# Richly Activated Graph Convolutional Network for Action Recognition with Incomplete Skeletons

## TL;DR

This paper introduces RA-GCN, a multi-stream graph convolutional network that enhances action recognition robustness with incomplete skeletons by focusing on unactivated joints using class activation maps.

## Contribution

The paper proposes a novel multi-stream GCN architecture that selectively learns from unactivated joints, improving robustness to incomplete skeleton data.

## Key findings

- Achieves comparable performance on NTU RGB+D dataset
- Significantly alleviates performance deterioration on occluded skeletons
- Demonstrates robustness in synthetic occlusion scenarios

## Abstract

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.