Many approaches can track objects moving in sequences of images but can su er in occlusion and noise, and often require initialisation. These factors can be handled by techniques ...
We introduce a new large-scale video dataset designed to assess the performance of diverse visual event recognition algorithms with a focus on continuous visual event recognition ...
Sangmin Oh, Anthony Hoogs, A.G.Amitha Perera, Chia...
While computing power and transmission bandwidth have both been steadily increasing over the last few years, bandwidth rather than processing power remains the primary bottleneck f...
This paper presents a Bayesian framework for multi-cue 3D object tracking of deformable objects. The proposed spatio-temporal object representation involves a set of distinct linea...
This paper describes the continuing development of a system for tracking multiple man made objects, (typically vehicles) moving in a natural open world scene, where the detected m...