# MixFormerV2: Efficient Fully Transformer Tracking

arXiv: https://arxiv.org/abs/2305.15896 · HTML: https://mlsanity.com/paper/2305.15896/

## Key facts

- Cited by 57 papers in the map (data through 14 Oct 2026).
- Builds on 48 of its 56 references that are in the map.
- First posted on arXiv 25 May 2023.

## Builds on (most cited first, 30 of 48)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [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)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [Channel Pruning for Accelerating Very Deep Neural Networks](https://mlsanity.com/paper/1707.06168/) (2017)
- [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)
- [SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks](https://mlsanity.com/paper/1812.11703/) (2018)
- [HAQ: Hardware-Aware Automated Quantization with Mixed Precision](https://mlsanity.com/paper/1811.08886/) (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)
- [Probabilistic Regression for Visual Tracking](https://mlsanity.com/paper/2003.12565/) (2020)
- [Compressing Deep Convolutional Networks using Vector Quantization](https://mlsanity.com/paper/1412.6115/) (2014)
- [Siamese Box Adaptive Network for Visual Tracking](https://mlsanity.com/paper/2003.06761/) (2020)
- [AutoFormer: Searching Transformers for Visual Recognition](https://mlsanity.com/paper/2107.00651/) (2021)
- [SiamFC++: Towards Robust and Accurate Visual Tracking with Target Estimation Guidelines](https://mlsanity.com/paper/1911.06188/) (2019)
- [Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer](https://mlsanity.com/paper/2108.01390/) (2021)
- [Learning Target Candidate Association to Keep Track of What Not to Track](https://mlsanity.com/paper/2103.16556/) (2021)
- [Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark](https://mlsanity.com/paper/2103.16746/) (2021)
- [SwinTrack: A Simple and Strong Baseline for Transformer Tracking](https://mlsanity.com/paper/2112.00995/) (2021)

## Built on by (most cited first, 30 of 57)

- [Separable Self and Mixed Attention Transformers for Efficient Object Tracking](https://mlsanity.com/paper/2309.03979/) (2023)
- [StableDrag: Stable Dragging for Point-based Image Editing](https://mlsanity.com/paper/2403.04437/) (2024)
- [VastTrack: Vast Category Visual Object Tracking](https://mlsanity.com/paper/2403.03493/) (2024)
- [Transferring Foundation Models for Generalizable Robotic Manipulation](https://mlsanity.com/paper/2306.05716/) (2023)
- [WebUOT-1M: Advancing Deep Underwater Object Tracking with A Million-Scale Benchmark](https://mlsanity.com/paper/2405.19818/) (2024)
- [Cross-modulated Attention Transformer for RGBT Tracking](https://mlsanity.com/paper/2408.02222/) (2024)
- [UncTrack: Reliable Visual Object Tracking with Uncertainty-Aware Prototype Memory Network](https://mlsanity.com/paper/2503.12888/) (2025)
- [Motion-Guided Dual-Camera Tracker for Endoscope Tracking and Motion Analysis in a Mechanical Gastric Simulator](https://mlsanity.com/paper/2403.05146/) (2024)
- [General Compression Framework for Efficient Transformer Object Tracking](https://mlsanity.com/paper/2409.17564/) (2024)
- [EmMixformer: Mix transformer for eye movement recognition](https://mlsanity.com/paper/2401.04956/) (2024)
- [Improving Visual Object Tracking through Visual Prompting](https://mlsanity.com/paper/2409.18901/) (2024)
- [Lightweight Full-Convolutional Siamese Tracker](https://mlsanity.com/paper/2310.05392/) (2023)
- [Cross-Modal Object Tracking via Modality-Aware Fusion Network and A Large-Scale Dataset](https://mlsanity.com/paper/2312.14446/) (2023)
- [CST Anti-UAV: A Thermal Infrared Benchmark for Tiny UAV Tracking in Complex Scenes](https://mlsanity.com/paper/2507.23473/) (2025)
- [Exploring Dynamic Transformer for Efficient Object Tracking](https://mlsanity.com/paper/2403.17651/) (2024)
- [Underwater Camouflaged Object Tracking Meets Vision-Language SAM2](https://mlsanity.com/paper/2409.16902/) (2024)
- [MambaTrack: Exploiting Dual-Enhancement for Night UAV Tracking](https://mlsanity.com/paper/2411.15761/) (2024)
- [FocusTrack: A Self-Adaptive Local Sampling Algorithm for Efficient Anti-UAV Tracking](https://mlsanity.com/paper/2504.13604/) (2025)
- [An Experimental Study on Exploring Strong Lightweight Vision Transformers via Masked Image Modeling Pre-Training](https://mlsanity.com/paper/2404.12210/) (2024)
- [MambaXCTrack: Mamba-based Tracker with SSM Cross-correlation and Motion Prompt for Ultrasound Needle Tracking](https://mlsanity.com/paper/2411.08395/) (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)
- [Towards Low-Latency Event Stream-based Visual Object Tracking: A Slow-Fast Approach](https://mlsanity.com/paper/2505.12903/) (2025)
- [Exploiting Lightweight Hierarchical ViT and Dynamic Framework for Efficient Visual Tracking](https://mlsanity.com/paper/2506.20381/) (2025)
- [Uncertainty-Guided Inference-Time Depth Adaptation for Transformer-Based Visual Tracking](https://mlsanity.com/paper/2602.16160/) (2026)
- [RELO: Reinforcement Learning to Localize for Visual Object Tracking](https://mlsanity.com/paper/2605.07379/) (2026)
- [Spectral-Enhanced Transformers: Leveraging Large-Scale Pretrained Models for Hyperspectral Object Tracking](https://mlsanity.com/paper/2502.18748/) (2025)
- [ATSTrack: Enhancing Visual-Language Tracking by Aligning Temporal and Spatial Scales](https://mlsanity.com/paper/2507.00454/) (2025)
- [PlanarTrack: A high-quality and challenging benchmark for large-scale planar object tracking](https://mlsanity.com/paper/2510.23368/) (2025)
- [FARTrack: Fast Autoregressive Visual Tracking with High Performance](https://mlsanity.com/paper/2602.03214/) (2026)

## Abstract (arXiv)

Transformer-based trackers have achieved strong accuracy on the standard benchmarks. However, their efficiency remains an obstacle to practical deployment on both GPU and CPU platforms. In this paper, to overcome this issue, we propose a fully transformer tracking framework, coined as MixFormerV2, without any dense convolutional operation and complex score prediction module. Our key design is to introduce four special prediction tokens and concatenate them with the tokens from target template and search areas. Then, we apply the unified transformer backbone on these mixed token sequence. These prediction tokens are able to capture the complex correlation between target template and search area via mixed attentions. Based on them, we can easily predict the tracking box and estimate its confidence score through simple MLP heads. To further improve the efficiency of MixFormerV2, we present a new distillation-based model reduction paradigm, including dense-to-sparse distillation and deep-to-shallow distillation. The former one aims to transfer knowledge from the dense-head based MixViT to our fully transformer tracker, while the latter one is used to prune some layers of the backbone. We instantiate two types of MixForemrV2, where the MixFormerV2-B achieves an AUC of 70.6% on LaSOT and an AUC of 57.4% on TNL2k with a high GPU speed of 165 FPS, and the MixFormerV2-S surpasses FEAR-L by 2.7% AUC on LaSOT with a real-time CPU speed.