Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition

08/23/2022
by   Jungho Lee, et al.
0

Graph convolutional networks (GCNs) are the most commonly used method for skeleton-based action recognition and have achieved remarkable performance. Generating adjacency matrices with semantically meaningful edges is particularly important for this task, but extracting such edges is challenging problem. To solve this, we propose a hierarchically decomposed graph convolutional network (HD-GCN) architecture with a novel hierarchically decomposed graph (HD-Graph). The proposed HD-GCN effectively decomposes every joint node into several sets to extract major adjacent and distant edges, and uses them to construct an HD-Graph containing those edges in the same semantic spaces of a human skeleton. In addition, we introduce an attention-guided hierarchy aggregation (A-HA) module to highlight the dominant hierarchical edge sets of the HD-Graph. Furthermore, we apply a new two-stream-three-graph ensemble method, which uses only joint and bone stream without any motion stream. The proposed model is evaluated and achieves state-of-the-art performance on three large, popular datasets: NTU-RGB+D 60, NTU-RGB+D 120, and Northwestern-UCLA. Finally, we demonstrate the effectiveness of our model with various comparative experiments.

READ FULL TEXT
research
09/13/2018

Part-based Graph Convolutional Network for Action Recognition

Human actions comprise of joint motion of articulated body parts or `ges...
research
12/15/2019

Skeleton-Based Action Recognition with Multi-Stream Adaptive Graph Convolutional Networks

Graph convolutional networks (GCNs), which generalize CNNs to more gener...
research
12/16/2020

Temporal Graph Modeling for Skeleton-based Action Recognition

Graph Convolutional Networks (GCNs), which model skeleton data as graphs...
research
08/09/2020

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

Current methods for skeleton-based human action recognition usually work...
research
07/12/2022

Skeletal Human Action Recognition using Hybrid Attention based Graph Convolutional Network

In skeleton-based action recognition, Graph Convolutional Networks model...
research
05/14/2021

REGINA - Reasoning Graph Convolutional Networks in Human Action Recognition

It is known that the kinematics of the human body skeleton reveals valua...
research
02/07/2020

Poisson Kernel Avoiding Self-Smoothing in Graph Convolutional Networks

Graph convolutional network (GCN) is now an effective tool to deal with ...

Please sign up or login with your details

Forgot password? Click here to reset