# MEX: Memory-efficient Approach to Referring Multi-Object Tracking

arXiv: https://arxiv.org/abs/2502.13875 · HTML: https://mlsanity.com/paper/2502.13875/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 32 references that are in the map.
- First posted on arXiv 19 Feb 2025.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [Simple Online and Realtime Tracking with a Deep Association Metric](https://mlsanity.com/paper/1703.07402/) (2017)
- [ByteTrack: Multi-Object Tracking by Associating Every Detection Box](https://mlsanity.com/paper/2110.06864/) (2021)
- [Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking](https://mlsanity.com/paper/1609.01775/) (2016)
- [HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking](https://mlsanity.com/paper/2009.07736/) (2020)
- [TrackFormer: Multi-Object Tracking with Transformers](https://mlsanity.com/paper/2101.02702/) (2021)
- [MOTR: End-to-End Multiple-Object Tracking with Transformer](https://mlsanity.com/paper/2105.03247/) (2021)
- [Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking](https://mlsanity.com/paper/2203.14360/) (2022)
- [BoT-SORT: Robust Associations Multi-Pedestrian Tracking](https://mlsanity.com/paper/2206.14651/) (2022)
- [Language as Queries for Referring Video Object Segmentation](https://mlsanity.com/paper/2201.00487/) (2022)
- [MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors](https://mlsanity.com/paper/2211.09791/) (2022)
- [MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking](https://mlsanity.com/paper/2010.07548/) (2020)
- [End-to-End Referring Video Object Segmentation with Multimodal Transformers](https://mlsanity.com/paper/2111.14821/) (2021)
- [MeMOT: Multi-Object Tracking with Memory](https://mlsanity.com/paper/2203.16761/) (2022)
- [Referring Multi-Object Tracking](https://mlsanity.com/paper/2303.03366/) (2023)
- [MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking](https://mlsanity.com/paper/2307.15700/) (2023)
- [Deep Cosine Metric Learning for Person Re-Identification](https://mlsanity.com/paper/1812.00442/) (2018)
- [Towards Unified Token Learning for Vision-Language Tracking](https://mlsanity.com/paper/2308.14103/) (2023)
- [Joint Visual Grounding and Tracking with Natural Language Specification](https://mlsanity.com/paper/2303.12027/) (2023)
- [iKUN: Speak to Trackers without Retraining](https://mlsanity.com/paper/2312.16245/) (2023)
- [Type-to-Track: Retrieve Any Object via Prompt-based Tracking](https://mlsanity.com/paper/2305.13495/) (2023)

## Built on by (most cited first, 4 of 4)

- [ReferGPT: Towards Zero-Shot Referring Multi-Object Tracking](https://mlsanity.com/paper/2504.09195/) (2025)
- [DRMOT: A Dataset and Framework for RGBD Referring Multi-Object Tracking](https://mlsanity.com/paper/2602.04692/) (2026)
- [YesTrack: Referring Multi-Object Tracking via MLLM-based Yes/No Verification](https://mlsanity.com/paper/2609.02318/) (2026)
- [Referring Multi-Object Tracking in Moving-Camera Videos via Global Motion Compensation](https://mlsanity.com/paper/2610.04185/) (2026)

## Abstract (arXiv)

Referring Multi-Object Tracking (RMOT) is a relatively new concept that has rapidly gained traction as a promising research direction at the intersection of computer vision and natural language processing. Unlike traditional multi-object tracking, RMOT identifies and tracks objects and incorporates textual descriptions for object class names, making the approach more intuitive. Various techniques have been proposed to address this challenging problem; however, most require the training of the entire network due to their end-to-end nature. Among these methods, iKUN has emerged as a particularly promising solution. Therefore, we further explore its pipeline and enhance its performance. In this paper, we introduce a practical module dubbed Memory-Efficient Cross-modality -- MEX. This memory-efficient technique can be directly applied to off-the-shelf trackers like iKUN, resulting in significant architectural improvements. Our method proves effective during inference on a single GPU with 4 GB of memory. Among the various benchmarks, the Refer-KITTI dataset, which offers diverse autonomous driving scenes with relevant language expressions, is particularly useful for studying this problem. Empirically, our method demonstrates effectiveness and efficiency regarding HOTA tracking scores, substantially improving memory allocation and processing speed.