Yang Sun
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Yang Sun has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Chong-Rong Li
Institute for Network Sciences and Cyberspace, Tsinghua University, Beijing, China
1 shared publication - Wenduo He
Institute for Network Sciences and Cyberspace, Tsinghua University, Beijing, China
1 shared publication - Xuan Zhang
Institute for Network Sciences and Cyberspace, Tsinghua University, Beijing, China
1 shared publication - Xuan Zhang
Tsinghua University
1 shared publication
Latest Publications
- Open Access
- 30 August 2018
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1069 (1) , 012164
Face Alignment Based on Two-Stage Localization
The traditional cascade regression model could easily drop into local optimum when the initial localization is far from real shape.This paper proposesa face alignment scheme based ontwo-stage localization. In theface detection stage, the multi-task CNN is adopted to get the information oflandmarks and poseas the initial localization for second stage. In the second stage, the cascade regression based on random forest is implemented for face alignment, and the localization from first stage is used as the initial coarse localization for regression model to solve the problem of initialization sensitivity. The scheme can achieve excellent performance even in the case of large pose variations and occlusion. Compared with the traditional method, experiments show that our algorithm can get state-of-art resultsin real-time on benchmark of 300W dataset.
- 30 August 2018
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1069 (1) , 012164
Open AccessFace Alignment Based on Two-Stage Localization
The traditional cascade regression model could easily drop into local optimum when the initial localization is far from real shape.This paper proposesa face alignment scheme based ontwo-stage localization. In theface detection stage, the multi-task CNN is adopted to get the information oflandmarks and poseas the initial localization for second stage. In the second stage, the cascade regression based on random forest is implemented for face alignment, and the localization from first stage is used as the initial coarse localization for regression model to solve the problem of initialization sensitivity. The scheme can achieve excellent performance even in the case of large pose variations and occlusion. Compared with the traditional method, experiments show that our algorithm can get state-of-art resultsin real-time on benchmark of 300W dataset.
- Open Access
- 1 August 2017
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 887 (1) , 012079
Multi-task convolution network for face alignment
In order to solve face alignment more effectively, we proposed a multi-task deep convolution network for face alignment, which achieves good performance even in the case of large pose variations and severe occlusion. Instead of dealing with face alignment as a single task, we jointly trained the auxiliary task of pose estimation together with face alignment to guide the distribution of facial points. By doing so we are able to 1) avoid trapping in the local optimum due to the inaccurate face boxes, 2) improve the robustness in dealing with faces with pose variation and severe occlusion. Compared with the traditional methods, our method also improves the accuracy by providing better initialization instead of mean shape. Extensive experiments show that our method has great performance on various benchmarks.
- 1 August 2017
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 887 (1) , 012079
Open AccessMulti-task convolution network for face alignment
In order to solve face alignment more effectively, we proposed a multi-task deep convolution network for face alignment, which achieves good performance even in the case of large pose variations and severe occlusion. Instead of dealing with face alignment as a single task, we jointly trained the auxiliary task of pose estimation together with face alignment to guide the distribution of facial points. By doing so we are able to 1) avoid trapping in the local optimum due to the inaccurate face boxes, 2) improve the robustness in dealing with faces with pose variation and severe occlusion. Compared with the traditional methods, our method also improves the accuracy by providing better initialization instead of mean shape. Extensive experiments show that our method has great performance on various benchmarks.