wanghongjun
Research Associate
Supervisor of Master's Candidates
- Master Tutor
- Education Level:PhD graduate
- Degree:Doctor of engineering
- Business Address:犀浦3号教学楼31529
- Professional Title:Research Associate
- Alma Mater:四川大学
- Supervisor of Master's Candidates
- School/Department:计算机与人工智能学院
- Discipline:Electronic Information
Software Engineering
Computer Application Technology
Contact Information
- PostalAddress:
- Email:
- Paper Publications
Human action recognition based on transformer
- Affiliation of Author(s):西南交通大学
- Journal:Machine Learning, Multi Agent and Cyber Physical Systems: Proceedings of the 15th International FLINS Conference (FLINS 2022)
- Place of Publication:Tianjin, China
- Key Words:Action recognition; transformer; deep learning
- Abstract:Human action recognition (HAR) has received extensive attention in artificial intelligence today. In view of the huge advantages of transformers in capturing global context information and extracting effective features compared with traditional deep neural networks, in this paper, we propose to utilize transformer to solve HAR problems and to our knowledge, this is the first time to solve HAR problems by transformer in sensor datasets. Experiments on 12 real sensor datasets with three evaluation metrics demonstrate the superiority of using transformer against four classic or state-of-the-art models.
- Co-author:Jian Wu,Yueying Li,Ran Hao
- First Author:Kehan Wu
- Indexed by:Vol.
- Correspondence Author:Hongjun Wang
- Discipline:Engineering
- Document Type:C
- Page Number:450-456
- Translation or Not:no