From handcrafted to end-to-end learning, and back: a journey for multi-object tracking

The challenging task of multi-object tracking (MOT) requires simultaneous reasoning about track initialization, identity, and spatiotemporal trajectories. This problem has been traditionally addressed with the tracking-by-detection paradigm, but recent research has focused on more recent end-to-end learning paradigms such as tracking-by-regression or tracking-by-attention. In this talk I will discuss all the paradigms shifts only to circle back right where we started, tracking-by-detection. Can this paradigm be state-of-the-art?