Richly Activated Graph Convolutional Network for Action Recognition with Incomplete Skeletons
This addresses the issue of incomplete skeleton data in real-world scenarios for action recognition, representing an incremental improvement over existing methods.
The paper tackles the problem of skeleton-based human action recognition with incomplete skeletons by proposing a richly activated graph convolutional network (RA-GCN) that enhances robustness, achieving comparable performance on the NTU RGB+D dataset and significantly alleviating performance deterioration on a synthetic occlusion dataset.
Current methods for skeleton-based human action recognition usually work with completely observed skeletons. However, in real scenarios, it is prone to capture incomplete and noisy skeletons, which will deteriorate the performance of traditional models. To enhance the robustness of action recognition models to incomplete skeletons, we propose a multi-stream graph convolutional network (GCN) for exploring sufficient discriminative features distributed over all skeleton joints. Here, each stream of the network is only responsible for learning features from currently unactivated joints, which are distinguished by the class activation maps (CAM) obtained by preceding streams, so that the activated joints of the proposed method are obviously more than traditional methods. Thus, the proposed method is termed richly activated GCN (RA-GCN), where the richly discovered features will improve the robustness of the model. Compared to the state-of-the-art methods, the RA-GCN achieves comparable performance on the NTU RGB+D dataset. Moreover, on a synthetic occlusion dataset, the performance deterioration can be alleviated by the RA-GCN significantly.