# GCNNMatch: Graph Convolutional Neural Networks for Multi-Object Tracking via Sinkhorn Normalization

arXiv: https://arxiv.org/abs/2010.00067 · HTML: https://mlsanity.com/paper/2010.00067/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Sep 2020.

## Built on by (most cited first, 25 of 25)

- [Learnable Graph Matching: Incorporating Graph Partitioning with Deep Feature Learning for Multiple Object Tracking](https://mlsanity.com/paper/2103.16178/) (2021)
- [Learning a Proposal Classifier for Multiple Object Tracking](https://mlsanity.com/paper/2103.07889/) (2021)
- [TransCenter: Transformers with Dense Representations for Multiple-Object Tracking](https://mlsanity.com/paper/2103.15145/) (2021)
- [Bending Graphs: Hierarchical Shape Matching using Gated Optimal Transport](https://mlsanity.com/paper/2202.01537/) (2022)
- [EchoTrack: Auditory Referring Multi-Object Tracking for Autonomous Driving](https://mlsanity.com/paper/2402.18302/) (2024)
- [Split and Connect: A Universal Tracklet Booster for Multi-Object Tracking](https://mlsanity.com/paper/2105.02426/) (2021)
- [Graph Neural Networks for Cross-Camera Data Association](https://mlsanity.com/paper/2201.06311/) (2022)
- [Learning of Global Objective for Network Flow in Multi-Object Tracking](https://mlsanity.com/paper/2203.16210/) (2022)
- [Local Metrics for Multi-Object Tracking](https://mlsanity.com/paper/2104.02631/) (2021)
- [Online and Real-Time Tracking in a Surveillance Scenario](https://mlsanity.com/paper/2106.01153/) (2021)
- [Recent Advances in Embedding Methods for Multi-Object Tracking: A Survey](https://mlsanity.com/paper/2205.10766/) (2022)
- [Rethinking Explaining Graph Neural Networks via Non-parametric Subgraph Matching](https://mlsanity.com/paper/2301.02780/) (2023)
- [SDOF-Tracker: Fast and Accurate Multiple Human Tracking by Skipped-Detection and Optical-Flow](https://mlsanity.com/paper/2106.14259/) (2021)
- [Simple online and real-time tracking with occlusion handling](https://mlsanity.com/paper/2103.04147/) (2021)
- [Fast Online and Relational Tracking](https://mlsanity.com/paper/2208.03659/) (2022)
- [Learnable Graph Matching: A Practical Paradigm for Data Association](https://mlsanity.com/paper/2303.15414/) (2023)
- [Synthetic Data Are as Good as the Real for Association Knowledge Learning in Multi-object Tracking](https://mlsanity.com/paper/2106.16100/) (2021)
- [Temporal Correlation Meets Embedding: Towards a 2nd Generation of JDE-based Real-Time Multi-Object Tracking](https://mlsanity.com/paper/2407.14086/) (2024)
- [Heterogeneous Graph Transformer for Multiple Tiny Object Tracking in RGB-T Videos](https://mlsanity.com/paper/2412.10861/) (2024)
- [How to Backpropagate through Hungarian in Your DETR?](https://mlsanity.com/paper/2211.14448/) (2022)
- [Sparse Message Passing Network with Feature Integration for Online Multiple Object Tracking](https://mlsanity.com/paper/2212.02992/) (2022)
- [A Hybrid Approach To Real-Time Multi-Object Tracking](https://mlsanity.com/paper/2308.01248/) (2023)
- [UnsMOT: Unified Framework for Unsupervised Multi-Object Tracking with Geometric Topology Guidance](https://mlsanity.com/paper/2309.01078/) (2023)
- [SSP-GNN: Learning to Track via Bilevel Optimization](https://mlsanity.com/paper/2407.04308/) (2024)
- [HDST-GNN: Heterogeneous Dynamic Spatiotemporal Graph Neural Networks for Multi-Object Tracking in UAV Aerial Imagery](https://mlsanity.com/paper/2606.05587/) (2026)

## Abstract (arXiv)

This paper proposes a novel method for online Multi-Object Tracking (MOT) using Graph Convolutional Neural Network (GCNN) based feature extraction and end-to-end feature matching for object association. The Graph based approach incorporates both appearance and geometry of objects at past frames as well as the current frame into the task of feature learning. This new paradigm enables the network to leverage the "context" information of the geometry of objects and allows us to model the interactions among the features of multiple objects. Another central innovation of our proposed framework is the use of the Sinkhorn algorithm for end-to-end learning of the associations among objects during model training. The network is trained to predict object associations by taking into account constraints specific to the MOT task. Experimental results demonstrate the efficacy of the proposed approach in achieving top performance on the MOT '15, '16, '17 and '20 Challenges among state-of-the-art online approaches. The code is available at https://github.com/IPapakis/GCNNMatch.