Current popular online multi-object tracking (MOT) solutions apply single object trackers
(SOTs) to capture object motions, while often requiring an extra affinity network to associate …

Traditional multiple object tracking methods divide the task into two parts: affinity learning
and data association. The separation of the task requires to define a hand-crafted training …

Recent progresses in model-free single object tracking (SOT) algorithms have largely
inspired applying SOT to multi-object tracking (MOT) to improve the robustness as well as …

Data association-based multiple object tracking (MOT) involves multiple separated modules
processed or optimized differently, which results in complex method design and requires …

Recent progress in multiple object tracking (MOT) has shown that a robust similarity score is
a key to the success of trackers. A good similarity score is expected to reflect multiple cues …

Discriminative representation is crucial for the association step in multi-object tracking.
Recent work mainly utilizes features in single or neighboring frames for constructing metric …

In this paper, we propose MOTRv2, a simple yet effective pipeline to bootstrap end-to-end
multi-object tracking with a pretrained object detector. Existing end-to-end methods, eg …

The recent trend in vision-based multi-object tracking (MOT) is heading towards leveraging
the representational power of deep learning to jointly learn to detect and track objects …

The recent trend in multiple object tracking (MOT) is heading towards leveraging deep
learning to boost the tracking performance. However, it is not trivial to solve the data …

Modern multiple object tracking (MOT) systems usually follow the tracking-by-detection
paradigm. It has 1) a detection model for target localization and 2) an appearance …