Lifted Disjoint Paths with Application in Multiple Object Tracking
Jul 12, 2020
Speakers
Andrea Hornakova
Speaker · 0 followers
Roberto Henschel
Speaker · 0 followers
Bodo Rosenhahn
Speaker · 0 followers
Paul Swoboda
Speaker · 0 followers
About
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 multicommodity flow and 3-SAT. To enable practical global optimization, we propose several classes of linear inequalities that produce a high-quality LP-relaxation. Additionally, we propose efficient cutting plane algorithms for separating the proposed linear inequalities. The lifted disjoint path problem is a natural model for multiple object tracking and allows an elegant mathematical formulation for long-range temporal interactions. Lifted edges help to prevent id switches and to re-identify persons. Our lifted disjoint paths tracker leads on all three main benchmarks of the MOT challenge, improving significantly over state-of-the-art.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 multicommodity flow and 3-SAT. To enable practical global optimization, we propose several classes of linear inequalities that produce a high-quality LP-relaxation. Additionally, we propose efficient cutting plane algorithms for…
Categories
AI & Data Science
Category · 10.8k presentations
About ICML 2020
The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics. ICML is one of the fastest growing artificial intelligence conferences in the world. Participants at ICML span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Dual Mirror Descent for Online Allocation Problems
Watch later
Online Probabilistic Label Trees (OPLTs)
Watch later
Explicit Gradient Learning for Black-Box Optimization
Watch later
Causal Modeling for Fairness In Dynamical Systems
Watch later
Continuous Graph Neural Networks
Watch later
