The deep learning technique has proven to be effective in the classification and localization
of objects on the image or ground plane over time. The strength of the technique's features …

The challenging task of multi-object tracking (MOT) requires simultaneous reasoning about
track initialization, identity, and spatio-temporal trajectories. We formulate this task as a …

The ability to recognize, localize and track dynamic objects in a scene is fundamental to
many real-world applications, such as self-driving and robotic systems. Yet, traditional …

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 …

Abstract Most (3D) multi-object tracking methods rely on appearance-based cues for data
association. By contrast, we investigate how far we can get by only encoding geometric …

Object tracking and 3D reconstruction are often performed together, with tracking used as
input for reconstruction. However, the obtained reconstructions also provide useful …

Temporal semantic scene understanding is critical for self-driving cars or robots operating in
dynamic environments. In this paper, we propose 4D panoptic LiDAR segmentation to …

Abstract Current multi-category Multiple Object Tracking (MOT) metrics use class labels to
group tracking results for per-class evaluation. Similarly, MOT methods typically only …

The task of assigning semantic classes and track identities to every pixel in a video is called
video panoptic segmentation. Our work is the first that targets this task in a real-world setting …

Existing methods for instance segmentation in videos typically involve multi-stage pipelines
that follow the tracking-by-detection paradigm and model a video clip as a sequence of …