Deep reinforcement learning augments the reinforcement learning framework and utilizes
the powerful representation of deep neural networks. Recent works have demonstrated the …

Object detection and tracking is one of the most important and challenging branches in
computer vision, and have been widely applied in various fields, such as health-care …

We introduce PointOdyssey, a large-scale synthetic dataset, and data generation framework,
for the training and evaluation of long-term fine-grained tracking algorithms. Our goal is to …

Temporal modeling of objects is a key challenge in multiple-object tracking (MOT). Existing
methods track by associating detections through motion-based and appearance-based …

A typical pipeline for multi-object tracking (MOT) is to use a detector for object localization,
and following re-identification (re-ID) for object association. This pipeline is partially …

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

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 …

Multi-object tracking (MOT) is an important problem in computer vision which has a wide
range of applications. Formulating MOT as multi-task learning of object detection and re-ID …

Standardized benchmarks are crucial for the majority of computer vision applications.
Although leaderboards and ranking tables should not be over-claimed, benchmarks often …

Tracking multiple objects in videos relies on modeling the spatial-temporal interactions of
the objects. In this paper, we propose TransMOT, which leverages powerful graph …