@inproceedings{HoKardoostPfreundtetal.2020,
  author    = {Kalun Ho and Amirhossein Kardoost and Franz-Josef Pfreundt and Janis Keuper and Margret Keuper},
  title     = {A Two-Stage Minimum Cost Multicut Approach to Self-Supervised Multiple Person Tracking},
  series = {ACCV 2020: Computer Vision – ACCV 2020},
  volume    = {LNCS 12623},
  publisher = {Springer},
  address   = {Cham},
  isbn      = {978-3-030-69531-6 (Print)},
  pages     = {539 -- 557},
  year      = {2020},
  abstract  = {Multiple Object Tracking (MOT) is a long-standing task in computer vision. Current approaches based on the tracking by detection paradigm either require some sort of domain knowledge or supervision to associate data correctly into tracks. In this work, we present a self-supervised multiple object tracking approach based on visual features and minimum cost lifted multicuts. Our method is based on straight-forward spatio-temporal cues that can be extracted from neighboring frames in an image sequences without supervision. Clustering based on these cues enables us to learn the required appearance invariances for the tracking task at hand and train an AutoEncoder to generate suitable latent representations. Thus, the resulting latent representations can serve as robust appearance cues for tracking even over large temporal distances where no reliable spatio-temporal features can be extracted. We show that, despite being trained without using the provided annotations, our model provides competitive results on the challenging MOT Benchmark for pedestrian tracking.},
  language  = {en}
}