Subspace Regression: Predicting a Subspace from One Sample
People
- Minyoung Kim
- Zengyin Zhang
- Fernando de la Torre
- Wende Zhang
Abstract
Subspace methods have been extensively used to solve a variety of problems
in computer vision including object detection, recognition, and tracking.
Typically subspaces are learned from a training set that contains different
configurations of a particular object (e.g., variations on shape and
appearance). However, in some situations it is not possible to have access to
data with multiple configurations of the object. For instance, consider the
problem of building a person-specific subspace of the pose variation by having
the only frontal face. We refer to this problem as subspace regression.
Subspace regression is a challenging problem for two main reasons: (i) it
involves a mapping between high-dimensional spaces, (ii) it is unclear how to
parameterize the mapping between one sample and a subspace. We propose four
methods to learn a mapping from one sample to a subspace: Individual Mapping on
Images, Direct Mapping to Subspaces, Regression on Subspaces, and Direct
Subspace Alignment. We show the validity of our approaches in predicting a
person-specific face subspace of pose or illumination, and its applications to
face recognition and tracking.
Citation
|
Minyoung Kim, Zengyin Zhang, Fernando de la Torre and Wende Zhang
Subspace Regression: Predicting a Subspace from One Sample Asian Conference on Computer Vision (ACCV), 2010 [PDF] [Bibtex] |
Results
Acknowledgements and Funding
This research is supported by:
Copyright notice
| Human Sensing Lab |