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
Approximation to the Fisher-Rao metric for the focus of expansion
TL;DR: The Fisher-Rao metric for the focus of expansion is approximated, under the assumption that the focus is estimated from correspondences between two images taken by a translating camera, if the errors in the image correspondences are small.
Proceedings 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.
Journal ArticleDOI
A Filter with a Guaranteed Asymptotic Performance
TL;DR: The asymptotic filter as mentioned in this paper is a suboptimal approximation to the Kalman filter that preserves the ability to estimate the expected values of functions to an accuracy of O( λ -2 ).
Self-taught semi-supervised dictionary learning with non-negative constraint
TL;DR: A novel unified framework termed self-taught semisupervised dictionary learning with non-negative constraint (NNST-SSDL) is proposed for simultaneously optimizing the components of a dictionary and a graph Laplacian.
Journal ArticleDOI
Learning to Explore Distillability and Sparsability: A Joint Framework for Model Compression
TL;DR: A dynamically distillability-and-sparsability learning framework (DDSL) is introduced for model compression and outperforms 24 state-of-the-art methods, including both knowledge distillation and filter pruning methods.