Seminar "From Handcrafted to End-to-End Learning, and Back: a Journey far Multi-Object Tracking" - Laura Leal-Taixé - GENDER UNBALANCED AI
On Friday, December 2nd, at 2:15 p.m., Laura Leal-Taixé (NVIDIA, Technical University of Munich) will give a talk on "From Handcrafted to End-to-End Learning, and Back: a Journey far Multi-Object Tracking". The event is organized as part of a cycle of seminars "GENDER UNBALANCED AI" and will be held at the Sala Eventi Tecnopolo (Building 52) of the Engineering Department "Enzo Ferrari".
Web streaming: link.
Abstract
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 leaming 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?
More information here.