Sciweavers

BMVC
2010
13 years 9 months ago
Object Recognition using 3D SIFT in Complex CT Volumes
The automatic detection of objects within complex volumetric imagery is becoming of increased interest due to the use of dual energy Computed Tomography (CT) scanners as an aviati...
Gregory T. Flitton, Toby P. Breckon, Najla Megherb...
BMVC
2010
13 years 9 months ago
Person Identification using Shadow Analysis
We introduce a novel person identification method for a surveillance system of much wider area than conventional systems using CCTV cameras. In the proposed system, we install cam...
Yumi Iwashita, Adrian Stoica, Ryo Kurazume
BMVC
2010
13 years 9 months ago
Manifold Alignment via Corresponding Projections
In this paper, we propose a novel manifold alignment method by learning the underlying common manifold with supervision of corresponding data pairs from different observation sets...
Deming Zhai, Bo Li, Hong Chang, Shiguang Shan, Xil...
BMVC
2010
13 years 9 months ago
Electoral College and Direct Popular Vote for Multi-Candidate Election
We introduce a stability analysis model for multi-candidate regional and national voting schemes (aka Electoral College and Direct Popular Vote, respectively), which can be expres...
Liang Chen
BMVC
2010
13 years 9 months ago
Learning Directional Local Pairwise Bases with Sparse Coding
Recently, sparse coding has been receiving much attention in object and scene recognition tasks because of its superiority in learning an effective codebook over k-means clusterin...
Nobuyuki Morioka, Shin'ichi Satoh
BMVC
2010
13 years 9 months ago
Image Topic Discovery with Saliency Detection
This work proposes a biologically inspired approach to integrate latent topic model with saliency detection. Firstly, a saliency detection algorithm is presented to discriminate s...
Zhidong Li, Yang Wang, Jing Chen, Jie Xu, John Lai...
BMVC
2010
13 years 9 months ago
Improved Anatomical Landmark Localization in Medical Images Using Dense Matching of Graphical Models
We propose a method for reliably and accurately identifying anatomical landmarks in 3D CT volumes based on dense matching of parts-based graphical models. Such a system can be use...
Vaclav Potesil, Timor Kadir, Günther Platsch,...
BMVC
2010
13 years 9 months ago
Robust Texture Recognition Using Credal Classifiers
Texture classification is used for many vision systems; in this paper we focus on improving the reliability of the classification through the so-called imprecise (or credal) class...
Giorgio Corani, Alessandro Giusti, Davide Migliore...
BMVC
2010
13 years 9 months ago
Person Re-Identification by Support Vector Ranking
Solving the person re-identification problem involves matching observations of individuals across disjoint camera views. The problem becomes particularly hard in a busy public sce...
Bryan Prosser, Wei-Shi Zheng, Shaogang Gong, Tao X...
BMVC
2010
13 years 9 months ago
Background Modelling on Tensor Field for Foreground Segmentation
The paper proposes a new method to perform foreground detection by means of background modeling using the tensor concept. Sometimes, statistical modelling directly on image values...
Rui Caseiro, Jorge Batista, Pedro Martins