Pose-Dependent Low-Rank Embedding for Head Pose Estimation

Handong Zhao, Zhengming Ding, Yun Fu

Abstract: Head pose estimation via embedding model has been demonstrated its effectiveness from the recent works. However, most of the previous methods only focus on manifold relationship among poses, while overlook the underlying global structure among subjects and poses. To build a robust and effective head pose estimator, we propose a novel Pose-dependent Low-Rank Embedding (PLRE) method, which is designed to exploit a discriminative subspace to keep within-pose samples close while between-pose samples far away. Specifically, low-rank embedding is employed under the multi-task framework, where each subject can be naturally considered as one task. Then, two novel terms are incorporated to align multiple tasks to pursue a better pose-dependent embedding. One is the cross-task alignment term, aiming to constrain each low-rank coefficient to share the similar structure. The other is pose-dependent graph regularizer, which is developed to capture manifold structure of same pose cross different subjects. Experiments on databases CMU-PIE, MIT-CBCL, and extended YaleB with different levels of random noise are conducted and six embedding model based baselines are compared. The consistent superior results demonstrate the effectiveness of our proposed method.