# Benchmarking SAM2-based Trackers on FMOX

arXiv: https://arxiv.org/abs/2512.09633 · HTML: https://mlsanity.com/paper/2512.09633/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 13 references that are in the map.
- First posted on arXiv 10 Dec 2025.

## Builds on (most cited first, 11 of 11)

- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [LaSOT: A High-quality Benchmark for Large-scale Single Object Tracking](https://mlsanity.com/paper/1809.07845/) (2018)
- [MixFormer: End-to-End Tracking with Iterative Mixed Attention](https://mlsanity.com/paper/2203.11082/) (2022)
- [SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory](https://mlsanity.com/paper/2411.11922/) (2024)
- [A Distractor-Aware Memory for Visual Object Tracking with SAM2](https://mlsanity.com/paper/2411.17576/) (2024)
- [MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes](https://mlsanity.com/paper/2508.05630/) (2025)
- [Efficient Track Anything](https://mlsanity.com/paper/2411.18933/) (2024)
- [The World of Fast Moving Objects](https://mlsanity.com/paper/1611.07889/) (2016)
- [Intra-frame Object Tracking by Deblatting](https://mlsanity.com/paper/1905.03633/) (2019)
- [Sub-frame Appearance and 6D Pose Estimation of Fast Moving Objects](https://mlsanity.com/paper/1911.10927/) (2019)
- [Benchmarking EfficientTAM on FMO datasets](https://mlsanity.com/paper/2509.06536/) (2025)

## Abstract (arXiv)

Several object tracking pipelines extending Segment Anything Model 2 (SAM2) have been proposed in the past year, where the approach is to follow and segment the object from a single exemplar template provided by the user on a initialization frame. We propose to benchmark these high performing trackers (SAM2, EfficientTAM, DAM4SAM and SAMURAI) on datasets containing fast moving objects (FMO) specifically designed to be challenging for tracking approaches. The goal is to understand better current limitations in state-of-the-art trackers by providing more detailed insights on the behavior of these trackers. We show that overall the trackers DAM4SAM and SAMURAI perform well on more challenging sequences.