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++6-5-dbg-mips-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++6-5-dbg-mips64-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++6-5-dbg-mips64el-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++6-5-dbg-mipsel-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++6-5-dbg-powerpc-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++6-5-dbg-powerpcspe-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++6-5-dbg-ppc64-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++6-5-dbg-ppc64el-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++6-5-dbg-s390x-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++6-5-dbg-sh4-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++6-5-dbg-sparc64-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++6-5-dbg-x32-cross/bionic,bionic 5.5.0-12ubuntu1cross1 all
    libstdc++6-6-dbg/bionic 6.4.0-17ubuntu1 amd64
    libstdc++6-6-dbg-alpha-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++6-6-dbg-amd64-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++6-6-dbg-arm64-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++6-6-dbg-armel-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++6-6-dbg-armhf-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++6-6-dbg-hppa-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++6-6-dbg-i386-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++6-6-dbg-m68k-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++6-6-dbg-mips-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++6-6-dbg-mips64-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++6-6-dbg-mips64el-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++6-6-dbg-mipsel-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++6-6-dbg-powerpc-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++6-6-dbg-powerpcspe-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++6-6-dbg-ppc64-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++6-6-dbg-ppc64el-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++6-6-dbg-s390x-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++6-6-dbg-sh4-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++6-6-dbg-sparc64-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++6-6-dbg-x32-cross/bionic,bionic 6.4.0-17ubuntu1cross1 all
    libstdc++6-7-dbg/bionic 7.3.0-16ubuntu3 amd64
    libstdc++6-7-dbg-alpha-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++6-7-dbg-amd64-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++6-7-dbg-arm64-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++6-7-dbg-armel-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++6-7-dbg-armhf-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++6-7-dbg-hppa-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++6-7-dbg-i386-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++6-7-dbg-m68k-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++6-7-dbg-mips-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++6-7-dbg-mips64-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++6-7-dbg-mips64el-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++6-7-dbg-mipsel-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++6-7-dbg-powerpc-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++6-7-dbg-powerpcspe-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++6-7-dbg-ppc64-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++6-7-dbg-ppc64el-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++6-7-dbg-riscv64-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++6-7-dbg-s390x-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++6-7-dbg-sh4-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++6-7-dbg-sparc64-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++6-7-dbg-x32-cross/bionic,bionic 7.3.0-16ubuntu3cross1 all
    libstdc++6-8-dbg/bionic 8-20180414-1ubuntu2 amd64
    libstdc++6-8-dbg-alpha-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++6-8-dbg-amd64-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++6-8-dbg-arm64-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++6-8-dbg-armel-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++6-8-dbg-armhf-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++6-8-dbg-hppa-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++6-8-dbg-i386-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++6-8-dbg-m68k-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++6-8-dbg-mips-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++6-8-dbg-mips64-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++6-8-dbg-mips64el-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++6-8-dbg-mipsel-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++6-8-dbg-powerpc-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++6-8-dbg-powerpcspe-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++6-8-dbg-ppc64-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++6-8-dbg-ppc64el-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++6-8-dbg-riscv64-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++6-8-dbg-s390x-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++6-8-dbg-sh4-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++6-8-dbg-sparc64-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++6-8-dbg-x32-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++6-alpha-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++6-amd64-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++6-arm64-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++6-armel-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++6-armhf-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++6-hppa-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++6-i386-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++6-m68k-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++6-mips-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++6-mips64-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++6-mips64el-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++6-mipsel-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++6-powerpc-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++6-powerpcspe-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++6-ppc64-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++6-ppc64el-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++6-riscv64-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++6-s390x-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++6-sh4-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++6-sparc64-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    libstdc++6-x32-cross/bionic,bionic 8-20180414-1ubuntu2cross1 all
    opened by ewagner70 16
  • runtime for FeatureExtraction?

    runtime for FeatureExtraction?

