This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Search for Publication

Year(s) from:  to 
Keywords (separated by spaces):

Learning Probabilistic Non-Linear Latent Variable Models for Tracking Complex Activities

A. Yao, J. Gall, L. Van Gool, and R. Urtasun
Neural Information Processing Systems (NIPS)


A common approach for handling the complexity and inherent ambiguities of 3D human pose estimation is to use pose priors learned from training data. Existing approaches however, are either too simplistic (linear), too complex to learn, or can only learn latent spaces from ``simple data'', i.e., single activities such as walking or running. In this paper, we present an efficient stochastic gradient descent algorithm that is able to learn probabilistic non-linear latent spaces composed of multiple activities. Furthermore, we derive an incremental algorithm for the online setting which can update the latent space without extensive relearning. We demonstrate the effectiveness of our approach on the task of monocular and multi-view tracking and show that our approach outperforms the state-of-the-art.

Download in pdf format
  author = {A. Yao and J. Gall and L. Van Gool and and R. Urtasun},
  title = {Learning Probabilistic Non-Linear Latent Variable Models for Tracking Complex Activities},
  booktitle = {Neural Information Processing Systems (NIPS)},
  year = {2011},
  keywords = {}