Arbitrary View Action Recognition via Transfer Dictionary Learning on Synthetic Training Data

Arbitrary View Action Recognition via Transfer Dictionary Learning on Synthetic Training Data

Abstract

Human action recognition is an important problem in robotic vision. Traditional recognition algorithms usually require the knowledge of view angle, which is not always available in robotic applications such as active vision. In this paper, we propose a new framework to recognize actions with arbitrary views. A main feature of our algorithm is that view-invariance is learned from synthetic 2D and 3D training data using transfer dictionary learning. This guarantees the availability of training data, and removes the hassle of obtaining real world video in specific viewing angles. The result of the process is a dictionary that can project real world 2D video into a view-invariant sparse representation. This facilitates the training of a view-invariant classifier. Experimental results on the IXMAS and N-UCLA datasets show significant improvements over existing algorithms.

Publication

Jingtian Zhang, Lining Zhang, Hubert P. H. Shum and Ling Shao,
"Arbitrary View Action Recognition via Transfer Dictionary Learning on Synthetic Training Data",
Proceedings of the 2016 IEEE International Conference on Robotics and Automation (ICRA)

Citation=2##

## Citation count from Google Scholar as of 2018

Downloads

YouTube

References

BibTeX

@inproceedings{zhang16arbitrary,
 author={Zhang, Jingtian and Zhang, Lining and Shum, Hubert P. H. and Shao, Ling},
 booktitle={Proceedings of the 2016 IEEE International Conference on Robotics and Automation},
 series={ICRA '16},
 title={Arbitrary View Action Recognition via Transfer Dictionary Learning on Synthetic Training Data},
 year={2016},
 month={May},
 pages={1678--1684},
 numpages={8},
 doi={10.1109/ICRA.2016.7487309},
 publisher={IEEE},
 location={Stockholm, Sweden},
}

EndNote/RefMan

TY  - CONF
AU  - Zhang, Jingtian
AU  - Zhang, Lining
AU  - Shum, Hubert P. H.
AU  - Shao, Ling
T2  - Proceedings of the 2016 IEEE International Conference on Robotics and Automation
TI  - Arbitrary View Action Recognition via Transfer Dictionary Learning on Synthetic Training Data
PY  - 2016
Y1  - May 2016
SP  - 1678
EP  - 1684
DO  - 10.1109/ICRA.2016.7487309
PB  - IEEE
ER  - 

Plain Text

Jingtian Zhang, Lining Zhang, Hubert P. H. Shum and Ling Shao, "Arbitrary View Action Recognition via Transfer Dictionary Learning on Synthetic Training Data," in ICRA '16: Proceedings of the 2016 IEEE International Conference on Robotics and Automation, pp. 1678-1684, Stockholm, Sweden, IEEE, May 2016.

Similar Research

 

         

Last update: 10/03/2019