TY - GEN
T1 - Cascaded Pose Regression Revisited
AU - Liu, Ruixu
AU - Shen, Ju
AU - Sun, Qingquan
AU - Yang, Jianjun
AU - Cheung, Sen Ching
PY - 2017/6/30
Y1 - 2017/6/30
N2 - Automated pose estimation is a fundamental task in computer vision. In this paper, we investigate the generic framework of Cascaded Pose Regression (CPR), which demonstrates practical effectiveness in pose estimation on deformable and articulated objects. In particular, we focus on the use of CPR for face alignment by exploring existing techniques and verifying their performances on different public facial datasets. We show that the correct selection of pose-invariant features is critical to encode the geometric arrangement of landmarks and crucial for the overall regressor learnability. Furthermore, by incorporating strategies that are commonly used among the state-of-the-art, we interpret the CPR training procedure as a repeated clustering problem with explicit regressor representation, which is complementary to the original CPR algorithm. In our experiment, the qualitative evaluation of existing alignment techniques demonstrates the success of CPR for facial pose inference that can be conveniently adopted to video detection and tracking applications.
AB - Automated pose estimation is a fundamental task in computer vision. In this paper, we investigate the generic framework of Cascaded Pose Regression (CPR), which demonstrates practical effectiveness in pose estimation on deformable and articulated objects. In particular, we focus on the use of CPR for face alignment by exploring existing techniques and verifying their performances on different public facial datasets. We show that the correct selection of pose-invariant features is critical to encode the geometric arrangement of landmarks and crucial for the overall regressor learnability. Furthermore, by incorporating strategies that are commonly used among the state-of-the-art, we interpret the CPR training procedure as a repeated clustering problem with explicit regressor representation, which is complementary to the original CPR algorithm. In our experiment, the qualitative evaluation of existing alignment techniques demonstrates the success of CPR for facial pose inference that can be conveniently adopted to video detection and tracking applications.
KW - Cascaded Pose Regression
KW - Face Alignment
KW - Face Shape Detection
KW - Pose Estimation
UR - http://www.scopus.com/inward/record.url?scp=85027721557&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85027721557&partnerID=8YFLogxK
U2 - 10.1109/BigMM.2017.81
DO - 10.1109/BigMM.2017.81
M3 - Conference contribution
AN - SCOPUS:85027721557
T3 - Proceedings - 2017 IEEE 3rd International Conference on Multimedia Big Data, BigMM 2017
SP - 291
EP - 298
BT - Proceedings - 2017 IEEE 3rd International Conference on Multimedia Big Data, BigMM 2017
Y2 - 19 April 2017 through 21 April 2017
ER -