Timezone: »

 
Poster
CRF-CNN: Modeling Structured Information in Human Pose Estimation
Xiao Chu · Wanli Ouyang · hongsheng Li · Xiaogang Wang

Wed Dec 07 09:00 AM -- 12:30 PM (PST) @ Area 5+6+7+8 #127 #None
in Wednesday Posters »

Deep convolutional neural networks (CNN) have achieved great success. On the other hand, modeling structural information has been proved critical in many vision problems. It is of great interest to integrate them effectively. In a classical neural network, there is no message passing between neurons in the same layer. In this paper, we propose a CRF-CNN framework which can simultaneously model structural information in both output and hidden feature layers in a probabilistic way, and it is applied to human pose estimation. A message passing scheme is proposed, so that in various layers each body joint receives messages from all the others in an efficient way. Such message passing can be implemented with convolution between features maps in the same layer, and it is also integrated with feedforward propagation in neural networks. Finally, a neural network implementation of end-to-end learning CRF-CNN is provided. Its effectiveness is demonstrated through experiments on two benchmark datasets.

Keywords: Deep Learning or Neural Networks · Structured Prediction · (Application) Computer Vision · (Application) Object and Pattern Recognition

Author Information

Xiao Chu (Cuhk)
Wanli Ouyang (The Chinese University of Hong Kong)
hongsheng Li (cuhk)
Xiaogang Wang (Chinese University of Hong Kong)

More from the Same Authors