In this work we consider the problem of binary classification where the classifier may abstain instead of classifying each observation, leaving the critical items for human evaluat...
This paper presents a multi-frame data association algorithm for tracking multiple targets in video sequences. Multi-frame data association involves finding the most probable corr...
The OKKAM initiative1 has recently highlighted the need of moving from the traditional web towards a "web of entities", where real-world objects descriptions could be ret...
Planning and optimizing urban traffic is a difficult problem, with considerable economic and social impacts. The development of suitable software tools to aid municipal governments...
Within the field of action recognition, features and descriptors are often engineered to be sparse and invariant to transformation. While sparsity makes the problem tractable, it ...