Part-based Graph Convolutional Network for Action Recognition

Abstract

Human actions comprise of joint motion of articulated body parts or `gestures'. Human skeleton is intuitively represented as a sparse graph with joints as nodes and natural connections between them as edges. Graph convolutional networks have been used to recognize actions from skeletal videos. We introduce a part-based graph convolutional network (PB-GCN) for this task, inspired by Deformable Part-based Models (DPMs). We divide the skeleton graph into four subgraphs with joints shared across them and learn a recognition model using a part-based graph convolutional network. We show that such a model improves performance of recognition, compared to a model using entire skeleton graph. Instead of using 3D joint coordinates as node features, we show that using relative coordinates and temporal displacements boosts performance. Our model achieves state-of-the-art performance on two challenging benchmark datasets NTURGB+D and HDM05, for skeletal action recognition.

Main: 13 pages, 3 figures, 2 tables. Supplementary: 5 pages, 3 figures, 1 table. Accepted at BMVC 2018

Cited by in corpus (10)

• Stronger, Faster and More Explainable: A Graph Convolutional Baseline for Skeleton-based Action Recognition
• Richly Activated Graph Convolutional Network for Robust Skeleton-based Action Recognition
• An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition
• Deep Independently Recurrent Neural Network (IndRNN)
• Feedback Graph Convolutional Network for Skeleton-based Action Recognition
• BabyNet: A Lightweight Network for Infant Reaching Action Recognition in Unconstrained Environments to Support Future Pediatric Rehabilitation Applications
• Predictively Encoded Graph Convolutional Network for Noise-Robust Skeleton-based Action Recognition
• Graph-based Normalizing Flow for Human Motion Generation and Reconstruction
• Skeleon-Based Typing Style Learning For Person Identification
• Hierarchic Neighbors Embedding