Skeleton-Split Framework using Spatial Temporal Graph Convolutional Networks for Action Recogntion

11/04/2021
by   Motasem Alsawadi, et al.
0

There has been a dramatic increase in the volume of videos and their related content uploaded to the internet. Accordingly, the need for efficient algorithms to analyse this vast amount of data has attracted significant research interest. An action recognition system based upon human body motions has been proven to interpret videos contents accurately. This work aims to recognize activities of daily living using the ST-GCN model, providing a comparison between four different partitioning strategies: spatial configuration partitioning, full distance split, connection split, and index split. To achieve this aim, we present the first implementation of the ST-GCN framework upon the HMDB-51 dataset. We have achieved 48.88 using the connection split partitioning approach. Through experimental simulation, we show that our proposals have achieved the highest accuracy performance on the UCF-101 dataset using the ST-GCN framework than the state-of-the-art approach. Finally, accuracy of 73.25 using the index split partitioning strategy.

READ FULL TEXT
research
08/03/2021

Skeleton Split Strategies for Spatial Temporal Graph Convolution Networks

A skeleton representation of the human body has been proven to be effect...
research
08/01/2020

Improving Skeleton-based Action Recognitionwith Robust Spatial and Temporal Features

Recently skeleton-based action recognition has made signif-icant progres...
research
09/27/2021

Fusion-GCN: Multimodal Action Recognition using Graph Convolutional Networks

In this paper, we present Fusion-GCN, an approach for multimodal action ...
research
12/13/2021

Split GCN: Effective Interactive Annotation for Segmentation of Disconnected Instance

Annotating object boundaries by humans demands high costs. Recently, pol...
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
07/30/2020

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

Graph Convolutional Networks (GCNs) have already demonstrated their powe...
research
05/08/2019

Automatic multiscale approach for water networks partitioning into dynamic district metered areas

This paper presents a novel methodology to automatically split a water d...

Please sign up or login with your details

Forgot password? Click here to reset