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
Posted Content
Wide-angle Image Rectification: A Survey.
TL;DR: This paper comprehensively survey progress in wide-angle image rectification from transformation models to rectification methods, evaluating the performance of state-of-the-art methods on public datasets and showing that although both kinds of methods can achieve good results, these methods only work well for specific camera models and distortion types.
Book Chapter
Fisher-Rao metric
TL;DR: The information in a mass of data is summarised by fitting to the data a probability density function chosen from a parameterised family of pdfs, which provides a measure of the accuracy with which parameter values can be estimated from the data.
Journal ArticleDOI
Robust Face Alignment via Deep Progressive Reinitialization and Adaptive Error-driven Learning.
TL;DR: Zhang et al. as mentioned in this paper proposed a deep regression architecture with progressive reinitialization and a new error-driven learning loss function to explicitly address the issues related to the initial alignment estimation and the final learning objective.
Journal ArticleDOI
Fisher information and model selection for projective transformations of the line
TL;DR: The Fisher information and the Rao measure are obtained in closed form for a family of probability density functions parametrized by the manifold PSL(2, R) of projective transformations of t... as mentioned in this paper.
Journal ArticleDOI
Handcrafted vs. learned representations for human action recognition [Editorial]
TL;DR: Both feature learning and feature engineering have their advantages in visual representation which, however, remains less explored in the video domain for action recognition.