# Joint Object Detection and Multi-Object Tracking with Graph Neural Networks

arXiv: https://arxiv.org/abs/2006.13164 · HTML: https://mlsanity.com/paper/2006.13164/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jun 2020.

## Built on by (most cited first, 14 of 14)

- [TransMOT: Spatial-Temporal Graph Transformer for Multiple Object Tracking](https://mlsanity.com/paper/2104.00194/) (2021)
- [MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?](https://mlsanity.com/paper/2108.09518/) (2021)
- [Multiple Object Tracking with Correlation Learning](https://mlsanity.com/paper/2104.03541/) (2021)
- [3D Siamese Transformer Network for Single Object Tracking on Point Clouds](https://mlsanity.com/paper/2207.11995/) (2022)
- [MOTRv3: Release-Fetch Supervision for End-to-End Multi-Object Tracking](https://mlsanity.com/paper/2305.14298/) (2023)
- [Track without Appearance: Learn Box and Tracklet Embedding with Local and Global Motion Patterns for Vehicle Tracking](https://mlsanity.com/paper/2108.06029/) (2021)
- [Split and Connect: A Universal Tracklet Booster for Multi-Object Tracking](https://mlsanity.com/paper/2105.02426/) (2021)
- [Generalizing Multiple Object Tracking to Unseen Domains by Introducing Natural Language Representation](https://mlsanity.com/paper/2212.01568/) (2022)
- [End-to-end video instance segmentation via spatial-temporal graph neural networks](https://mlsanity.com/paper/2203.03145/) (2022)
- [Local Metrics for Multi-Object Tracking](https://mlsanity.com/paper/2104.02631/) (2021)
- [Autonomous Apple Fruitlet Sizing and Growth Rate Tracking using Computer Vision](https://mlsanity.com/paper/2212.01506/) (2022)
- [GraphKD: Exploring Knowledge Distillation Towards Document Object Detection with Structured Graph Creation](https://mlsanity.com/paper/2402.11401/) (2024)
- [Localization-Based Tracking](https://mlsanity.com/paper/2104.05823/) (2021)
- [3D Multi-Object Tracking with Differentiable Pose Estimation](https://mlsanity.com/paper/2206.13785/) (2022)

## Abstract (arXiv)

Object detection and data association are critical components in multi-object tracking (MOT) systems. Despite the fact that the two components are dependent on each other, prior works often design detection and data association modules separately which are trained with separate objectives. As a result, one cannot back-propagate the gradients and optimize the entire MOT system, which leads to sub-optimal performance. To address this issue, recent works simultaneously optimize detection and data association modules under a joint MOT framework, which has shown improved performance in both modules. In this work, we propose a new instance of joint MOT approach based on Graph Neural Networks (GNNs). The key idea is that GNNs can model relations between variable-sized objects in both the spatial and temporal domains, which is essential for learning discriminative features for detection and data association. Through extensive experiments on the MOT15/16/17/20 datasets, we demonstrate the effectiveness of our GNN-based joint MOT approach and show state-of-the-art performance for both detection and MOT tasks. Our code is available at: https://github.com/yongxinw/GSDT