# Graph Neural Networks for Cross-Camera Data Association

arXiv: https://arxiv.org/abs/2201.06311 · HTML: https://mlsanity.com/paper/2201.06311/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 78 references that are in the map.
- First posted on arXiv 17 Jan 2022.

## Builds on (most cited first, 30 of 35)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://mlsanity.com/paper/1706.02677/) (2017)
- [Relational inductive biases, deep learning, and graph networks](https://mlsanity.com/paper/1806.01261/) (2018)
- [End-to-end Recovery of Human Shape and Pose](https://mlsanity.com/paper/1712.06584/) (2017)
- [Representation Learning on Graphs with Jumping Knowledge Networks](https://mlsanity.com/paper/1806.03536/) (2018)
- [Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking](https://mlsanity.com/paper/1609.01775/) (2016)
- [Person Transfer GAN to Bridge Domain Gap for Person Re-Identification](https://mlsanity.com/paper/1711.08565/) (2017)
- [Bag of Tricks for Image Classification with Convolutional Neural Networks](https://mlsanity.com/paper/1812.01187/) (2018)
- [ResNet strikes back: An improved training procedure in timm](https://mlsanity.com/paper/2110.00476/) (2021)
- [Relation Networks for Object Detection](https://mlsanity.com/paper/1711.11575/) (2017)
- [Omni-Scale Feature Learning for Person Re-Identification](https://mlsanity.com/paper/1905.00953/) (2019)
- [Graph networks as learnable physics engines for inference and control](https://mlsanity.com/paper/1806.01242/) (2018)
- [Learning a Neural Solver for Multiple Object Tracking](https://mlsanity.com/paper/1912.07515/) (2019)
- [Knowledge Transfer for Out-of-Knowledge-Base Entities: A Graph Neural Network Approach](https://mlsanity.com/paper/1706.05674/) (2017)
- [Features for Multi-Target Multi-Camera Tracking and Re-Identification](https://mlsanity.com/paper/1803.10859/) (2018)
- [Fast and Robust Multi-Person 3D Pose Estimation from Multiple Views](https://mlsanity.com/paper/1901.04111/) (2019)
- [Spatial-Temporal Relation Networks for Multi-Object Tracking](https://mlsanity.com/paper/1904.11489/) (2019)
- [Learning Generalisable Omni-Scale Representations for Person Re-Identification](https://mlsanity.com/paper/1910.06827/) (2019)
- [Batch DropBlock Network for Person Re-identification and Beyond](https://mlsanity.com/paper/1811.07130/) (2018)
- [Semantic Object Parsing with Graph LSTM](https://mlsanity.com/paper/1603.07063/) (2016)
- [Cross-View Tracking for Multi-Human 3D Pose Estimation at over 100 FPS](https://mlsanity.com/paper/2003.03972/) (2020)
- [A generalizable approach for multi-view 3D human pose regression](https://mlsanity.com/paper/1804.10462/) (2018)
- [GCNNMatch: Graph Convolutional Neural Networks for Multi-Object Tracking via Sinkhorn Normalization](https://mlsanity.com/paper/2010.00067/) (2020)
- [Online Multi-Object Tracking with Instance-Aware Tracker and Dynamic Model Refreshment](https://mlsanity.com/paper/1902.08231/) (2019)
- [Top-DB-Net: Top DropBlock for Activation Enhancement in Person Re-Identification](https://mlsanity.com/paper/2010.05435/) (2020)

## Built on by (most cited first, 13 of 13)

- [SparseTrack: Multi-Object Tracking by Performing Scene Decomposition based on Pseudo-Depth](https://mlsanity.com/paper/2306.05238/) (2023)
- [ReST: A Reconfigurable Spatial-Temporal Graph Model for Multi-Camera Multi-Object Tracking](https://mlsanity.com/paper/2308.13229/) (2023)
- [Learning from Synchronization: Self-Supervised Uncalibrated Multi-View Person Association in Challenging Scenes](https://mlsanity.com/paper/2503.13739/) (2025)
- [Multi-View Pedestrian Occupancy Prediction with a Novel Synthetic Dataset](https://mlsanity.com/paper/2412.13569/) (2024)
- [Graph Convolutional Network for Multi-Target Multi-Camera Vehicle Tracking](https://mlsanity.com/paper/2211.15538/) (2022)
- [Multi Player Tracking in Ice Hockey with Homographic Projections](https://mlsanity.com/paper/2405.13397/) (2024)
- [Enhancing Multi-Camera Gymnast Tracking Through Domain Knowledge Integration](https://mlsanity.com/paper/2511.16532/) (2025)
- [Classification-Aided Robust Multiple Target Tracking Using Neural Enhanced Message Passing](https://mlsanity.com/paper/2310.12407/) (2023)
- [Cross-Camera Data Association via GNN for Supervised Graph Clustering](https://mlsanity.com/paper/2410.00643/) (2024)
- [C-DOG: Multi-View Multi-instance Feature Association Using Connected δ-Overlap Graphs](https://mlsanity.com/paper/2507.14095/) (2025)
- [mmGAT: Pose Estimation by Graph Attention with Mutual Features from mmWave Radar Point Cloud](https://mlsanity.com/paper/2603.08551/) (2026)
- [Ranking vs. Assignment: The Metric Mismatch in Multi-View Object Association](https://mlsanity.com/paper/2606.02022/) (2026)
- [MVDGC: Joint 3D and 2D Multi-view Pedestrian Detection via Dual Geometric Constraints](https://mlsanity.com/paper/2607.00273/) (2026)

## Abstract (arXiv)

Cross-camera image data association is essential for many multi-camera computer vision tasks, such as multi-camera pedestrian detection, multi-camera multi-target tracking, 3D pose estimation, etc. This association task is typically stated as a bipartite graph matching problem and often solved by applying minimum-cost flow techniques, which may be computationally inefficient with large data. Furthermore, cameras are usually treated by pairs, obtaining local solutions, rather than finding a global solution at once. Other key issue is that of the affinity measurement: the widespread usage of non-learnable pre-defined distances, such as the Euclidean and Cosine ones. This paper proposes an efficient approach for cross-cameras data-association focused on a global solution, instead of processing cameras by pairs. To avoid the usage of fixed distances, we leverage the connectivity of Graph Neural Networks, previously unused in this scope, using a Message Passing Network to jointly learn features and similarity. We validate the proposal for pedestrian multi-view association, showing results over the EPFL multi-camera pedestrian dataset. Our approach considerably outperforms the literature data association techniques, without requiring to be trained in the same scenario in which it is tested. Our code is available at urlhttp://www-vpu.eps.uam.es/publications/gnncca.