Richly Activated Graph Convolutional Network for Robust Skeleton-based Action Recognition

08/09/2020
by   Yi-Fan Song, et al.
2

Current methods for skeleton-based human action recognition usually work with complete skeletons. However, in real scenarios, it is inevitable to capture incomplete or noisy skeletons, which could significantly deteriorate the performance of current methods when some informative joints are occluded or disturbed. To improve the robustness of action recognition models, a multi-stream graph convolutional network (GCN) is proposed to explore sufficient discriminative features spreading over all skeleton joints, so that the distributed redundant representation reduces the sensitivity of the action models to non-standard skeletons. Concretely, the backbone GCN is extended by a series of ordered streams which is responsible for learning discriminative features from the joints less activated by preceding streams. Here, the activation degrees of skeleton joints of each GCN stream are measured by the class activation maps (CAM), and only the information from the unactivated joints will be passed to the next stream, by which rich features over all active joints are obtained. Thus, the proposed method is termed richly activated GCN (RA-GCN). Compared to the state-of-the-art (SOTA) methods, the RA-GCN achieves comparable performance on the standard NTU RGB+D 60 and 120 datasets. More crucially, on the synthetic occlusion and jittering datasets, the performance deterioration due to the occluded and disturbed joints can be significantly alleviated by utilizing the proposed RA-GCN.

READ FULL TEXT

page 1

page 2

page 3

page 11

research
05/16/2019

Richlt Activated Graph Convolutional Network for Action Recognition with Incomplete Skeletons

Current methods for skeleton-based human action recognition usually work...
research
05/16/2019

Richly Activated Graph Convolutional Network for Action Recognition with Incomplete Skeletons

Current methods for skeleton-based human action recognition usually work...
research
10/20/2020

Stronger, Faster and More Explainable: A Graph Convolutional Baseline for Skeleton-based Action Recognition

One essential problem in skeleton-based action recognition is how to ext...
research
11/16/2020

JOLO-GCN: Mining Joint-Centered Light-Weight Information for Skeleton-Based Action Recognition

Skeleton-based action recognition has attracted research attentions in r...
research
08/23/2022

Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition

Graph convolutional networks (GCNs) are the most commonly used method fo...
research
06/29/2021

Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition

One essential problem in skeleton-based action recognition is how to ext...
research
07/30/2020

Mix Dimension in Poincaré Geometry for 3D Skeleton-based Action Recognition

Graph Convolutional Networks (GCNs) have already demonstrated their powe...

Please sign up or login with your details

Forgot password? Click here to reset