# RAGTrack: Language-aware RGBT Tracking with Retrieval-Augmented Generation

arXiv: https://arxiv.org/abs/2603.03617 · HTML: https://mlsanity.com/paper/2603.03617/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Video understanding with MLLMs, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 58 of its 88 references that are in the map.
- First posted on arXiv 4 Mar 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Video understanding with MLLMs](https://mlsanity.com/mllm/video-understanding-with-mllms/)
- Retrieval-augmented generation / [Multimodal RAG](https://mlsanity.com/rag/multimodal-rag/)

## Builds on (most cited first, 30 of 58)

- [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)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019)
- [CornerNet: Detecting Objects as Paired Keypoints](https://mlsanity.com/paper/1808.01244/) (2018)
- [Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework](https://mlsanity.com/paper/2203.11991/) (2022)
- [Learning Multi-Domain Convolutional Neural Networks for Visual Tracking](https://mlsanity.com/paper/1510.07945/) (2015)
- [Visual Prompt Multi-Modal Tracking](https://mlsanity.com/paper/2303.10826/) (2023)
- [ODTrack: Online Dense Temporal Token Learning for Visual Tracking](https://mlsanity.com/paper/2401.01686/) (2024)
- [Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark](https://mlsanity.com/paper/2103.16746/) (2021)
- [RGB-T Object Tracking:Benchmark and Baseline](https://mlsanity.com/paper/1805.08982/) (2018)
- [LasHeR: A Large-scale High-diversity Benchmark for RGBT Tracking](https://mlsanity.com/paper/2104.13202/) (2021)
- [Transformer Tracking with Cyclic Shifting Window Attention](https://mlsanity.com/paper/2205.03806/) (2022)
- [Single-Model and Any-Modality for Video Object Tracking](https://mlsanity.com/paper/2311.15851/) (2023)
- [OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuning](https://mlsanity.com/paper/2403.09634/) (2024)
- [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)
- [Exploiting Multimodal Spatial-temporal Patterns for Video Object Tracking](https://mlsanity.com/paper/2412.15691/) (2024)
- [Challenge-Aware RGBT Tracking](https://mlsanity.com/paper/2007.13143/) (2020)
- [SUTrack: Towards Simple and Unified Single Object Tracking](https://mlsanity.com/paper/2412.19138/) (2024)
- [Compact Transformer Tracker with Correlative Masked Modeling](https://mlsanity.com/paper/2301.10938/) (2023)
- [Bi-directional Adapter for Multi-modal Tracking](https://mlsanity.com/paper/2312.10611/) (2023)
- [Vision-based Anti-UAV Detection and Tracking](https://mlsanity.com/paper/2205.10851/) (2022)
- [SDSTrack: Self-Distillation Symmetric Adapter Learning for Multi-Modal Visual Object Tracking](https://mlsanity.com/paper/2403.16002/) (2024)
- [Dense Feature Aggregation and Pruning for RGBT Tracking](https://mlsanity.com/paper/1907.10451/) (2019)
- [CiteTracker: Correlating Image and Text for Visual Tracking](https://mlsanity.com/paper/2308.11322/) (2023)
- [Duality-Gated Mutual Condition Network for RGBT Tracking](https://mlsanity.com/paper/2011.07188/) (2020)

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

- [DRGBT-1K: A Large-scale High-quality Benchmark for Dynamic RGBT Tracking](https://mlsanity.com/paper/2607.19772/) (2026)
- [STAR: A Spatial-Topology Aware Routing Framework for Generalizable 3D Scene Understanding](https://mlsanity.com/paper/2608.11699/) (2026)

## Abstract (arXiv)

RGB-Thermal (RGBT) tracking aims to achieve robust object localization across diverse environmental conditions by fusing visible and thermal infrared modalities. However, existing RGBT trackers rely solely on initial-frame visual information for target modeling, failing to adapt to appearance variations due to the absence of language guidance. Furthermore, current methods suffer from redundant search regions and heterogeneous modality gaps, causing background distraction. To address these issues, we first introduce textual descriptions into RGBT tracking benchmarks. This is accomplished through a pipeline that leverages Multi-modal Large Language Models (MLLMs) to automatically produce texual annotations. Afterwards, we propose RAGTrack, a novel Retrieval-Augmented Generation framework for robust RGBT tracking. To this end, we introduce a Multi-modal Transformer Encoder (MTE) for unified visual-language modeling. Then, we design an Adaptive Token Fusion (ATF) to select target-relevant tokens and perform channel exchanges based on cross-modal correlations, mitigating search redundancies and modality gaps. Finally, we propose a Context-aware Reasoning Module (CRM) to maintain a dynamic knowledge base and employ a Retrieval-Augmented Generation (RAG) to enable temporal linguistic reasoning for robust target modeling. Extensive experiments on four RGBT benchmarks demonstrate that our framework achieves state-of-the-art performance across various challenging scenarios. The source code is available https://github.com/IdolLab/RAGTrack.