Search Results for author: Jannis Stoppe

Found 3 papers, 3 papers with code

UTrack: Multi-Object Tracking with Uncertain Detections

1 code implementation30 Aug 2024 Edgardo Solano-Carrillo, Felix Sattler, Antje Alex, Alexander Klein, Bruno Pereira Costa, Angel Bueno Rodriguez, Jannis Stoppe

The tracking-by-detection paradigm is the mainstream in multi-object tracking, associating tracks to the predictions of an object detector.

Autonomous Driving Multi-Object Tracking +3

Learning Representative Trajectories of Dynamical Systems via Domain-Adaptive Imitation

1 code implementation19 Apr 2023 Edgardo Solano-Carrillo, Jannis Stoppe

Domain-adaptive trajectory imitation is a skill that some predators learn for survival, by mapping dynamic information from one domain (their speed and steering direction) to a different domain (current position of the moving prey).

Deep Reinforcement Learning Diversity +2

Look ATME: The Discriminator Mean Entropy Needs Attention

1 code implementation18 Apr 2023 Edgardo Solano-Carrillo, Angel Bueno Rodriguez, Borja Carrillo-Perez, Yannik Steiniger, Jannis Stoppe

To restore the information symmetry, the generator is endowed with knowledge of the entropic state of the discriminator, which is leveraged to allow the adversarial game to converge towards equilibrium.

Denoising Image-to-Image Translation

Cannot find the paper you are looking for? You can Submit a new open access paper.