# Learning Tracking Representations via Dual-Branch Fully Transformer Networks

arXiv: https://arxiv.org/abs/2112.02571 · HTML: https://mlsanity.com/paper/2112.02571/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 57 references that are in the map.
- First posted on arXiv 5 Dec 2021.

## Builds on (most cited first, 30 of 47)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [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)
- [CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification](https://mlsanity.com/paper/2103.14899/) (2021)
- [Going deeper with Image Transformers](https://mlsanity.com/paper/2103.17239/) (2021)
- [Fully-Convolutional Siamese Networks for Object Tracking](https://mlsanity.com/paper/1606.09549/) (2016)
- [Twins: Revisiting the Design of Spatial Attention in Vision Transformers](https://mlsanity.com/paper/2104.13840/) (2021)
- [TrackFormer: Multi-Object Tracking with Transformers](https://mlsanity.com/paper/2101.02702/) (2021)
- [GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild](https://mlsanity.com/paper/1810.11981/) (2018)
- [SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks](https://mlsanity.com/paper/1812.11703/) (2018)
- [Video Object Segmentation using Space-Time Memory Networks](https://mlsanity.com/paper/1904.00607/) (2019)
- [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)
- [DeepViT: Towards Deeper Vision Transformer](https://mlsanity.com/paper/2103.11886/) (2021)
- [ATOM: Accurate Tracking by Overlap Maximization](https://mlsanity.com/paper/1811.07628/) (2018)
- [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, 15 of 15)

- [MixFormer: End-to-End Tracking with Iterative Mixed Attention](https://mlsanity.com/paper/2203.11082/) (2022)
- [AiATrack: Attention in Attention for Transformer Visual Tracking](https://mlsanity.com/paper/2207.09603/) (2022)
- [Correlation-Aware Deep Tracking](https://mlsanity.com/paper/2203.01666/) (2022)
- [Efficient Visual Tracking via Hierarchical Cross-Attention Transformer](https://mlsanity.com/paper/2203.13537/) (2022)
- [Learning Occlusion-Robust Vision Transformers for Real-Time UAV Tracking](https://mlsanity.com/paper/2504.09228/) (2025)
- [Exploiting More Information in Sparse Point Cloud for 3D Single Object Tracking](https://mlsanity.com/paper/2210.00519/) (2022)
- [Multi-Tailed Vision Transformer for Efficient Inference](https://mlsanity.com/paper/2203.01587/) (2022)
- [Transformers in Single Object Tracking: An Experimental Survey](https://mlsanity.com/paper/2302.11867/) (2023)
- [P2P: Part-to-Part Motion Cues Guide a Strong Tracking Framework for LiDAR Point Clouds](https://mlsanity.com/paper/2407.05238/) (2024)
- [Correlation-Embedded Transformer Tracking: A Single-Branch Framework](https://mlsanity.com/paper/2401.12743/) (2024)
- [Mamba-Adaptor: State Space Model Adaptor for Visual Recognition](https://mlsanity.com/paper/2505.12685/) (2025)
- [Learning an Adaptive and View-Invariant Vision Transformer for Real-Time UAV Tracking](https://mlsanity.com/paper/2412.20002/) (2024)
- [TrackingMiM: Efficient Mamba-in-Mamba Serialization for Real-time UAV Object Tracking](https://mlsanity.com/paper/2507.01535/) (2025)
- [MixFormer: End-to-End Tracking with Iterative Mixed Attention](https://mlsanity.com/paper/2302.02814/) (2023)
- [Geometric-Topological Perception and Motion Prior for Real-Time Satellite Video Object Tracking](https://mlsanity.com/paper/2603.07564/) (2026)

## Abstract (arXiv)

We present a Siamese-like Dual-branch network based on solely Transformers for tracking. Given a template and a search image, we divide them into non-overlapping patches and extract a feature vector for each patch based on its matching results with others within an attention window. For each token, we estimate whether it contains the target object and the corresponding size. The advantage of the approach is that the features are learned from matching, and ultimately, for matching. So the features are aligned with the object tracking task. The method achieves better or comparable results as the best-performing methods which first use CNN to extract features and then use Transformer to fuse them. It outperforms the state-of-the-art methods on the GOT-10k and VOT2020 benchmarks. In addition, the method achieves real-time inference speed (about 40 fps) on one GPU. The code and models will be released.