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):

Optimizing Over a Set of Manifolds

J. Gall, A. Yao and L. Van Gool
271, 2010
Computer Vision Lab, ETH Zuerich


3D human pose estimation in multi-view settings benefits from embeddings of human actions in low-dimensional manifolds, but the complexity of the embeddings increases with the number of actions. Creating separate, action-specific manifolds seems to be a more practical solution. Using multiple manifolds for pose estimation, however, requires a joint optimization over the set of manifolds and the human pose embedded in the manifolds. In order to solve this problem, we propose a particle-based optimization algorithm that can efficiently estimate human pose even in challenging in-house scenarios. We give a comprehensive description of the algorithm proposed in ``2D Action Recognition Serves 3D Human Pose Estimation''.

Download in pdf format
  author = {J. Gall and A. Yao and L. Van Gool},
  title = {Optimizing Over a Set of Manifolds},
  year = {2010},
  month = {June},
  number = {271},
  institution = {Computer Vision Lab, ETH Zuerich},
  keywords = {optimization, human pose estimation, dimensionality reduction, action recognition}