Modern visual object tracking

We will start with single-target visual tracking methods and explore the paradigm of tracking as detection and correlation filters. Then we will continue with early deep-learning methods and more recent methods based on transformer architectures. We will look at multi-object tracking and explore the role of segmentation in tracking. The last part of the course will be dedicated to empirical evaluation, we will explore the challenges of designing a suitable evaluation methodology and observe the role of VOT initiative. The course will conclude with a practical session where we will learn how to evaluate tracking algorithms on a benchmark dataset or on a dataset of their own choice.