About Me
I'm currently a second year PhD student at the College of Engineering and Computer Science, Australian National University and a member of the Computer Vision Research Group at NICTA's Canberra Research Lab. My main research interests are Riemannian geometry, and kernel methods with applications to computer vision. Prof. Richard Hartley is my PhD advisor.
I'm also a committer at The Apache Software Foundation.
My Erdos number is 4 through the following
path.
Sadeep Jayasumana -> Richard Hartley -> Marc Kilgour -> Peter Fishburn
-> Paul Erdős.
Selected Publications
-
M. Harandi, M. Salzmann, S. Jayasumana, R. Hartley, H. Li
Expanding the Family of Grassmannian Kernels: An Embedding Perspective
In European Conference on Computer Vision (ECCV), 2014.
Accepted.
[PDF] [Bibtex] -
S. Jayasumana, R. Hartley, M. Salzmann, H. Li, M. Harandi
Optimizing Over Radial Kernels on Compact Manifolds
In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014.
Oral presentation, Acceptance rate 5.75%.
[PDF] [Bibtex] -
S. Jayasumana, R. Hartley, M. Salzmann, H. Li, M. Harandi
Kernel Methods on the Riemannian Manifold of Symmetric Positive Definite Matrices
In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013.
Oral presentation, Acceptance rate 3.2%.
[PDF] [Presentation] [Code] [Bibtex] -
S. Jayasumana, M. Salzmann, H. Li, M. Harandi
A Framework for Shape Analysis via Hilbert Space Embedding
In IEEE International Conference on Computer Vision (ICCV), 2013.
[PDF] [Bibtex] -
S. Jayasumana, R. Hartley, M. Salzmann, H. Li, M. Harandi
Combining Multiple Manifold-valued Descriptors for Improved Object Recognition
In IEEE International Conference on Digital Image Computing: Techniques and Applications (DICTA), 2013.
Winner of the Best Recognition Paper prize awarded by Canon Information Systems Research Australia (CiSRA).
[PDF] [Bibtex] -
S. Jayasumana, R. Hartley, M. Salzmann, H. Li, M. Harandi
Kernel Methods on Riemannian Manifolds with Gaussian RBF Kernels
Submitted to IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI).