Abstract Information perception is crucial in MOT tasks. Recent approaches use positional,
motion, and appearance information to model object states. However, in scenes involving …

In this paper, we propose an online multi-object tracking (MOT) approach that integrates
data association and single object tracking (SOT) with a unified convolutional network …

Abstract Appearance-based Multi-Object Tracking (MOT) methods rely on the appearance
cues of objects. However, existing deep appearance extraction schemes struggle to balance …

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 …

Tracking a time-varying indefinite number of objects in a video sequence over time remains
a challenge despite recent advances in the field. Most existing approaches are not able to …

Online multi-object tracking needs to overcome the intrinsic detector deficiencies, eg,
missing detections, false alarms, and inaccurate detection responses, to grow multiple …

In the last few years, enormous strides have been made for object detection and data
association, which are vital subtasks for one-stage online multi-object tracking (MOT) …

In this paper, we propose a sequence-to-sequence affinity metric for the data association of
near-online multi-object tracking. The proposed metric learns the affinity between track …

Online multi-object tracking (MOT) is a longstanding task for computer vision and intelligent
vehicle platform. At present, the main paradigm is tracking-by-detection, and the main …

Multi-Object Tracking (MOT) aims to detect and associate all desired objects across frames.
Most methods accomplish the task by explicitly or implicitly leveraging strong cues (ie …