论文标题
空间变压器网络具有转移学习，用于基于小粒子骨架的Tai Chi Action识别
Spatial Transformer Network with Transfer Learning for Small-scale Fine-grained Skeleton-based Tai Chi Action Recognition
论文作者
论文摘要
人类的行动识别是一个非常受过大量研究的领域，在该领域中，最引人注目的动作识别网络通常使用日常人类行动的大规模粗颗粒动作数据集作为陈述其网络优势的输入。我们打算使用神经网络来识别我们的小规模细粒Tai Chi动作数据集，并使用NTU RGB+D数据集提出一种转移学习方法，以预先培训我们的网络。更具体地说，该提出的方法首先使用大规模的NTU RGB+D数据集来预先培训基于变压器的网络，以在人类运动中提取共同的特征。然后，我们冻结除完全连接（FC）层以外的网络权重，并将我们的Tai Chi动作作为输入，仅用于训练初始化的FC权重。实验结果表明，我们的通用模型管道可以达到小规模细粒的Tai Chi Action识别的高精度，甚至很少输入，并且证明我们的方法与先前的Tai Chi动作识别方法相比，我们的方法实现了最先进的性能。
Human action recognition is a quite hugely investigated area where most remarkable action recognition networks usually use large-scale coarse-grained action datasets of daily human actions as inputs to state the superiority of their networks. We intend to recognize our small-scale fine-grained Tai Chi action dataset using neural networks and propose a transfer-learning method using NTU RGB+D dataset to pre-train our network. More specifically, the proposed method first uses a large-scale NTU RGB+D dataset to pre-train the Transformer-based network for action recognition to extract common features among human motion. Then we freeze the network weights except for the fully connected (FC) layer and take our Tai Chi actions as inputs only to train the initialized FC weights. Experimental results show that our general model pipeline can reach a high accuracy of small-scale fine-grained Tai Chi action recognition with even few inputs and demonstrate that our method achieves the state-of-the-art performance compared with previous Tai Chi action recognition methods.
