Recurrent human pose estimation

Conference item

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: Belagiannis, V; Zisserman, A

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Institute of Electrical and Electronics Engineers
• Host title: 12th IEEE Conference on Automatic Face and Gesture Recognition
• Journal: 12th IEEE Conference on Automatic Face and Gesture Recognition
• Publication date: 2017-06-01
• Acceptance date: 2016-10-10
• Event location: Washington DC
• DOI: 10.1109/FG.2017.64