Adversarial PoseNet: a structure-aware convolutional network for human pose estimation

Date

2017

Authors

Chen, Y.
Shen, C.
Wei, X.
Liu, L.
Yang, J.

Editors

Advisors

Journal Title

Journal ISSN

Volume Title

Type:

Conference paper

Citation

Proceedings / IEEE International Conference on Computer Vision. IEEE International Conference on Computer Vision, 2017, vol.2017, pp.1221-1230

Statement of Responsibility

Yu Chen, Chunhua Shen, Xiu-Shen Wei, Lingqiao Liu, Jian Yang

Conference Name

IEEE International Conference on Computer Vision (ICCV 2017) (22 Oct 2017 - 29 Oct 2017 : Venice, ITALY)

Abstract

For human pose estimation in monocular images, joint occlusions and overlapping upon human bodies often result in deviated pose predictions. Under these circumstances, biologically implausible pose predictions may be produced. In contrast, human vision is able to predict poses by exploiting geometric constraints of joint inter-connectivity. To address the problem by incorporating priors about the structure of human bodies, we propose a novel structure-aware convolutional network to implicitly take such priors into account during training of the deep network. Explicit learning of such constraints is typically challenging. Instead, we design discriminators to distinguish the real poses from the fake ones (such as biologically implausible ones). If the pose generator (G) generates results that the discriminator fails to distinguish from real ones, the network successfully learns the priors.,,To better capture the structure dependency of human body joints, the generator G is designed in a stacked multi-task manner to predict poses as well as occlusion heatmaps. Then, the pose and occlusion heatmaps are sent to the discriminators to predict the likelihood of the pose being real. Training of the network follows the strategy of conditional Generative Adversarial Networks (GANs). The effectiveness of the proposed network is evaluated on two widely used human pose estimation benchmark datasets. Our approach significantly outperforms the state-of-the-art methods and almost always generates plausible human pose predictions.

School/Discipline

Dissertation Note

Provenance

Description

Access Status

Rights

© 2017 IEEE

License

Grant ID

Call number

Persistent link to this record