Recurrent Human Pose Estimation

Belagiannis V, Zisserman A (2017)

Publication Type: Conference contribution

Publication year: 2017

Publisher: Institute of Electrical and Electronics Engineers Inc.

Pages Range: 468-475

Conference Proceedings Title: Proceedings - 12th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2017 - 1st International Workshop on Adaptive Shot Learning for Gesture Understanding and Production, ASL4GUP 2017, Biometrics in the Wild, Bwild 2017, Heterogeneous Face Recognition, HFR 2017, Joint Challenge on Dominant and Complementary Emotion Recognition Using Micro Emotion Features and Head-Pose Estimation, DCER and HPE 2017 and 3rd Facial Expression Recognition and Analysis Challenge, FERA 2017

Event location: Washington, DC US

ISBN: 9781509040230

DOI: 10.1109/FG.2017.64

Abstract

We propose a ConvNet model for predicting 2D human body poses in an image. The model regresses a heatmap representation for each body keypoint, and is able to learn and represent both the part appearances and the context of the part configuration. We make the following three contributions: (i) an architecture combining a feed forward module with a recurrent module, where the recurrent module can be run iteratively to improve the performance; (ii) the model can be trained end-to-end and from scratch, with auxiliary losses incorporated to improve performance; (iii) we investigate whether keypoint visibility can also be predicted. The model is evaluated on two benchmark datasets. The result is a simple architecture that achieves performance on par with the state of the art, but without the complexity of a graphical model stage (or layers).

Authors with CRIS profile

Vasileios Belagiannis

Involved external institutions

University of Oxford GB United Kingdom (GB)

How to cite

APA:

Belagiannis, V., & Zisserman, A. (2017). Recurrent Human Pose Estimation. In Proceedings - 12th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2017 - 1st International Workshop on Adaptive Shot Learning for Gesture Understanding and Production, ASL4GUP 2017, Biometrics in the Wild, Bwild 2017, Heterogeneous Face Recognition, HFR 2017, Joint Challenge on Dominant and Complementary Emotion Recognition Using Micro Emotion Features and Head-Pose Estimation, DCER and HPE 2017 and 3rd Facial Expression Recognition and Analysis Challenge, FERA 2017 (pp. 468-475). Washington, DC, US: Institute of Electrical and Electronics Engineers Inc..

MLA:

Belagiannis, Vasileios, and Andrew Zisserman. "Recurrent Human Pose Estimation." Proceedings of the 12th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2017, Washington, DC Institute of Electrical and Electronics Engineers Inc., 2017. 468-475.

BibTeX: Download