Multi-object tracking (MOT) aims at estimating bounding boxes and identities of objects in
videos. Most methods obtain identities by associating detection boxes whose scores are …

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 …

Multi-object tracking (MOT) requires detecting and associating objects through frames.
Unlike tracking via detected bounding boxes or center points, we propose tracking objects …

Due to balanced accuracy and speed, one-shot models which jointly learn detection and
identification embeddings, have drawn great attention in multi-object tracking (MOT) …

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 …

Despite considerable similarities between multiple object tracking (MOT) and single object
tracking (SOT) tasks, modern MOT methods have not benefited from the development of …

We present a novel transformer-based architecture for global multi-object tracking. Our
network takes a short sequence of frames as input and produces global trajectories for all …

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 one-shot multi-object tracking, which integrates object detection and ID embedding
extraction into a unified network, has achieved groundbreaking results in recent years …

In this work, we propose TransTrack, a simple but efficient scheme to solve the multiple
object tracking problems. TransTrack leverages the transformer architecture, which is an …