Proceedings of the 1st International Conference on AI for People: Towards Sustainable AI, CAIP 2021, 20-24 November 2021, Bologna, Italy

Research Article

Two-Person Mutual Action Recognition Using Joint Dynamics and Coordinate Transformation

Download282 downloads
  • @INPROCEEDINGS{10.4108/eai.20-11-2021.2314154,
        author={Shian-Yu  Chiu and Kun-Ru  Wu and Yu-Chee  Tseng},
        title={Two-Person Mutual Action Recognition Using Joint Dynamics and Coordinate Transformation},
        proceedings={Proceedings of the 1st International Conference on AI for People: Towards Sustainable AI, CAIP 2021, 20-24 November 2021, Bologna, Italy},
        publisher={EAI},
        proceedings_a={CAIP},
        year={2021},
        month={12},
        keywords={skeleton-based action recognition mutual interaction recognition bidirectional lstm deep learning human behavior analysis},
        doi={10.4108/eai.20-11-2021.2314154}
    }
    
  • Shian-Yu Chiu
    Kun-Ru Wu
    Yu-Chee Tseng
    Year: 2021
    Two-Person Mutual Action Recognition Using Joint Dynamics and Coordinate Transformation
    CAIP
    EAI
    DOI: 10.4108/eai.20-11-2021.2314154
Shian-Yu Chiu1, Kun-Ru Wu1,*, Yu-Chee Tseng1
  • 1: National Yang Ming Chiao Tung University, Taiwan
*Contact email: wufish@nycu.edu.tw

Abstract

Skeleton-based action recognition has attracted lots of attention in computer vision. Human mutual interaction recognition relies on extracting discriminative features for better understanding details. In this work, we propose two vectors to encode joint dynamics and spatial interaction information. The proposed model shows remarkable performance at handling sequential data. Experimental results demonstrate that our model outperforms state-of-the-art approaches with much less overheads.