# Learning Motion Blur Robust Vision Transformers for Real-Time UAV Tracking

arXiv: https://arxiv.org/abs/2407.05383 · HTML: https://mlsanity.com/paper/2407.05383/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 55 of its 92 references that are in the map.
- First posted on arXiv 7 Jul 2024.

## Builds on (most cited first, 30 of 55)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [CornerNet: Detecting Objects as Paired Keypoints](https://mlsanity.com/paper/1808.01244/) (2018)
- [BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks](https://mlsanity.com/paper/1709.01686/) (2017)
- [Multimodal Learning with Transformers: A Survey](https://mlsanity.com/paper/2206.06488/) (2022)
- [AdaViT: Adaptive Tokens for Efficient Vision Transformer](https://mlsanity.com/paper/2112.07658/) (2021)
- [Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework](https://mlsanity.com/paper/2203.11991/) (2022)
- [BERT Loses Patience: Fast and Robust Inference with Early Exit](https://mlsanity.com/paper/2006.04152/) (2020)
- [EfficientFormer: Vision Transformers at MobileNet Speed](https://mlsanity.com/paper/2206.01191/) (2022)
- [ECO: Efficient Convolution Operators for Tracking](https://mlsanity.com/paper/1611.09224/) (2016)
- [Probabilistic Regression for Visual Tracking](https://mlsanity.com/paper/2003.12565/) (2020)
- [Ocean: Object-aware Anchor-free Tracking](https://mlsanity.com/paper/2006.10721/) (2020)
- [Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection](https://mlsanity.com/paper/1708.01642/) (2017)
- [The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking](https://mlsanity.com/paper/1804.00518/) (2018)
- [Backbone is All Your Need: A Simplified Architecture for Visual Object Tracking](https://mlsanity.com/paper/2203.05328/) (2022)
- [Generalized Relation Modeling for Transformer Tracking](https://mlsanity.com/paper/2303.16580/) (2023)
- [LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search](https://mlsanity.com/paper/2104.14545/) (2021)
- [Robust Object Modeling for Visual Tracking](https://mlsanity.com/paper/2308.05140/) (2023)
- [Transformer Tracking with Cyclic Shifting Window Attention](https://mlsanity.com/paper/2205.03806/) (2022)
- [HiFT: Hierarchical Feature Transformer for Aerial Tracking](https://mlsanity.com/paper/2108.00202/) (2021)
- [TCTrack: Temporal Contexts for Aerial Tracking](https://mlsanity.com/paper/2203.01885/) (2022)
- [Learn to Match: Automatic Matching Network Design for Visual Tracking](https://mlsanity.com/paper/2108.00803/) (2021)
- [Improved Techniques for Training Adaptive Deep Networks](https://mlsanity.com/paper/1908.06294/) (2019)
- [Learning Background-Aware Correlation Filters for Visual Tracking](https://mlsanity.com/paper/1703.04590/) (2017)
- [AutoTrack: Towards High-Performance Visual Tracking for UAV with Automatic Spatio-Temporal Regularization](https://mlsanity.com/paper/2003.12949/) (2020)
- [Correlation-Aware Deep Tracking](https://mlsanity.com/paper/2203.01666/) (2022)
- [FrameExit: Conditional Early Exiting for Efficient Video Recognition](https://mlsanity.com/paper/2104.13400/) (2021)

## Built on by (most cited first, 1 of 1)

- [Recursive Vision Transformer with Dynamic Depth and Width Adjustment for Resource-Efficient Image Semantic Communication](https://mlsanity.com/paper/2606.00114/) (2026)

## Abstract (arXiv)

Unmanned aerial vehicle (UAV) tracking is critical for applications like surveillance, search-and-rescue, and autonomous navigation. However, the high-speed movement of UAVs and targets introduces unique challenges, including real-time processing demands and severe motion blur, which degrade the performance of existing generic trackers. While single-stream vision transformer (ViT) architectures have shown promise in visual tracking, their computational inefficiency and lack of UAV-specific optimizations limit their practicality in this domain. In this paper, we boost the efficiency of this framework by tailoring it into an adaptive computation framework that dynamically exits Transformer blocks for real-time UAV tracking. The motivation behind this is that tracking tasks with fewer challenges can be adequately addressed using low-level feature representations. Simpler tasks can often be handled with less demanding, lower-level features. This approach allows the model use computational resources more efficiently by focusing on complex tasks and conserving resources for easier ones. Another significant enhancement introduced in this paper is the improved effectiveness of ViTs in handling motion blur, a common issue in UAV tracking caused by the fast movements of either the UAV, the tracked objects, or both. This is achieved by acquiring motion blur robust representations through enforcing invariance in the feature representation of the target with respect to simulated motion blur. We refer to our proposed approach as BDTrack. Extensive experiments conducted on four tracking benchmarks validate the effectiveness and versatility of our approach, demonstrating its potential as a practical and effective approach for real-time UAV tracking. Code is released at: https://github.com/wuyou3474/BDTrack.