# LSOTB-TIR:A Large-Scale High-Diversity Thermal Infrared Object Tracking Benchmark

arXiv: https://arxiv.org/abs/2008.00836 · HTML: https://mlsanity.com/paper/2008.00836/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Aug 2020.

## Built on by (most cited first, 25 of 25)

- [Anti-UAV: A Large Multi-Modal Benchmark for UAV Tracking](https://mlsanity.com/paper/2101.08466/) (2021)
- [DiffV2IR: Visible-to-Infrared Diffusion Model via Vision-Language Understanding](https://mlsanity.com/paper/2503.19012/) (2025)
- [IRGPT: Understanding Real-world Infrared Image with Bi-cross-modal Curriculum on Large-scale Benchmark](https://mlsanity.com/paper/2507.14449/) (2025)
- [M-SpecGene: Generalized Foundation Model for RGBT Multispectral Vision](https://mlsanity.com/paper/2507.16318/) (2025)
- [CST Anti-UAV: A Thermal Infrared Benchmark for Tiny UAV Tracking in Complex Scenes](https://mlsanity.com/paper/2507.23473/) (2025)
- [A Survey on Infrared Image and Video Sets](https://mlsanity.com/paper/2203.08581/) (2022)
- [Unsupervised Cross-Modal Distillation for Thermal Infrared Tracking](https://mlsanity.com/paper/2108.00187/) (2021)
- [PAD: Self-Supervised Pre-Training with Patchwise-Scale Adapter for Infrared Images](https://mlsanity.com/paper/2312.08192/) (2023)
- [Enhancing Thermal MOT: A Novel Box Association Method Leveraging Thermal Identity and Motion Similarity](https://mlsanity.com/paper/2411.12943/) (2024)
- [UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation](https://mlsanity.com/paper/2502.02257/) (2025)
- [Domain Adaptive SiamRPN++ for Object Tracking in the Wild](https://mlsanity.com/paper/2106.07862/) (2021)
- [Self-Supervised Learning for Real-World Object Detection: a Survey](https://mlsanity.com/paper/2410.07442/) (2024)
- [Progressive Domain Adaptation for Thermal Infrared Object Tracking](https://mlsanity.com/paper/2407.19430/) (2024)
- [SMMT: Siamese Motion Mamba with Self-attention for Thermal Infrared Target Tracking](https://mlsanity.com/paper/2505.04088/) (2025)
- [Coordinate-Aware Thermal Infrared Tracking Via Natural Language Modeling](https://mlsanity.com/paper/2407.08265/) (2024)
- [Performance Evaluation of Deep Learning-based Quadrotor UAV Detection and Tracking Methods](https://mlsanity.com/paper/2410.00285/) (2024)
- [Spatio-Temporal Progressive Attention Model for EEG Classification in Rapid Serial Visual Presentation Task](https://mlsanity.com/paper/2502.00730/) (2025)
- [RAMCT: Novel Region-adaptive Multi-channel Tracker with Iterative Tikhonov Regularization for Thermal Infrared Tracking](https://mlsanity.com/paper/2504.14278/) (2025)
- [FGSGT: Saliency-Guided Siamese Network Tracker Based on Key Fine-Grained Feature Information for Thermal Infrared Target Tracking](https://mlsanity.com/paper/2504.14309/) (2025)
- [DCFG: Diverse Cross-Channel Fine-Grained Feature Learning and Progressive Fusion Siamese Tracker for Thermal Infrared Target Tracking](https://mlsanity.com/paper/2504.14311/) (2025)
- [STARS: Sparse Learning Correlation Filter with Spatio-temporal Regularization and Super-resolution Reconstruction for Thermal Infrared Target Tracking](https://mlsanity.com/paper/2504.14491/) (2025)
- [SMTT: Novel Structured Multi-task Tracking with Graph-Regularized Sparse Representation for Robust Thermal Infrared Target Tracking](https://mlsanity.com/paper/2504.14566/) (2025)
- [DuGI-MAE: Improving Infrared Mask Autoencoders via Dual-Domain Guidance](https://mlsanity.com/paper/2512.04511/) (2025)
- [Learning Progressive Adaptation for Multi-Modal Tracking](https://mlsanity.com/paper/2603.21100/) (2026)
- [Revealing Physical-World Semantic Vulnerabilities: Universal Adversarial Patch for Infrared Vision-Language Models](https://mlsanity.com/paper/2604.03117/) (2026)

## Abstract (arXiv)

In this paper, we present a Large-Scale and high-diversity general Thermal InfraRed (TIR) Object Tracking Benchmark, called LSOTBTIR, which consists of an evaluation dataset and a training dataset with a total of 1,400 TIR sequences and more than 600K frames. We annotate the bounding box of objects in every frame of all sequences and generate over 730K bounding boxes in total. To the best of our knowledge, LSOTB-TIR is the largest and most diverse TIR object tracking benchmark to date. To evaluate a tracker on different attributes, we define 4 scenario attributes and 12 challenge attributes in the evaluation dataset. By releasing LSOTB-TIR, we encourage the community to develop deep learning based TIR trackers and evaluate them fairly and comprehensively. We evaluate and analyze more than 30 trackers on LSOTB-TIR to provide a series of baselines, and the results show that deep trackers achieve promising performance. Furthermore, we re-train several representative deep trackers on LSOTB-TIR, and their results demonstrate that the proposed training dataset significantly improves the performance of deep TIR trackers. Codes and dataset are available at https://github.com/QiaoLiuHit/LSOTB-TIR.