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

Abstract

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.

arXiv commentAccepted by IEEE T-CSVT, 11 pages, 6 figures, 10 tables

References in corpus (10)

• Semi-Supervised Classification with Graph Convolutional Networks
• NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding
• Skeleton-Based Human Action Recognition with Global Context-Aware Attention LSTM Networks
• An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data
• Action Recognition using Visual Attention
• SkeleMotion: A New Representation of Skeleton Joint Sequences Based on Motion Information for 3D Action Recognition
• Part-based Graph Convolutional Network for Action Recognition
• Richly Activated Graph Convolutional Network for Action Recognition with Incomplete Skeletons
• Skeleton based action recognition using translation-scale invariant image mapping and multi-scale deep cnn
• Vertex Feature Encoding and Hierarchical Temporal Modeling in a Spatial-Temporal Graph Convolutional Network for Action Recognition

Cited by in corpus (9)

• A Central Difference Graph Convolutional Operator for Skeleton-Based Action Recognition
• D-STGCNT: A Dense Spatio-Temporal Graph Conv-GRU Network based on transformer for assessment of patient physical rehabilitation
• Two-person Graph Convolutional Network for Skeleton-based Human Interaction Recognition
• Temporal Graph Modeling for Skeleton-based Action Recognition
• Logsig-RNN: a novel network for robust and efficient skeleton-based action recognition
• Action Recognition in Real-World Ambient Assisted Living Environment
• Automated Dominative Subspace Mining for Efficient Neural Architecture Search
• Text-Derived Relational Graph-Enhanced Network for Skeleton-Based Action Segmentation
• Balanced Representation Learning for Long-tailed Skeleton-based Action Recognition