# Tell Me What to Track: Infusing Robust Language Guidance for Enhanced Referring Multi-Object Tracking

arXiv: https://arxiv.org/abs/2412.12561 · HTML: https://mlsanity.com/paper/2412.12561/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 59 references that are in the map.
- First posted on arXiv 17 Dec 2024.

## Builds on (most cited first, 30 of 44)

- [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)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019)
- [Modeling Context in Referring Expressions](https://mlsanity.com/paper/1608.00272/) (2016)
- [Generation and Comprehension of Unambiguous Object Descriptions](https://mlsanity.com/paper/1511.02283/) (2015)
- [ByteTrack: Multi-Object Tracking by Associating Every Detection Box](https://mlsanity.com/paper/2110.06864/) (2021)
- [DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR](https://mlsanity.com/paper/2201.12329/) (2022)
- [Fully-Convolutional Siamese Networks for Object Tracking](https://mlsanity.com/paper/1606.09549/) (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)
- [FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking](https://mlsanity.com/paper/2004.01888/) (2020)
- [LaSOT: A High-quality Benchmark for Large-scale Single Object Tracking](https://mlsanity.com/paper/1809.07845/) (2018)
- [Conditional DETR for Fast Training Convergence](https://mlsanity.com/paper/2108.06152/) (2021)
- [Tracking without bells and whistles](https://mlsanity.com/paper/1903.05625/) (2019)
- [MOTR: End-to-End Multiple-Object Tracking with Transformer](https://mlsanity.com/paper/2105.03247/) (2021)
- [Learning a Neural Solver for Multiple Object Tracking](https://mlsanity.com/paper/1912.07515/) (2019)
- [Language as Queries for Referring Video Object Segmentation](https://mlsanity.com/paper/2201.00487/) (2022)
- [Video Object Segmentation with Language Referring Expressions](https://mlsanity.com/paper/1803.08006/) (2018)
- [MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors](https://mlsanity.com/paper/2211.09791/) (2022)
- [Referring Transformer: A One-step Approach to Multi-task Visual Grounding](https://mlsanity.com/paper/2106.03089/) (2021)
- [Talk2Car: Taking Control of Your Self-Driving Car](https://mlsanity.com/paper/1909.10838/) (2019)
- [Learning to Assemble Neural Module Tree Networks for Visual Grounding](https://mlsanity.com/paper/1812.03299/) (2018)
- [Character-Level Language Modeling with Deeper Self-Attention](https://mlsanity.com/paper/1808.04444/) (2018)

## Built on by (most cited first, 2 of 2)

- [QUILL: An Algorithm-Architecture Co-Design for Cache-Local Deformable Attention](https://mlsanity.com/paper/2511.13679/) (2025)
- [COAL: Counterfactual and Observation-Enhanced Alignment Learning for Discriminative Referring Multi-Object Tracking](https://mlsanity.com/paper/2605.14795/) (2026)

## Abstract (arXiv)

Referring multi-object tracking (RMOT) is an emerging cross-modal task that aims to localize an arbitrary number of targets based on a language expression and continuously track them in a video. This intricate task involves reasoning on multi-modal data and precise target localization with temporal association. However, prior studies overlook the imbalanced data distribution between newborn targets and existing targets due to the nature of the task. In addition, they only indirectly fuse multi-modal features, struggling to deliver clear guidance on newborn target detection. To solve the above issues, we conduct a collaborative matching strategy to alleviate the impact of the imbalance, boosting the ability to detect newborn targets while maintaining tracking performance. In the encoder, we integrate and enhance the cross-modal and multi-scale fusion, overcoming the bottlenecks in previous work, where limited multi-modal information is shared and interacted between feature maps. In the decoder, we also develop a referring-infused adaptation that provides explicit referring guidance through the query tokens. The experiments showcase the superior performance of our model (+3.42%) compared to prior works, demonstrating the effectiveness of our designs.