326 citations · 790 across the 29 of their papers we have counts for
43 papers
EarlyBird: Early-Fusion for Multi-View Tracking in the Bird's Eye View
Torben Teepe, Philipp Wolters, Johannes Gilg +2
Multi-view aggregation promises to overcome the occlusion and missed detection challenge in multi-object detection and tracking. Recent approaches in multi-view detection and 3D ob…
Do We Still Need Non-Maximum Suppression? Accurate Confidence Estimates and Implicit Duplication Modeling with IoU-Aware Calibration
Johannes Gilg, Torben Teepe, Fabian Herzog +2
Object detectors are at the heart of many semi- and fully autonomous decision systems and are poised to become even more indispensable. They are, however, still lacking in accessib…
Tackling Face Verification Edge Cases: In-Depth Analysis and Human-Machine Fusion Approach
Martin Knoche, Gerhard Rigoll
Nowadays, face recognition systems surpass human performance on several datasets. However, there are still edge cases that the machine can't correctly classify. This paper investig…
Explainable Model-Agnostic Similarity and Confidence in Face Verification
Martin Knoche, Torben Teepe, Stefan Hörmann +1
Recently, face recognition systems have demonstrated remarkable performances and thus gained a vital role in our daily life. They already surpass human face verification accountabi…
Synthehicle: Multi-Vehicle Multi-Camera Tracking in Virtual Cities
Fabian Herzog, Junpeng Chen, Torben Teepe +3
Smart City applications such as intelligent traffic routing or accident prevention rely on computer vision methods for exact vehicle localization and tracking. Due to the scarcity…
Octuplet Loss: Make Face Recognition Robust to Image Resolution
Martin Knoche, Mohamed Elkadeem, Stefan Hörmann +1
Image resolution, or in general, image quality, plays an essential role in the performance of today's face recognition systems. To address this problem, we propose a novel combinat…