SlowFast-GCN: A Novel Skeleton-Based Action Recognition Framework

Cheng Hsien Lin, Po Yung Chou, Cheng Hsien Lin, Min Yen Tsai

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Human action recognition plays an important role in video surveillance, human-computer interaction, video understanding, and virtual reality. Different from two-dimensional object recognition, human action recognition is a dynamic object recognition with a time series relationship, and it faces many challenges from complex environments, such as color shift, light and shadow changes, and sampling angles. In order to improve the accuracy of human action recognition, many studies have proposed skeleton-based action recognition methods that are not affected by the background, but the current framework does not have much discussion on the integration of the time dimension.In this paper, we propose a novel SlowFast-GCN framework which combines the advantages of ST-GCN and SlowFastNet with dynamic human skeleton to improve the accuracy of human action recognition. The proposed framework uses two streams, one stream captures fine-grained motion changes, and the other stream captures static semantics. Through these two streams, we can merge the human skeleton features from two different time dimensions. Experimental results show that the proposed framework outperforms to state-of-the-art approaches on the NTU-RGBD dataset.

Original languageEnglish
Title of host publicationProceedings - 2020 International Conference on Pervasive Artificial Intelligence, ICPAI 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages170-174
Number of pages5
ISBN (Electronic)9780738142623
DOIs
Publication statusPublished - 2020 Dec
Event1st International Conference on Pervasive Artificial Intelligence, ICPAI 2020 - Taipei, Taiwan
Duration: 2020 Dec 32020 Dec 5

Publication series

NameProceedings - 2020 International Conference on Pervasive Artificial Intelligence, ICPAI 2020

Conference

Conference1st International Conference on Pervasive Artificial Intelligence, ICPAI 2020
CountryTaiwan
CityTaipei
Period2020/12/032020/12/05

Keywords

  • Graph Convolution Neural Network
  • Skeleton base action recognition
  • Temporal fusion

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Decision Sciences (miscellaneous)
  • Aerospace Engineering
  • Industrial and Manufacturing Engineering
  • Control and Optimization

Fingerprint Dive into the research topics of 'SlowFast-GCN: A Novel Skeleton-Based Action Recognition Framework'. Together they form a unique fingerprint.

Cite this