S
Stephen J. Maybank
Researcher at Birkbeck, University of London
Publications - 172
Citations - 17723
Stephen J. Maybank is an academic researcher from Birkbeck, University of London. The author has contributed to research in topics: Video tracking & Motion estimation. The author has an hindex of 50, co-authored 166 publications receiving 15225 citations. Previous affiliations of Stephen J. Maybank include University of Oxford & University of Reading.
Papers
More filters
Journal ArticleDOI
Application of the Fisher-Rao Metric to Structure Detection
TL;DR: The main result is a derivation of an asymptotic approximation to the Fisher-Rao metric, under the assumption that the measurement noise is small, to within the level of accuracy allowed by the measurement errors.
Journal ArticleDOI
Minimum Description Length method for facet matching
TL;DR: The Minimum Description Length (MDL) criterion is used to fit a facet model of a car to an image when the difference image between the car and the background has the greatest compression.
Book ChapterDOI
Ambiguity in reconstruction from image correspondences
TL;DR: In this paper, the ambiguous surfaces are invariant under a rotation through 180° that interchanges the two possible positions for the optical center of the camera taking the second image, and they are subject to a cubic polynomial constraint.
Proceedings ArticleDOI
Non-parametric Hidden Conditional Random Fields for action classification
Natraj Raman,Stephen J. Maybank +1 more
TL;DR: The training and inference procedure is fully Bayesian eliminating the over fitting problem associated with frequentist methods, and the construction is based on scale mixtures of Gaussians as priors over the HCRF parameters and makes use of Hierarchical Dirichlet Process and Laplace distribution.
Journal ArticleDOI
Iteration Functions re-visited
TL;DR: Two classes of Iteration Functions (IFs) are derived from Joseph Traub using a different approach to the authors' and are demonstrably shown to be more informationally efficient than the first.