---
title: "Modality-Guided Dynamic Graph Fusion and Temporal Diffusion for Self-Supervised RGB-T Tracking"
authors:
  - "Shenglan Li"
  - "Rui Yao"
  - "Yong Zhou"
  - "Hancheng Zhu"
  - "Kunyang Sun"
  - "Bing Liu"
  - "Zhiwen Shao"
  - "Jiaqi Zhao"
doi: "10.24963/ijcai.2025/159"
url: "https://ijcai.org/proceedings/2025/159"
pdf: "https://ijcai.org/proceedings/2025/0159.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "1422-1430"
track: "Main Track"
keywords:
  - "Machine Learning: ML: Multi-modal learning"
  - "Machine Learning: ML: Unsupervised learning"
  - "Computer Vision: CV: Motion and tracking"
---

# Modality-Guided Dynamic Graph Fusion and Temporal Diffusion for Self-Supervised RGB-T Tracking

Shenglan Li, Rui Yao, Yong Zhou, Hancheng Zhu, Kunyang Sun, Bing Liu, Zhiwen Shao, Jiaqi Zhao

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 1422-1430. DOI: [10.24963/ijcai.2025/159](https://doi.org/10.24963/ijcai.2025/159)

## Abstract

To reduce the reliance on large-scale annotations, self-supervised RGB-T tracking approaches have garnered significant attention. However, the omission of the object region by erroneous pseudo-label or the introduction of background noise affects the efficiency of modality fusion, while pseudo-label noise triggered by similar object noise can further affect the tracking performance. In this paper, we propose GDSTrack, a novel approach that introduces dynamic graph fusion and temporal diffusion to address the above challenges in self-supervised RGB-T tracking. GDSTrack dynamically fuses the modalities of neighboring frames, treats them as distractor noise, and leverages the denoising capability of a generative model. Specifically, by constructing an adjacency matrix via an Adjacency Matrix Generator (AMG), the proposed Modality-guided Dynamic Graph Fusion (MDGF) module uses a dynamic adjacency matrix to guide graph attention, focusing on and fusing the object’s coherent regions. Temporal Graph-Informed Diffusion (TGID) models MDGF features from neighboring frames as interference, and thus improving robustness against similar-object noise. Extensive experiments conducted on four public RGB-T tracking datasets demonstrate that GDSTrack outperforms the existing state-of-the-art methods. 
The source code is available at https://github.com/LiShenglana/GDSTrack.