Skip navigation
Skip navigation

Combining multiple manifold-valued descriptors for improved object recognition

Hirimbura Matara (Jayasumana), Gayan (Sadeep); Hartley, Richard; Salzmann, Mathieu; Li, Hongdong; Harandi, Mehrtash T.


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

CollectionsANU Research Publications
Date published: 2013
Type: Conference paper
Source: 2013 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2013
DOI: 10.1109/DICTA.2013.6691493


File Description SizeFormat Image
01_Hirimbura Matara (Jayasumana)_Combining_multiple_2013.pdf1.02 MBAdobe PDF    Request a copy
02_Hirimbura Matara (Jayasumana)_Combining_multiple_2013.pdf30.03 kBAdobe PDF    Request a copy

Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  22 January 2019/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator