Recently, the significant achievements have been made in skeleton-based human action recognition with the emergence of graph convolutional networks (GCNs). However, the state-of-the-art (SOTA) models used for this task focus on constructing more complex higher-order connections between joint nodes to describe skeleton information, which leads to complex inference processes and high computational costs. To address the slow inference speed caused by overly complex model structures, we introduce re-parameterization and over-parameterization techniques to GCNs and propose two novel high-performance inference GCNs, namely HPI-GCN-RP and HPI-GCN-OP. After the completion of model training, model parameters are fixed. HPI-GCN-RP adopts re-parameterization technique to transform high-performance training model into fast inference model through linear transformations, which achieves a higher inference speed with competitive model performance. HPI-GCN-OP further utilizes over-parameterization technique to achieve higher performance improvement by introducing additional inference parameters, albeit with slightly decreased inference speed. The experimental results on the two skeleton-based action recognition datasets demonstrate the effectiveness of our approach. Our HPI-GCN-OP achieves performance comparable to the current SOTA models, with inference speeds five times faster. Specifically, our HPI-GCN-OP achieves an accuracy of 93\% on the cross-subject split of the NTU-RGB+D 60 dataset, and 90.1\% on the cross-subject benchmark of the NTU-RGB+D 120 dataset. Code is available at github.com/lizaowo/HPI-GCN.

翻译：近年来，随着图卷积网络（GCNs）的出现，基于骨架的人体动作识别领域取得了显著成就。然而，用于此任务的当前最先进（SOTA）模型侧重于构建关节节点间更复杂的高阶连接以描述骨架信息，这导致了复杂的推理过程和高昂的计算成本。为解决因模型结构过于复杂而导致的推理速度缓慢问题，我们将重参数化与过参数化技术引入GCN，并提出了两种新颖的高性能推理GCN，即HPI-GCN-RP与HPI-GCN-OP。模型训练完成后，其参数即被固定。HPI-GCN-RP采用重参数化技术，通过线性变换将高性能训练模型转换为快速推理模型，在保持模型性能竞争力的同时实现了更高的推理速度。HPI-GCN-OP则进一步利用过参数化技术，通过引入额外的推理参数实现了更高的性能提升，尽管推理速度略有下降。在两个基于骨架的动作识别数据集上的实验结果验证了我们方法的有效性。我们的HPI-GCN-OP实现了与当前SOTA模型相当的性能，且推理速度提升了五倍。具体而言，我们的HPI-GCN-OP在NTU-RGB+D 60数据集的跨受试者划分上达到了93%的准确率，在NTU-RGB+D 120数据集的跨受试者基准上达到了90.1%的准确率。代码发布于github.com/lizaowo/HPI-GCN。