# Exploring Lightweight Hierarchical Vision Transformers for Efficient Visual Tracking

arXiv: https://arxiv.org/abs/2308.06904 · HTML: https://mlsanity.com/paper/2308.06904/

## Key facts

- Cited by 53 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 56 references that are in the map.
- First posted on arXiv 14 Aug 2023.

## Builds on (most cited first, 30 of 46)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019)
- [Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet](https://mlsanity.com/paper/2101.11986/) (2021)
- [CvT: Introducing Convolutions to Vision Transformers](https://mlsanity.com/paper/2103.15808/) (2021)
- [MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer](https://mlsanity.com/paper/2110.02178/) (2021)
- [Fully-Convolutional Siamese Networks for Object Tracking](https://mlsanity.com/paper/1606.09549/) (2016)
- [GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild](https://mlsanity.com/paper/1810.11981/) (2018)
- [LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference](https://mlsanity.com/paper/2104.01136/) (2021)
- [SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks](https://mlsanity.com/paper/1812.11703/) (2018)
- [LaSOT: A High-quality Benchmark for Large-scale Single Object Tracking](https://mlsanity.com/paper/1809.07845/) (2018)
- [Transformer Tracking](https://mlsanity.com/paper/2103.15436/) (2021)
- [Learning Spatio-Temporal Transformer for Visual Tracking](https://mlsanity.com/paper/2103.17154/) (2021)
- [Learning Discriminative Model Prediction for Tracking](https://mlsanity.com/paper/1904.07220/) (2019)
- [TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild](https://mlsanity.com/paper/1803.10794/) (2018)
- [Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework](https://mlsanity.com/paper/2203.11991/) (2022)
- [ATOM: Accurate Tracking by Overlap Maximization](https://mlsanity.com/paper/1811.07628/) (2018)
- [MixFormer: End-to-End Tracking with Iterative Mixed Attention](https://mlsanity.com/paper/2203.11082/) (2022)
- [Fast Online Object Tracking and Segmentation: A Unifying Approach](https://mlsanity.com/paper/1812.05050/) (2018)
- [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)
- [Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking](https://mlsanity.com/paper/2103.11681/) (2021)

## Built on by (most cited first, 30 of 53)

- [Single-Model and Any-Modality for Video Object Tracking](https://mlsanity.com/paper/2311.15851/) (2023)
- [Lightweight Deep Learning for Resource-Constrained Environments: A Survey](https://mlsanity.com/paper/2404.07236/) (2024)
- [ZoomTrack: Target-aware Non-uniform Resizing for Efficient Visual Tracking](https://mlsanity.com/paper/2310.10071/) (2023)
- [Similarity-Guided Layer-Adaptive Vision Transformer for UAV Tracking](https://mlsanity.com/paper/2503.06625/) (2025)
- [Learning Occlusion-Robust Vision Transformers for Real-Time UAV Tracking](https://mlsanity.com/paper/2504.09228/) (2025)
- [LiteTrack: Layer Pruning with Asynchronous Feature Extraction for Lightweight and Efficient Visual Tracking](https://mlsanity.com/paper/2309.09249/) (2023)
- [Two-stream Beats One-stream: Asymmetric Siamese Network for Efficient Visual Tracking](https://mlsanity.com/paper/2503.00516/) (2025)
- [SDTrack: A Baseline for Event-based Tracking via Spiking Neural Networks](https://mlsanity.com/paper/2503.08703/) (2025)
- [General Compression Framework for Efficient Transformer Object Tracking](https://mlsanity.com/paper/2409.17564/) (2024)
- [Correlation-Embedded Transformer Tracking: A Single-Branch Framework](https://mlsanity.com/paper/2401.12743/) (2024)
- [Improving Visual Object Tracking through Visual Prompting](https://mlsanity.com/paper/2409.18901/) (2024)
- [Exploring Dynamic Transformer for Efficient Object Tracking](https://mlsanity.com/paper/2403.17651/) (2024)
- [RGB-Sonar Tracking Benchmark and Spatial Cross-Attention Transformer Tracker](https://mlsanity.com/paper/2406.07189/) (2024)
- [Fully Spiking Neural Networks for Unified Frame-Event Object Tracking](https://mlsanity.com/paper/2505.20834/) (2025)
- [SpikeTrack: A Spike-driven Framework for Efficient Visual Tracking](https://mlsanity.com/paper/2602.23963/) (2026)
- [Video Understanding: From Geometry and Semantics to Unified Models](https://mlsanity.com/paper/2603.17840/) (2026)
- [An Experimental Study on Exploring Strong Lightweight Vision Transformers via Masked Image Modeling Pre-Training](https://mlsanity.com/paper/2404.12210/) (2024)
- [Tracking Transforming Objects: A Benchmark](https://mlsanity.com/paper/2404.18143/) (2024)
- [TP-Spikformer: Token Pruned Spiking Transformer](https://mlsanity.com/paper/2603.00527/) (2026)
- [SSF-Net: Spatial-Spectral Fusion Network with Spectral Angle Awareness for Hyperspectral Object Tracking](https://mlsanity.com/paper/2403.05852/) (2024)
- [LoReTrack: Efficient and Accurate Low-Resolution Transformer Tracking](https://mlsanity.com/paper/2405.17660/) (2024)
- [Improving Accuracy and Generalization for Efficient Visual Tracking](https://mlsanity.com/paper/2411.18855/) (2024)
- [DARTer: Dynamic Adaptive Representation Tracker for Nighttime UAV Tracking](https://mlsanity.com/paper/2505.00752/) (2025)
- [Exploiting Lightweight Hierarchical ViT and Dynamic Framework for Efficient Visual Tracking](https://mlsanity.com/paper/2506.20381/) (2025)
- [Track-On2: Enhancing Online Point Tracking with Memory](https://mlsanity.com/paper/2509.19115/) (2025)
- [RELO: Reinforcement Learning to Localize for Visual Object Tracking](https://mlsanity.com/paper/2605.07379/) (2026)
- [AViTMP: A Tracking-Specific Transformer for Single-Branch Visual Tracking](https://mlsanity.com/paper/2310.19542/) (2023)
- [MambaNUT: Nighttime UAV Tracking via Mamba-based Adaptive Curriculum Learning](https://mlsanity.com/paper/2412.00626/) (2024)
- [FARTrack: Fast Autoregressive Visual Tracking with High Performance](https://mlsanity.com/paper/2602.03214/) (2026)
- [UETrack: A Unified and Efficient Framework for Single Object Tracking](https://mlsanity.com/paper/2603.01412/) (2026)

## Abstract (arXiv)

Transformer-based visual trackers have demonstrated significant progress owing to their superior modeling capabilities. However, existing trackers are hampered by low speed, limiting their applicability on devices with limited computational power. To alleviate this problem, we propose HiT, a new family of efficient tracking models that can run at high speed on different devices while retaining high performance. The central idea of HiT is the Bridge Module, which bridges the gap between modern lightweight transformers and the tracking framework. The Bridge Module incorporates the high-level information of deep features into the shallow large-resolution features. In this way, it produces better features for the tracking head. We also propose a novel dual-image position encoding technique that simultaneously encodes the position information of both the search region and template images. The HiT model achieves promising speed with competitive performance. For instance, it runs at 61 frames per second (fps) on the Nvidia Jetson AGX edge device. Furthermore, HiT attains 64.6% AUC on the LaSOT benchmark, surpassing all previous efficient trackers.