S
Stephen J. Maybank
Researcher at Birkbeck, University of London
Publications - Â 172
Citations - Â 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
Action classification using a discriminative multilevel HDP-HMM
Natraj Raman,Stephen J. Maybank +1 more
TL;DR: Experiments with two different datasets show that action class models learnt using the HDP-HMM technique produce good classification results.
Journal ArticleDOI
Human Behavior Analysis Based on a New Motion Descriptor
TL;DR: A novel motion descriptor, which is an improved feature based on optical flow, is proposed for motion representation that is improved with a motion filter, and feature fusion with the shape and trajectory information.
Journal ArticleDOI
Visible and infrared image registration based on region features and edginess
TL;DR: This paper presents a coarse-to-fine procedure for registering visible and infrared images based on stable region features and edginess and shows that the proposed method provides more robust and accurate registration than the existing methods.
Book ChapterDOI
Leukocyte Recognition Using EM-Algorithm
TL;DR: This document describes a method for classifying images of blood cells using the maximum a posteriori decision rule using three different classes of cells: Band Neutrophils, Eosinophils and Lymphocytes.
Journal ArticleDOI
Modeling Geometric-Temporal Context With Directional Pyramid Co-Occurrence for Action Recognition
TL;DR: The proposed modified covariance descriptor under the log-Euclidean Riemannian metric to represent the spatio-temporal cuboids detected in the video sequences improves on the recognition performance of the bag-of-visual-words models by a large margin on six public data sets.