Sciweavers

519 search results - page 58 / 104
» Object Detection using Background Context
Sort
View
PR
2011
12 years 10 months ago
Detecting and discriminating behavioural anomalies
This paper aims to address the problem of anomaly detection and discrimination in complex behaviours, where anomalies are subtle and difficult to detect owing to the complex tempo...
Chen Change Loy, Tao Xiang, Shaogang Gong
ACIVS
2006
Springer
13 years 11 months ago
Constrained Region-Growing and Edge Enhancement Towards Automated Semantic Video Object Segmentation
Most existing object segmentation algorithms suffer from a so-called under-segmentation problem, where parts of the segmented object are missing and holes often occur inside the ob...
L. Gao, J. Jiang, S. Y. Yang
FGR
2000
IEEE
163views Biometrics» more  FGR 2000»
14 years 4 days ago
Tracking Interacting People
A computer vision system for tracking multiple people in relatively unconstrained environments is described. Trackerformed at three levels of abstraction: regions, people and grou...
Stephen J. McKenna, Sumer Jabri, Zoran Duric, Harr...
CVPR
2005
IEEE
14 years 9 months ago
Generative versus Discriminative Methods for Object Recognition
Many approaches to object recognition are founded on probability theory, and can be broadly characterized as either generative or discriminative according to whether or not the di...
Ilkay Ulusoy, Christopher M. Bishop
IROS
2007
IEEE
157views Robotics» more  IROS 2007»
14 years 2 months ago
A spatio-temporal probabilistic model for multi-sensor object recognition
— This paper presents a general framework for multi-sensor object recognition through a discriminative probabilistic approach modelling spatial and temporal correlations. The alg...
Bertrand Douillard, Dieter Fox, Fabio T. Ramos