In this case, the source/target domains are represented in the form of subspaces, which are treated as points on the Grassmann manifold.
In particular, acquiring ground truth 3D shapes of objects pictured in 2D images remains a challenging feat and this has hampered progress in recognition-based object reconstruction from a single image.
In many datasets, the samples are related by a known image transformation, such as rotation, or a repeatable non-rigid deformation.
We address the problem of populating object category detection datasets with dense, per-object 3D reconstructions, bootstrapped from class labels, ground truth figure-ground segmentations and a small set of keypoint annotations.
Interestingly, for linear regression our formulation is equivalent to a correlation filter, used by some of the fastest competitive trackers.
In the past few years there has been a growing interest on geometric frameworks to learn supervised classification models on Riemannian manifolds [31, 27].