Abstract

Accurate ground truth pose is essential to the training of most existing head pose estimation algorithms. However, in many cases, the “ground truth” pose is obtained in rather subjective ways, such as asking the human subjects to stare at different markers on the wall. In such case, it is better to use soft labels rather than explicit hard labels. Therefore, this paper proposes to associate a multivariate label distribution (MLD) to each image. An MLD covers a neighborhood around the original pose. Labeling the images with MLD can not only alleviate the problem of inaccurate pose labels, but also boost the training examples associated to each pose without actually increasing the total amount of training examples. Two algorithms are proposed to learn from the MLD by minimizing the weighted Jeffrey’s divergence between the predicted MLD and the ground truth MLD. Experimental results show that the MLD-based methods perform signifificantly better than the compared state-ofthe-art head pose estimation algorithms