论文标题
结合深度学习分类器以进行3D动作识别
Combining Deep Learning Classifiers for 3D Action Recognition
论文作者
论文摘要
3D人类行动识别的流行任务几乎通过培训深度学习分类器来解决。为了达到高识别精度，输入3D动作通常是通过各种归一化或增强技术预处理的。但是，为每个可能的训练数据变体训练分类器在计算上是不可行的，以便为给定数据集选择最佳性能的预处理技术子集。在本文中，我们建议为每种可用的预处理技术培训一个独立的分类器，并根据严格的多数投票规则融合分类结果。加上提出的评估程序，我们可以非常有效地确定特定数据集的归一化和增强技术的最佳组合。对于表现最佳的组合，我们可以回顾性地将输入数据的归一化/增强变体应用于训练单个分类器。这也使我们能够确定训练单个模型还是一组独立分类器是更好的。
The popular task of 3D human action recognition is almost exclusively solved by training deep-learning classifiers. To achieve a high recognition accuracy, the input 3D actions are often pre-processed by various normalization or augmentation techniques. However, it is not computationally feasible to train a classifier for each possible variant of training data in order to select the best-performing subset of pre-processing techniques for a given dataset. In this paper, we propose to train an independent classifier for each available pre-processing technique and fuse the classification results based on a strict majority vote rule. Together with a proposed evaluation procedure, we can very efficiently determine the best combination of normalization and augmentation techniques for a specific dataset. For the best-performing combination, we can retrospectively apply the normalized/augmented variants of input data to train only a single classifier. This also allows us to decide whether it is better to train a single model, or rather a set of independent classifiers.
