# Referring Multi-Object Tracking in Moving-Camera Videos via Global Motion Compensation

arXiv: https://arxiv.org/abs/2610.04185 · HTML: https://mlsanity.com/paper/2610.04185/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 19 references that are in the map.
- First posted on arXiv 3 Oct 2026.

## Builds on (most cited first, 13 of 13)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking](https://mlsanity.com/paper/2009.07736/) (2020)
- [BoT-SORT: Robust Associations Multi-Pedestrian Tracking](https://mlsanity.com/paper/2206.14651/) (2022)
- [Referring Multi-Object Tracking](https://mlsanity.com/paper/2303.03366/) (2023)
- [UCMCTrack: Multi-Object Tracking with Uniform Camera Motion Compensation](https://mlsanity.com/paper/2312.08952/) (2023)
- [iKUN: Speak to Trackers without Retraining](https://mlsanity.com/paper/2312.16245/) (2023)
- [Bootstrapping Referring Multi-Object Tracking](https://mlsanity.com/paper/2406.05039/) (2024)
- [ReferGPT: Towards Zero-Shot Referring Multi-Object Tracking](https://mlsanity.com/paper/2504.09195/) (2025)
- [MEX: Memory-efficient Approach to Referring Multi-Object Tracking](https://mlsanity.com/paper/2502.13875/) (2025)
- [Ego-Motion Aware Target Prediction Module for Robust Multi-Object Tracking](https://mlsanity.com/paper/2404.03110/) (2024)
- [Rethinking Two-Stage Referring-by-Tracking in Referring Multi-Object Tracking: Make it Strong Again](https://mlsanity.com/paper/2503.07516/) (2025)
- [STORM: End-to-End Referring Multi-Object Tracking in Videos](https://mlsanity.com/paper/2604.10527/) (2026)

## Abstract (arXiv)

Referring multi-object tracking (RMOT) takes a video and a language expression as input and tracks all referred objects. Many tracking requirements involve how an object moves rather than how it appears. However, in a video captured by a moving camera, a parked vehicle may appear to move, while a moving vehicle may show little displacement. Existing RMOT methods relate motion with text but do not explicitly remove camera-induced motion. In this paper, we propose extracting residual motion across frames by estimating camera motion in driver-view videos and compare motion characteristics with the query expression. We consider the motion-matching extent and integrate it with the RMOT method's prediction result through late fusion. In the evaluation, we verify the performance gain of taking the motion compensation module as a plug-in across different RMOT hosts.