# MeNToS: Tracklets Association with a Space-Time Memory Network

arXiv: https://arxiv.org/abs/2107.07067 · HTML: https://mlsanity.com/paper/2107.07067/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 10 references that are in the map.
- First posted on arXiv 15 Jul 2021.

## Builds on (most cited first, 5 of 5)

- [HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking](https://mlsanity.com/paper/2009.07736/) (2020)
- [Video Object Segmentation using Space-Time Memory Networks](https://mlsanity.com/paper/1904.00607/) (2019)
- [MOTS: Multi-Object Tracking and Segmentation](https://mlsanity.com/paper/1902.03604/) (2019)
- [Track to Reconstruct and Reconstruct to Track](https://mlsanity.com/paper/1910.00130/) (2019)
- [ReMOTS: Self-Supervised Refining Multi-Object Tracking and Segmentation](https://mlsanity.com/paper/2007.03200/) (2020)

## Abstract (arXiv)

We propose a method for multi-object tracking and segmentation (MOTS) that does not require fine-tuning or per benchmark hyperparameter selection. The proposed method addresses particularly the data association problem. Indeed, the recently introduced HOTA metric, that has a better alignment with the human visual assessment by evenly balancing detections and associations quality, has shown that improvements are still needed for data association. After creating tracklets using instance segmentation and optical flow, the proposed method relies on a space-time memory network (STM) developed for one-shot video object segmentation to improve the association of tracklets with temporal gaps. To the best of our knowledge, our method, named MeNToS, is the first to use the STM network to track object masks for MOTS. We took the 4th place in the RobMOTS challenge. The project page is https://mehdimiah.com/mentos.html.