Conventional head pose estimation methods are regarded as a classification or regression paradigm, individually. The accuracy of classification-based approaches is limited to pose quantized interval and regression-based methods are fragile due to extremely large pose in non-ideal conditions. On the contrary to these methods, this paper introduces a novel head pose estimation method using two-stage ensembles with average top-k regression. The first stage is a binned classification subtask with the optimal pose partition. The second stage achieves average top-k regression based on the former prediction. Then we combine the two subtasks by considering the task-dependent weights instead of setting coefficients by grid search. We conduct several experiments to analyze the optimal pose partition for classification part and to validate the average top-k loss for regression part. Furthermore, we report the performance of proposed method on AFW, AFLW2000 and BIWI datasets and results show rather competitive performance in head pose prediction.

常规的头部姿势估计方法分别被视为分类或回归范式。基于分类的方法的准确性仅限于姿势量化间隔，而基于回归的方法由于在非理想条件下的姿势非常大而十分脆弱。与这些方法相反，本文介绍了一种新颖的，使用具有平均top- k回归的两阶段合奏的头部姿态估计方法。第一阶段是具有最佳姿势分区的装箱分类子任务。第二阶段实现平均顶ķ基于先前的预测进行回归。然后，我们通过考虑与任务相关的权重而不是通过网格搜索设置系数来组合两个子任务。我们进行了一些实验，以分析分类部分的最佳姿势分配，并验证回归部分的平均top- k损失。此外，我们报告了该方法在AFW，AFLW2000和BIWI数据集上的性能，结果表明在头部姿势预测中具有相当的竞争力。