Andrea Hornakova — accepted AI-conference papers

2021

Making Higher Order MOT Scalable: An Efficient Approximate Solver for Lifted Disjoint Paths

Andrea Hornakova, Timo Kaiser, Paul Swoboda, Michal Rolinek, Bodo Rosenhahn, Roberto Henschel

ICCV 2021poster

We present an efficient approximate message passing solver for the lifted disjoint paths problem (LDP), a natural but NP-hard model for multiple object tracking (MOT). Our tracker scales to very large instances that come from long and crowded MOT sequences. Our approximate solver enables us to proce…

Cited by 45 PDF ↗code ↗Scholar ↗

2020

Lifted Disjoint Paths with Application in Multiple Object Tracking

Andrea Hornakova, Roberto Henschel, Bodo Rosenhahn, Paul Swoboda

ICML 2020poster

We present an extension to the disjoint paths problem in which additional lifted edges are introduced to provide path connectivity priors. We call the resulting optimization problem the lifted disjoint paths problem. We show that this problem is NP-hard by reduction from integer multicommodity flow…

Cited by 159 Source ↗PDF ↗code ↗Scholar ↗