项目作者: LynnHo

项目描述 :
Robust FEC-CNN for Face Datasets
高级语言: Python
项目地址: git://github.com/LynnHo/Facial-Landmarks-of-Face-Datasets.git
创建时间: 2018-10-06T15:57:01Z
项目社区:https://github.com/LynnHo/Facial-Landmarks-of-Face-Datasets

开源协议:MIT License

下载



Robust-FEC-CNN Results of Face Datasets


Robust FEC-CNN: A High Accuracy Facial Landmark Detection System \
Zhenliang He1,2, Jie Zhang1,2, Meina Kan1,3, Shiguang Shan1,3, Xilin Chen1

A Fully End-to-End Cascaded CNN for Facial Landmark Detection \
Zhenliang He1,2, Meina Kan1,3, Jie Zhang1,2, Xilin Chen1, Shiguang Shan1,3

1Key Lab of Intelligent Information Processing, Institute of Computing Technology, CAS, China \
2University of Chinese Academy of Sciences, China \
3CAS Center for Excellence in Brain Science and Intelligence Technology, China

This repository provides facial landmark detection results of several face datasets by the technique of Robust-FEC-CNN (Won 2nd of CVPR 2017 Faces “In-The-Wild” Workshop-Challenge). These landmarks can be used for aligning faces of these datasets (use align.py).

Format

  • bbox.txt

    1. ...
    2. image x_min y_min x_max y_max
    3. ...
  • landmark.txt

    1. ...
    2. image x_1 y_1 ... x_i y_i ... x_68 y_68
    3. ...

Landmarks File of Face Datasets

Attribute

Age

Identity

Citation

If you find the results of Robust-FEC-CNN useful in your research work, please consider citing:

  1. @InProceedings{he2017robust,
  2. author = {He, Zhenliang and Zhang, Jie and Kan, Meina and Shan, Shiguang and Chen, Xilin},
  3. title = {Robust FEC-CNN: A High Accuracy Facial Landmark Detection System},
  4. booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
  5. year = {2017}
  6. }
  7. @InProceedings{he2017fully,
  8. author={He, Zhenliang and Kan, Meina and Zhang, Jie and Chen, Xilin and Shan, Shiguang},
  9. title={A Fully End-to-end Cascaded CNN for Facial Landmark Detection},
  10. booktitle={The IEEE International Conference on Automatic Face \& Gesture Recognition (FG)},
  11. year={2017}
  12. }