Combining Deep Learning Classifiers for 3D Action Recognition
This addresses a computational bottleneck for researchers in 3D action recognition, though it is incremental as it builds on existing deep learning classifiers.
The paper tackles the computational inefficiency of selecting optimal pre-processing techniques for 3D action recognition by proposing a method to train independent classifiers for each technique and fuse results via majority vote, achieving efficient determination of the best combination for a dataset.
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.