Projects per year
Abstract
This paper presents generalized Laplacian eigenmaps, a novel dimensionality reduction approach designed to address stylistic variations in time series. It generates compact and coherent continuous spaces whose geometry is data-driven. This paper also introduces graph-based particle filter, a novel methodology conceived for efficient tracking in low dimensional space derived from a spectral dimensionality reduction method. Its strengths are a propagation scheme, which facilitates the prediction in time and style, and a noise model coherent with the manifold, which prevents divergence, and increases robustness. Experiments show that a combination of both techniques achieves state-of-the-art performance for human pose tracking in underconstrained scenarios.
Original language | English |
---|---|
Pages (from-to) | 1646-1660 |
Number of pages | 15 |
Journal | IEEE Transactions on Cybernetics |
Volume | 44 |
Issue number | 9 |
Early online date | 11 Dec 2013 |
DOIs | |
Publication status | Published - Sep 2014 |
Fingerprint Dive into the research topics of 'Generalized Laplacian Eigenmaps for Modeling and Tracking Human Motions'. Together they form a unique fingerprint.
Projects
- 1 Finished
-
R1118ECI: Centre for Secure Information Technologies (CSIT)
McCanny, J. V., Cowan, C., Crookes, D., Fusco, V., Linton, D., Liu, W., Miller, P., O'Neill, M., Scanlon, W. & Sezer, S.
01/08/2009 → 30/06/2014
Project: Research