    Hello! I was running FeatureExtraction with the options -no2Dfp -no3Dfp -noMparams -noPose -noGaze on a 30-second mp4-format video clip and the program ran for approximately 10 minutes. It is supposed to run that long? Is there something I might be doing wrong? Is there any way that I can make it run faster? Thank you!

    opened by yuxunhe 15
  • Head-bound box changes colour what does it mean ?

    Head-bound box changes colour what does it mean ?

    The box that is bound to the head that is detected is usually blue, and I don't know exactly why, but I have found a few instances of it turning purple in the middle of the video, I've not seen that before and can't find the reason behind it. Is the colour change linked to a particular value ?

    I'm using openface 2.0 on windows (the offline tool)

    examples : head_box_purple head_box_blue

    opened by Oscar-L-F 0
  • Bug in gaze direction when looking down.

    Bug in gaze direction when looking down.

    I've been trying to use openface 2.2.0 for windows to study the gaze behaviour of subjects in front of a camera, but I've run into an error into the gaze_angle_y estimation that perturbs my results a lot.

    When the subject is looking down, the estimation of the gaze_angle_y suddenly jumps all the way up. as can be seen in the following screenshot : Capture2

    My goal is to detect when the subject is looking above the horizontal, so those errors interfere with my results in a significant way and I'm trying to find a way to either detect those errors and/or at least have an idea of how often I can expect those kind of errors.

    I've been trying to use the AU45_c "blink" to detect those errors because I noticed that openface counts "looking down" as a blink, but during those errors the AU45_c is never 0. Therefore, I cannot use it this way, as it actually interprets the situation as the subject looking up with open eyes. I'm also currently trying to use the vertical head angle (pose_Rx) to detect the error by identifying when the gaze is extremely high up and the head very low, but it is very finnicky.

    If this error is a known one and someone has found a way to circumvent it It would be great, but otherwise I'd appreciate a lot if you have some data on the gaze estimation error in different situations so I can at least mitigate my results using that. I've found in the openface paper that the absolute mean error on the gaze estimation is 9.96 degrees, but there isn't much explanation on what kind of error is being measured in what situations etc... I'd especially appreciate knowing a bit more about a comparison on the vertical error compared to the horizontal error, or values concerning the gaze error in the extremes.

    Best regards,


    opened by Oscar-L-F 3
  • opencv-4.1.0 has totally different structure?

    opencv-4.1.0 has totally different structure?

    Describe the bug I follow the advanced install for ubuntu, and the result folder has totally different structure. Can't find the script to execute and download model

    To Reproduce

    Desktop (please complete the following information):

    • OS: Ubuntu
    • Version 20.04
    opened by brianw0924 1
  • Running feature extraction script on multiple video files in a directory

    Running feature extraction script on multiple video files in a directory

    I understand its possible to run the feature extraction script on a single video file using the terminal e.g. ./FeatureExtraction.exe -f "...\CREMA-D\VideoFlash\1001_DFA_ANG_XX.flv" -out_dir ".../openface-output", but is it possible to run the code on multiple video files in a selected directory?

    opened by JeffinSiby 0
  • feed my model with camera frames

    feed my model with camera frames

    Hello, Thank you for this work, I want to feed a dynamic library that added to your work for detecting the facial expression for each frame, I need to know how I can feed my model with the camera frames that show in the GUI of OpenFaceOffline. I have doubts which of these files should I include in my project: OpenCVWrappers.h or SequenceReader.h

    I appreciate if you help me urgently! Kind regards

    opened by FereshtehFeiz 0
  • The make command throws error in FaceLandmarkImg

    The make command throws error in FaceLandmarkImg

    Hi, So I have been trying to install and build openface on my Mac Intel chip system. I perform all the steps as stated in the installation guide however when I do the make command in the build directory, it fails at 84% with an error of Screenshots -

    Please let me know how to resolve this.

    opened by jsinghh09 1
  • OpenFace_2.2.0(Jul 13, 2019)

    Update of OpenFace to version 2.2.0, a number of bug fixes and library updates

    Change log:

    • Moving to C++17. This means that the code can only be build using C++17 compilers (e.g. g++ >8 and Visual Studio 2017, clang > 5), fixing related bugs - (,,
    • Removing an explicit dependency on boost (all the filesystem operations are performed using std::filesystem or boost::filesysteme). If boost is available it will used boost:filesystem, otherwise std::filesystem (this requires C++17).
    • Visual Studio 2017 is now the main version for Visual Studio builds, VS 2015 is no longer supported
    • Updating OpenCV to 4.1 version (
    • Fixing a bug with output images when using GUI (
    • Updating RAWImage -, so it can be initialized from System.Drawing.Bitmap directly
    • Fixing overlap detection for multi face tracking: (
    Source code(tar.gz)
    Source code(zip) MB) MB)
  • OpenFace_2.1.0(Nov 29, 2018)

    • Removing TBB dependency. TBB can still be used, but is called through OpenCV (
    • Updating OpenBLAS version in 64-bit Windows builds (should lead to significant performance gains on that architecture)
    • Allow specifying image output format (for both aligned images and visualized images). See wiki for more details
    • Removing unused -q flag (
    Source code(tar.gz)
    Source code(zip) MB) MB)
  • OpenFace_2.0.6(Oct 6, 2018)

    A number of changes:

    • Removed duplicated code and some C++ warnings
    • Fixing snapshot function in HeadPoseLive
    • C++ code cleanup (,
    • Adding a Visual Studio 2017 solution file
    • Moving to C++ OpenCV convention
    • Storing models in additional locations (see wiki and scripts (
    Source code(tar.gz)
    Source code(zip) MB) MB)
  • OpenFace_2.0.5(Aug 22, 2018)


    • Fixing a crash in OpenFaceOffline in processing images without any faces present (
    • Fixing a crash in OpenFaceDemo that was caused by memory management issues in wrapper between C# and C++ (
    • Fixing waitKey being called even when no output is visualized
    • Removing AVX requirements on Windows code (will make it more compatible with some older machines)
    • Fixing bbox directory issue (
    Source code(tar.gz)
    Source code(zip) MB) MB)
  • OpenFace_2.0.4(Jul 21, 2018)


    • Fixing a bug that sometimes caused a crash when the face left the screen
    • Updating readme for OSX to do with memory issues in OpenBLAS
    • Hard stop in CMake if Boost or OpenCV not found
    • Fixing Haar detector copy in CMake (mentioned in
    • Getting ready for OpenCV 4.0 (thanks
    • Updating wiki on Mac installation and possible OpenBLAS issues
    Source code(tar.gz)
    Source code(zip) MB) MB)
  • OpenFace_v2.0.3(Jun 29, 2018)

    A lot of house-keeping: updating libraries and extra testing on various Ubuntu versions.


    • Big re-org and cleanup of CMake (thanks aleh-arol - and severin-lemaignan -
    • CMake is now only for Ubuntu and OSX, while for windows builds use Visual Studio 2015
    • Updating dlib to 19.13
      • Bringing up to recent build that has fewer clashes with OpenBLAS and boost
      • Now the code will require a separate build to link to on OS X and Ubuntu (this will allow users to re-use their own dlib builds and will increase stability)
    • Instructions and testing for Ubuntu 14, 16, and 18
    • Fixing boost and dlib clashes, that resulted in requiring a certain version of boost, now most versions of boost should work
    • OpenBLAS include fixes with testing on Ubuntu 14.04, 16.04, 18.04, and OS X
    • Some of the issues were caused by Ubuntu 14.04 openblas install not containing headers
    • Some CNN util cleanup
    • Cleaning up includes in Cpp interop code
    • Bug fixes:
      • Really short executables using FeatureExtraction
    • Option to process .webm files in the GUI
    Source code(tar.gz)
    Source code(zip) MB) MB)
  • OpenFace_v2.0.2(Jun 2, 2018)

  • OpenFace_v2.0.1(May 23, 2018)

  • OpenFace_v2.0.0(May 11, 2018)

    A lot of changes:

    • A new facial landmark detection model - CE-CLM. Much more accurate model that is able to cope much better with profile faces
      • Training code for new models
      • Slightly slower than previous model, but previous models can still be used as well
    • A new CNN based face detector (MTCNN) that can detect faces in much more difficult scenarios and even at profile faces!
    • Both combined lead to better results on landmark detection, head pose estimation, gaze, and AUs
    • GUI better support for multi-face images (correct visualization, output fixes with face id)
    • GUI selection of face detector and landmark detector
    • bug fix with memory allocation in visual C++ bindings
    • Experimental evaluation on 300VW data
    • Experimental evaluation on IJB-FL data
    • Matlab hierarchical fitting has much cleaner and clearer code
    • A lot of code optimizations
    • Threading based input and output
    Source code(tar.gz)
    Source code(zip) MB)
  • OpenFace_v1.0.0(Apr 3, 2018)

  • OpenFace_v0.4.1(Mar 1, 2018)

  • OpenFace_v0.4.0(Feb 5, 2018)

  • OpenFace_v0.3.0(Dec 29, 2017)

    Big changes to the interface and API making it much easier to use:

    • Big change in output for image features, now consistent with sequence ones, making it easier to interpret results, and functionality is the same, with both outputting 3D eye landmarks, HOG, and aligned faces (see Wiki for more details)
    • Added a utilities project and library that contains
      • Separate recorder class for recording features computed by OpenFace
      • Separate image and sequence capture classes for easier loading of data
      • Image manipulation and rotation utilities, removing some code repetition
    • Capability to process features live
    • bug fixes with working with 16bit data
    • More sensible output when faces are not tracked
    Source code(tar.gz)
    Source code(zip) MB) MB)
  • OpenFace_v0.2.5(Oct 27, 2017)

    A number of changes to the interface and output of the model: - Separation of landmark detection and action unit analysis, now the action unit module only requires location of facial landmarks to perform predictions, this allows for easy substitution of other facial landmark detection models, as long as they use the same 68 point markup - Allowing for output of gaze angle and eye region landmarks - Moving gaze analysis to a separate project - Updating wiki to reflect these changes

    Source code(tar.gz)
    Source code(zip) MB) MB)
  • OpenFace_v0.2.4(Oct 15, 2017)

  • OpenFace_v0.2.3(Jan 5, 2017)

Tadas Baltrusaitis
I am a researcher working in Computer Vision and Machine Learning especially as they relate to Affective Computing and facial behaviour analysis.
Tadas Baltrusaitis
Code for BMVC2021 "MOS: A Low Latency and Lightweight Framework for Face Detection, Landmark Localization, and Head Pose Estimation"

MOS-Multi-Task-Face-Detect Introduction This repo is the official implementation of "MOS: A Low Latency and Lightweight Framework for Face Detection,

null 104 Dec 8, 2022
Facial Action Unit Intensity Estimation via Semantic Correspondence Learning with Dynamic Graph Convolution

FAU Implementation of the paper: Facial Action Unit Intensity Estimation via Semantic Correspondence Learning with Dynamic Graph Convolution. Yingruo

Evelyn 78 Nov 29, 2022
The official TensorFlow implementation of the paper Action Transformer: A Self-Attention Model for Short-Time Pose-Based Human Action Recognition

Action Transformer A Self-Attention Model for Short-Time Human Action Recognition This repository contains the official TensorFlow implementation of t

PIC4SeRCentre 20 Jan 3, 2023
Facial detection, landmark tracking and expression transfer library for Windows, Linux and Mac

Welcome to the CSIRO Face Analysis SDK. Documentation for the SDK can be found in doc/documentation.html. All code in this SDK is provided according t

