Learning human pose estimation features with convolutional networks

This paper introduces a new architecture for human pose estimation using a multi-layer convolutional network architecture and a modified learning technique that learns low-level features and a higher-level weak spatial model. Unconstrained human pose estimation is one of the hardest problems in computer vision, and our new architecture and learning schema shows improvement over the current state-of-the-art. The main contribution of this paper is showing, for the first time, that a specific variation of deep learning is able to meet the performance, and in many cases outperform, existing traditional architectures on this task. The paper also discusses several lessons learned while researching alternatives, most notably, that it is possible to learn strong low-level feature detectors on regions that might only cover a few pixels in the image. Higher-level spatial models improve somewhat the overall result, but to a much lesser extent than expected. Many researchers previously argued that the kinematic structure and top-down information are cru-cial for this domain, but with our purely bottom-up, and weak spatial model, we improve on other more complicated architectures that currently produce the best results. This echos what many other researchers, like those in the speech recogni-tion, object recognition, and other domains have experienced [26]. Figure 1: The green cross is our new technique’s wrist locator, the red cross is the state-of-the-art CVPR13 MODEC detector [38] on the FLIC database.