This repository contains multiple research modules related to multi-modal tracking, RGB–TIR fusion, and unaligned cross-modal UAV tracking.
Among them, our recent work:

“Progressive Multi-cue Alignment for Unaligned RGBT Tracking”
has been accepted by CVPR 2026 🎉.

“Unaligned UAV RGBT Tracking: A Largescale Benchmark and A Novel Approach”
has been accepted by AAAI 2026 🎉.

This repository includes more than this single paper, but LUART and SFCATrack are important components released here.

• 2026.02 – Our Progressive Multi-cue Alignment for Unaligned RGBT Tracking is accepted by CVPR 2026.
• 2025.11 – Our Unaligned UAV RGBT Tracking: A Largescale Benchmark and A Novel Approach is accepted by AAAI 2026.
• 2025.11 – LUART (1.02M dual-modality frames) dataset is available for download.
• Additional modules and trackers will be released soon.

• 2026.02, we will release the PMATrack(CVPR 2026)
• 2025.12, we publicly released:
• AAAI 2026 paper,
• SFCATrack,
• LUART dataset
• LUART evaluation toolkit

to support reproducibility and future research on unaligned RGBT tracking.

To be coming soon....

LUART is the first large-scale benchmark focusing on unaligned UAV visible–thermal tracking.
It includes:

• 1,453 RGB–TIR sequence pairs
• 1.02M dual-modality frames
• 42 object categories
• 22 challenge attributes
• Original UAV resolutions:
  • RGB: 1920×1080
  • TIR: 640×512

LUART Dataset

• Baidu Cloud:
  https://pan.baidu.com/s/168vWYtxPqoagds8WcPuJUA
• Access Code: er4r

Evaluation Toolkit

• Baidu Cloud:
  https://pan.baidu.com/s/1lv0IBj6UtxZhj1S1UNMPsQ
• Access Code: t1vv

We also provide LasHeR-Unaligned, a derived benchmark based on
LasHeR, where spatial alignment assumptions are explicitly removed to support fair evaluation of unaligned RGBT trackers.

Official implementation of our AAAI 2026 method:

🔗 https://github.com/Yhw-lol127/SFCATrack

If you find this repository or the LUART dataset useful for your research,
please consider citing our AAAI 2026 paper: