An Efficient Convolutional Network for Human Pose Estimation
Umer Rafi, Bastian Leibe, Juergen Gall and Ilya Kostrikov
Abstract
In recent years, human pose estimation has greatly benefited from deep learning and huge gains in performance have been achieved. The trend to maximise the accuracy on benchmarks, however, resulted in computationally expensive deep network architectures that require expensive hardware and pre-training on large datasets. This makes it difficult to compare different methods and to reproduce existing results. In this paper, we therefore propose an efficient deep network architecture that can be efficiently trained on mid-range GPUs without the need of any pre-training. Despite the low computational requirements of our network, it is on par with much more complex models on popular benchmarks for human pose estimation.
Session
Posters 2
Files
Extended Abstract (PDF, 2M)
Paper (PDF, 2M)
DOI
10.5244/C.30.109
https://dx.doi.org/10.5244/C.30.109
Citation
Umer Rafi, Bastian Leibe, Juergen Gall and Ilya Kostrikov. An Efficient Convolutional Network for Human Pose Estimation. In Richard C. Wilson, Edwin R. Hancock and William A. P. Smith, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 109.1-109.11. BMVA Press, September 2016.
Bibtex
@inproceedings{BMVC2016_109,
title={An Efficient Convolutional Network for Human Pose Estimation},
author={Umer Rafi, Bastian Leibe, Juergen Gall and Ilya Kostrikov},
year={2016},
month={September},
pages={109.1-109.11},
articleno={109},
numpages={11},
booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
publisher={BMVA Press},
editor={Richard C. Wilson, Edwin R. Hancock and William A. P. Smith},
doi={10.5244/C.30.109},
isbn={1-901725-59-6},
url={https://dx.doi.org/10.5244/C.30.109}
}