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

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

研究成果: 書貢獻/報告類型會議論文篇章

摘要

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.

原文英語
主出版物標題Proceedings - 2020 International Conference on Pervasive Artificial Intelligence, ICPAI 2020
發行者Institute of Electrical and Electronics Engineers Inc.
頁面170-174
頁數5
ISBN(電子)9780738142623
DOIs
出版狀態已發佈 - 2020 十二月
事件1st International Conference on Pervasive Artificial Intelligence, ICPAI 2020 - Taipei, 臺灣
持續時間: 2020 十二月 32020 十二月 5

出版系列

名字Proceedings - 2020 International Conference on Pervasive Artificial Intelligence, ICPAI 2020

會議

會議1st International Conference on Pervasive Artificial Intelligence, ICPAI 2020
國家/地區臺灣
城市Taipei
期間2020/12/032020/12/05

ASJC Scopus subject areas

  • 人工智慧
  • 電腦科學應用
  • 決策科學(雜項)
  • 航空工程
  • 工業與製造工程
  • 控制和優化

指紋

深入研究「SlowFast-GCN: A Novel Skeleton-Based Action Recognition Framework」主題。共同形成了獨特的指紋。

引用此