# MambaMOT: State-Space Model as Motion Predictor for Multi-Object Tracking

Source: [MambaMOT: State-Space Model as Motion Predictor for Multi-Object Tracking](<https://www.sota2.com/research/paper/68fa76a81e209131cea6e391>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T03:57:55.860Z

Authors: Hsiang-Wei Huang, Cheng-Yen Yang, Wenhao Chai, Zhongyu Jiang, Jenq-Neng Hwang

Published: 2024-03-16T06:26:52.000Z

## Abstract

In the field of multi-object tracking (MOT), traditional methods often rely on the Kalman filter for motion prediction, leveraging its strengths in linear motion scenarios. However, the inherent limitations of these methods become evident when confronted with complex, nonlinear motions and occlusions prevalent in dynamic environments like sports and dance. This paper explores the possibilities of replacing the Kalman filter with a learning-based motion model that effectively enhances tracking accuracy and adaptability beyond the constraints of Kalman filter-based tracker. In this paper, our proposed method MambaMOT and MambaMOT+, demonstrate advanced performance on challenging MOT datasets such as DanceTrack and SportsMOT, showcasing their ability to handle intricate, non-linear motion patterns and frequent occlusions more effectively than traditional methods.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Multi-Object Tracking on SportsMOT 1.0 (test)](<https://www.sota2.com/research/sota/multi-object-tracking-on-sportsmot-1-0-test.md>): Multi-Object Tracking; SportsMOT 1.0 (test); HOTA: 71.3.

- [Multi-Object Tracking on SportsMOT (test)](<https://www.sota2.com/research/sota/multi-object-tracking-on-sportsmot-test.md>): Multi-Object Tracking; SportsMOT (test); HOTA: 71.3.

- [Multi-Object Tracking on DanceTrack (test)](<https://www.sota2.com/research/sota/multi-object-tracking-on-dancetrack-test.md>): Multi-Object Tracking; DanceTrack (test); HOTA: 0.561.

- [Multiple Object Tracking on MOT17 (test)](<https://www.sota2.com/research/sota/multiple-object-tracking-on-mot17-test.md>): Multiple Object Tracking; MOT17 (test); MOTA: 78.1.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2403.10826>)

[PDF](<https://arxiv.org/pdf/2403.10826.pdf>)