We combine and extend the previous work on DCT-based image signatures and face detection to determine the visual saliency. To this end, we transfer the scalar definition of image...
In sports broadcasts, networks consisting of pan-tiltzoom (PTZ) cameras usually exhibit very wide baselines, making standard matching techniques for camera calibration very hard t...
Jens Puwein, Remo Ziegler, Luca Ballan, Marc Polle...
A convenient way of analysing Riemannian manifolds is to embed them in Euclidean spaces, with the embedding typically obtained by flattening the manifold via tangent spaces. This...
We introduce the Longterm Observation of Scenes (with Tracks) dataset. This dataset comprises videos taken from streaming outdoor webcams, capturing the same half hour, each day, ...
Austin Abrams, Jim Tucek, Joshua Little, Nathan Ja...
Human movements are important cues for recognizing human actions, which can be captured by explicit modeling and tracking of actor or through space-time low-level features. Howeve...
We propose an online algorithm based on local sparse representation for robust object tracking. Local image patches of a target object are represented by their sparse codes with a...
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 tempor...
We present a new approach for activity modelling and anomaly detection based on non-parametric Gaussian Process (GP) models. Specifically, GP regression models are formulated to l...