Luiz Carlos Vieira 7 Jul 16, 2020
End-to-end face detection, cropping, norm estimation, and landmark detection in a single onnx model

onnx-facial-lmk-detector End-to-end face detection, cropping, norm estimation, and landmark detection in a single onnx model, model.onnx. Demo You can

atksh 42 Dec 30, 2022
Implementation of the state of the art beat-detection, downbeat-detection and tempo-estimation model

The ISMIR 2020 Beat Detection, Downbeat Detection and Tempo Estimation Model Implementation. This is an implementation in TensorFlow to implement the

Koen van den Brink 1 Nov 12, 2021
Unit-Convertor - Unit Convertor Built With Python

Python Unit Converter This project can convert Weigth,length and ... units for y

Mahdis Esmaeelian 1 May 31, 2022
Propose a principled and practically effective framework for unsupervised accuracy estimation and error detection tasks with theoretical analysis and state-of-the-art performance.

Detecting Errors and Estimating Accuracy on Unlabeled Data with Self-training Ensembles This project is for the paper: Detecting Errors and Estimating

Jiefeng Chen 13 Nov 21, 2022
Human head pose estimation using Keras over TensorFlow.

RealHePoNet: a robust single-stage ConvNet for head pose estimation in the wild.

Rafael Berral Soler 71 Jan 5, 2023
WHENet: Real-time Fine-Grained Estimation for Wide Range Head Pose

WHENet: Real-time Fine-Grained Estimation for Wide Range Head Pose Yijun Zhou and James Gregson - BMVC2020 Abstract: We present an end-to-end head-pos

null 368 Dec 26, 2022
Deep Learning Head Pose Estimation using PyTorch.

Hopenet is an accurate and easy to use head pose estimation network. Models have been trained on the 300W-LP dataset and have been tested on real data with good qualitative performance.

Nataniel Ruiz 1.3k Dec 26, 2022
Official Pytorch implementation of 6DRepNet: 6D Rotation representation for unconstrained head pose estimation.

6D Rotation Representation for Unconstrained Head Pose Estimation (Pytorch) Paper Thorsten Hempel and Ahmed A. Abdelrahman and Ayoub Al-Hamadi, "6D Ro

Thorsten Hempel 284 Dec 23, 2022
A selection of State Of The Art research papers (and code) on human locomotion (pose + trajectory) prediction (forecasting)

A selection of State Of The Art research papers (and code) on human trajectory prediction (forecasting). Papers marked with [W] are workshop papers.

Karttikeya Manglam 40 Nov 18, 2022
LaneDet is an open source lane detection toolbox based on PyTorch that aims to pull together a wide variety of state-of-the-art lane detection models

LaneDet is an open source lane detection toolbox based on PyTorch that aims to pull together a wide variety of state-of-the-art lane detection models. Developers can reproduce these SOTA methods and build their own methods.

TuZheng 405 Jan 4, 2023
Video lie detector using xgboost - A video lie detector using OpenFace and xgboost

video_lie_detector_using_xgboost a video lie detector using OpenFace and xgboost

null 2 Jan 11, 2022
Official implementation of ACTION-Net: Multipath Excitation for Action Recognition (CVPR'21).

ACTION-Net Official implementation of ACTION-Net: Multipath Excitation for Action Recognition (CVPR'21). Getting Started EgoGesture data folder struct

V-Sense 171 Dec 26, 2022
PyTorch module to use OpenFace's nn4.small2.v1.t7 model

OpenFace for Pytorch Disclaimer: This codes require the input face-images that are aligned and cropped in the same way of the original OpenFace. * I m

Pete Tae-hoon Kim 176 Dec 12, 2022
SE3 Pose Interp - Interpolate camera pose or trajectory in SE3, pose interpolation, trajectory interpolation

SE3 Pose Interpolation Pose estimated from SLAM system are always discrete, and

Ran Cheng 4 Dec 15, 2022
The codes and models in 'Gaze Estimation using Transformer'.

GazeTR We provide the code of GazeTR-Hybrid in "Gaze Estimation using Transformer". We recommend you to use data processing codes provided in GazeHub.

null 65 Dec 27, 2022