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...
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...
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...
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...
— This paper presents a general framework for multi-sensor object recognition through a discriminative probabilistic approach modelling spatial and temporal correlations. The alg...