# An Uncertainty-Aware Performance Measure for Multi-Object Tracking

arXiv: https://arxiv.org/abs/2108.04619 · HTML: https://mlsanity.com/paper/2108.04619/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Aug 2021.

## Built on by (most cited first, 9 of 9)

- [NeuRadar: Neural Radiance Fields for Automotive Radar Point Clouds](https://mlsanity.com/paper/2504.00859/) (2025)
- [Can Deep Learning be Applied to Model-Based Multi-Object Tracking?](https://mlsanity.com/paper/2202.07909/) (2022)
- [Object Detection as Probabilistic Set Prediction](https://mlsanity.com/paper/2203.07980/) (2022)
- [Transformer-Based Multi-Object Smoothing with Decoupled Data Association and Smoothing](https://mlsanity.com/paper/2312.17261/) (2023)
- [From Target Tracking to Targeting Track -- Part I: A Metric for Spatio-Temporal Trajectory Evaluation](https://mlsanity.com/paper/2502.15842/) (2025)
- [Detection-aware multi-object tracking evaluation](https://mlsanity.com/paper/2212.08536/) (2022)
- [MATT-Diff: Multimodal Active Target Tracking by Diffusion Policy](https://mlsanity.com/paper/2511.11931/) (2025)
- [Deep Fusion of Multi-Object Densities Using Transformer](https://mlsanity.com/paper/2209.08857/) (2022)
- [Diffusion Policy with Bayesian Expert Selection for Active Multi-Target Tracking](https://mlsanity.com/paper/2604.03404/) (2026)

## Abstract (arXiv)

Evaluating the performance of multi-object tracking (MOT) methods is not straightforward, and existing performance measures fail to consider all the available uncertainty information in the MOT context. This can lead practitioners to select models which produce uncertainty estimates of lower quality, negatively impacting any downstream systems that rely on them. Additionally, most MOT performance measures have hyperparameters, which makes comparisons of different trackers less straightforward. We propose the use of the negative log-likelihood (NLL) of the multi-object posterior given the set of ground-truth objects as a performance measure. This measure takes into account all available uncertainty information in a sound mathematical manner without hyperparameters. We provide efficient algorithms for approximating the computation of the NLL for several common MOT algorithms, show that in some cases it decomposes and approximates the widely-used GOSPA metric, and provide several illustrative examples highlighting the advantages of the NLL in comparison to other MOT performance measures.