Meeting ID: 862 3823 3298
Title: Shifting paradigms in multi-object tracking
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, which proposes to split the problems into two subtasks: detection and data association. In this talk, I will discuss the shift towards more recent learning-based paradigms, most notably, tracking-by-regression, and the rise of a new paradigm: tracking-by-attention. I will focus on the problems in current MOT algorithms and the need to focus on merging the detection and the data association tasks. At the end of the talk, I will show a glimpse of my view of the future of MOT.
Bio: Prof. Dr. Laura Leal-Taixé is a tenure-track professor (W2) at the Technical University of Munich, leading the Dynamic Vision and Learning group. Since 2021, she is also a Principal Scientist at Argo AI. She is a recipient of the Sofja Kovalevskaja Award and the Google Faculty Award. Her research interests are dynamic scene understanding, including multi object tracking and video segmentation, and visual localization.