Augmented reality (AR) has proven to be an invaluable interactive medium to reduce
cognitive load by bridging the gap between the task-at-hand and relevant information by …

End-to-End driving is a promising paradigm as it circumvents the drawbacks associated with
modular systems, such as their overwhelming complexity and propensity for error …

Multi-object tracking (MOT) has been notoriously difficult to evaluate. Previous metrics
overemphasize the importance of either detection or association. To address this, we …

Abstract The problem of Multiple Object Tracking (MOT) consists in following the trajectory of
different objects in a sequence, usually a video. In recent years, with the rise of Deep …

Drones, or general UAVs, equipped with cameras have been fast deployed with a wide
range of applications, including agriculture, aerial photography, and surveillance …

Standardized benchmarks have been crucial in pushing the performance of computer vision
algorithms, especially since the advent of deep learning. Although leaderboards should not …

The ability to detect objects regardless of image distortions or weather conditions is crucial
for real-world applications of deep learning like autonomous driving. We here provide an …

This paper extends the popular task of multi-object tracking to multi-object tracking and
segmentation (MOTS). Towards this goal, we create dense pixel-level annotations for two …

3D multi-object tracking (MOT) is an essential component for many applications such as
autonomous driving and assistive robotics. Recent work on 3D MOT focuses on developing …

Deep learning-based methods for video pedestrian detection and tracking require large
volumes of training data to achieve good performance. However, data acquisition in …