Action Recognition Based on Joint Trajectory Maps Using Convolutional Neural Networks

@inproceedings{Wang2016ActionRB,
  title={Action Recognition Based on Joint Trajectory Maps Using Convolutional Neural Networks},
  author={Pichao Wang and Zhaoyang Li and Yonghong Hou and Wanqing Li},
  booktitle={MM '16},
  year={2016}
}
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 spatio-temporal 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… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 115 CITATIONS

3D action recognition using data visualization and convolutional neural networks

VIEW 14 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Multiview-Based 3-D Action Recognition Using Deep Networks

VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS

Skeleton based action recognition using pose change map and convolutional neural networks

VIEW 3 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

3D skeleton based action recognition by video-domain translation-scale invariant mapping and multi-scale dilated CNN

VIEW 10 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Skeleton-Based Human Action Recognition Using Spatial Temporal 3D Convolutional Neural Networks

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

3D CNNs on Distance Matrices for Human Action Recognition

VIEW 9 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2016
2020

CITATION STATISTICS

  • 18 Highly Influenced Citations

  • Averaged 36 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-4 OF 4 REFERENCES

UTD-MHAD: A multimodal dataset for human action recognition utilizing a depth camera and a wearable inertial sensor

VIEW 11 EXCERPTS
HIGHLY INFLUENTIAL

G3D: A gaming action dataset and real time action recognition evaluation framework

VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL