Skip to main content
placeholder image

Action recognition based on joint trajectory maps using convolutional neural networks

Conference Paper


Download full-text (Open Access)

Abstract


  • Recently, Convolutional Neural Networks (ConvNets) have shown promising performances in many computer vision tasks, especially image-based recognition. How to effectively use ConvNets for video-based recognition is still an open problem. In this paper, we propose a compact, effective yet simple method to encode spatiotemporal information carried in 3D skeleton sequences into multiple

    2D images, referred to as Joint Trajectory Maps (JTM), and ConvNets are adopted to exploit the discriminative features for realtime human action recognition. The proposed method has been

    evaluated on three public benchmarks, i.e., MSRC-12 Kinect gesture dataset (MSRC-12), G3D dataset and UTD multimodal human action dataset (UTD-MHAD) and achieved the state-of-the-art results.

UOW Authors


  •   Wang, Pichao (external author)
  •   Li, Zhaoyang (external author)
  •   Hou, Yonghong (external author)
  •   Li, Wanqing

Publication Date


  • 2016

Citation


  • Wang, P., Li, Z., Hou, Y. & Li, W. (2016). Action recognition based on joint trajectory maps using convolutional neural networks. Proceedings of the 2016 ACM on Multimedia Conference (pp. 102-106). New York, United States: ACM.

Scopus Eid


  • 2-s2.0-84994571080

Ro Full-text Url


  • http://ro.uow.edu.au/cgi/viewcontent.cgi?article=7125&context=eispapers

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers/6095

Has Global Citation Frequency


Start Page


  • 102

End Page


  • 106

Place Of Publication


  • New York, United States

Abstract


  • Recently, Convolutional Neural Networks (ConvNets) have shown promising performances in many computer vision tasks, especially image-based recognition. How to effectively use ConvNets for video-based recognition is still an open problem. In this paper, we propose a compact, effective yet simple method to encode spatiotemporal information carried in 3D skeleton sequences into multiple

    2D images, referred to as Joint Trajectory Maps (JTM), and ConvNets are adopted to exploit the discriminative features for realtime human action recognition. The proposed method has been

    evaluated on three public benchmarks, i.e., MSRC-12 Kinect gesture dataset (MSRC-12), G3D dataset and UTD multimodal human action dataset (UTD-MHAD) and achieved the state-of-the-art results.

UOW Authors


  •   Wang, Pichao (external author)
  •   Li, Zhaoyang (external author)
  •   Hou, Yonghong (external author)
  •   Li, Wanqing

Publication Date


  • 2016

Citation


  • Wang, P., Li, Z., Hou, Y. & Li, W. (2016). Action recognition based on joint trajectory maps using convolutional neural networks. Proceedings of the 2016 ACM on Multimedia Conference (pp. 102-106). New York, United States: ACM.

Scopus Eid


  • 2-s2.0-84994571080

Ro Full-text Url


  • http://ro.uow.edu.au/cgi/viewcontent.cgi?article=7125&context=eispapers

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers/6095

Has Global Citation Frequency


Start Page


  • 102

End Page


  • 106

Place Of Publication


  • New York, United States