Multiple Instance Learning (MIL) has been widely exploited in many computer vision tasks, such as image retrieval, object tracking and so on. To handle ambiguity of instance label...
Active learning aims to reduce the amount of labels required for classification. The main difficulty is to find a good trade-off between exploration and exploitation of the lab...
Existing object tracking algorithms generally use some form of local optimisation, assuming that an object's position and shape change smoothly over time. In some situations ...
A critical success factor for the reuse of learning objects is the ease by which they may be repurposed in order to enable reusability in a different teaching context from which th...
This paper presents a simple but robust visual tracking algorithm based on representing the appearances of objects using affine warps of learned linear subspaces of the image spac...