We describe a method for recovering 3D human body pose from silhouettes. Our model is based on learning a latent space using the Gaussian Process Latent Variable Model (GP-LVM) [1]...
Carl Henrik Ek, Philip H. S. Torr, Neil D. Lawrenc...
Current approaches to pose estimation and tracking can be classified into two categories: generative and discriminative. While generative approaches can accurately determine human...
Abhinav Gupta, Trista Chen, Francine Chen, Don Kim...
Abstract. Learned, activity-specific motion models are useful for human pose and motion estimation. Nevertheless, while the use of activityspecific models simplifies monocular t...
Discriminative approaches for human pose estimation model the functional mapping, or conditional distribution, between image features and 3D pose. Learning such multi-modal models ...
Tracking 3D people from monocular video is often poorly constrained. To mitigate this problem, prior knowledge should be exploited. In this paper, the Gaussian process spatio-temp...