论文标题
通过网络修剪进行分层操作分类
Hierarchical Action Classification with Network Pruning
论文作者
论文摘要
在过去的几年中，对人类行动分类的研究取得了重大进展。大多数深度学习方法都专注于通过添加更多网络组件来提高性能。但是，我们建议更好地利用辅助机制，包括分层分类，网络修剪和基于骨架的预处理，以增强模型的鲁棒性和性能。我们在四个常用的测试数据集上测试了方法的有效性：NTU RGB+D 60，NTU RGB+D 120，Northwestern-UCLA Multiview Action 3D和UTD多模式人类动作数据集。我们的实验表明，我们的方法可以在所有四个数据集上实现可比性或更好的性能。特别是，我们的方法为NTU 120建立了一个新的基线，这是四个数据集中最大的数据集。我们还通过广泛的比较和消融研究来分析我们的方法。
Research on human action classification has made significant progresses in the past few years. Most deep learning methods focus on improving performance by adding more network components. We propose, however, to better utilize auxiliary mechanisms, including hierarchical classification, network pruning, and skeleton-based preprocessing, to boost the model robustness and performance. We test the effectiveness of our method on four commonly used testing datasets: NTU RGB+D 60, NTU RGB+D 120, Northwestern-UCLA Multiview Action 3D, and UTD Multimodal Human Action Dataset. Our experiments show that our method can achieve either comparable or better performance on all four datasets. In particular, our method sets up a new baseline for NTU 120, the largest dataset among the four. We also analyze our method with extensive comparisons and ablation studies.
