论文标题
持续时空图卷积网络
Continual Spatio-Temporal Graph Convolutional Networks
论文作者
论文摘要
基于图形的骨骼数据的推理已成为人类行动识别的有前途的方法。但是，以先验的基于图的方法的应用，这些方法主要采用整个时间序列作为其输入，在线推理的设置需要相当大的计算冗余。在本文中，我们通过将时空图卷积神经网络作为持续的推理网络重新提出来解决此问题，该网络可以在不重复帧处理的情况下及时执行逐步预测。为了评估我们的方法，我们创建了一个连续的ST-GCN成本GCN的版本，以及两种具有不同自我发项机制的衍生方法，分别是COAGCN和COS-TR。我们研究了推理加速度的重量转移策略和体系结构修改，并对NTU RGB+D 60，NTU RGB+D 120和动力学骨骼400数据集进行实验。保持相似的预测精度，我们观察到时间复杂性降低109倍，硬件加速度为26倍，并减少在线推断期间最大分配记忆力为52％。
Graph-based reasoning over skeleton data has emerged as a promising approach for human action recognition. However, the application of prior graph-based methods, which predominantly employ whole temporal sequences as their input, to the setting of online inference entails considerable computational redundancy. In this paper, we tackle this issue by reformulating the Spatio-Temporal Graph Convolutional Neural Network as a Continual Inference Network, which can perform step-by-step predictions in time without repeat frame processing. To evaluate our method, we create a continual version of ST-GCN, CoST-GCN, alongside two derived methods with different self-attention mechanisms, CoAGCN and CoS-TR. We investigate weight transfer strategies and architectural modifications for inference acceleration, and perform experiments on the NTU RGB+D 60, NTU RGB+D 120, and Kinetics Skeleton 400 datasets. Retaining similar predictive accuracy, we observe up to 109x reduction in time complexity, on-hardware accelerations of 26x, and reductions in maximum allocated memory of 52% during online inference.
