Spatio-Temporal Inception Graph Convolutional Networks for Skeleton-Based Action Recognition

11/26/2020
by   Zhen Huang, et al.
0

Skeleton-based human action recognition has attracted much attention with the prevalence of accessible depth sensors. Recently, graph convolutional networks (GCNs) have been widely used for this task due to their powerful capability to model graph data. The topology of the adjacency graph is a key factor for modeling the correlations of the input skeletons. Thus, previous methods mainly focus on the design/learning of the graph topology. But once the topology is learned, only a single-scale feature and one transformation exist in each layer of the networks. Many insights, such as multi-scale information and multiple sets of transformations, that have been proven to be very effective in convolutional neural networks (CNNs), have not been investigated in GCNs. The reason is that, due to the gap between graph-structured skeleton data and conventional image/video data, it is very challenging to embed these insights into GCNs. To overcome this gap, we reinvent the split-transform-merge strategy in GCNs for skeleton sequence processing. Specifically, we design a simple and highly modularized graph convolutional network architecture for skeleton-based action recognition. Our network is constructed by repeating a building block that aggregates multi-granularity information from both the spatial and temporal paths. Extensive experiments demonstrate that our network outperforms state-of-the-art methods by a significant margin with only 1/5 of the parameters and 1/10 of the FLOPs.

READ FULL TEXT

page 7

page 8

research
11/11/2020

Progressive Spatio-Temporal Graph Convolutional Network for Skeleton-Based Human Action Recognition

Graph convolutional networks (GCNs) have been very successful in skeleto...
research
11/29/2018

Generalized Graph Convolutional Networks for Skeleton-based Action Recognition

With the prevalence of accessible depth sensors, dynamic human body skel...
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
07/12/2022

Skeletal Human Action Recognition using Hybrid Attention based Graph Convolutional Network

In skeleton-based action recognition, Graph Convolutional Networks model...
research
01/23/2018

Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition

Dynamics of human body skeletons convey significant information for huma...
research
12/08/2021

Topology-aware Convolutional Neural Network for Efficient Skeleton-based Action Recognition

In the context of skeleton-based action recognition, graph convolutional...
research
01/21/2019

Skeleton-based Action Recognition of People Handling Objects

In visual surveillance systems, it is necessary to recognize the behavio...

Please sign up or login with your details

Forgot password? Click here to reset