Combining multiple manifold-valued descriptors for improved object recognition
We present a learning method for classification using multiple manifold-valued features. Manifold techniques are becoming increasingly popular in computer vision since Riemannian geometry often comes up as a natural model for many descriptors encountered
|Collections||ANU Research Publications|
|Source:||2013 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2013|
|01_Hirimbura Matara (Jayasumana)_Combining_multiple_2013.pdf||1.02 MB||Adobe PDF||Request a copy|
|02_Hirimbura Matara (Jayasumana)_Combining_multiple_2013.pdf||30.03 kB||Adobe PDF||Request a copy|
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.