# AiATrack: Attention in Attention for Transformer Visual Tracking

arXiv: https://arxiv.org/abs/2207.09603 · HTML: https://mlsanity.com/paper/2207.09603/

## Key facts

- Cited by 137 papers in the map (data through 14 Oct 2026).
- Builds on 54 of its 68 references that are in the map.
- First posted on arXiv 20 Jul 2022.

## Builds on (most cited first, 30 of 54)

- [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)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019)
- [ByteTrack: Multi-Object Tracking by Associating Every Detection Box](https://mlsanity.com/paper/2110.06864/) (2021)
- [CCNet: Criss-Cross Attention for Semantic Segmentation](https://mlsanity.com/paper/1811.11721/) (2018)
- [Fully-Convolutional Siamese Networks for Object Tracking](https://mlsanity.com/paper/1606.09549/) (2016)
- [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)
- [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)
- [TransTrack: Multiple Object Tracking with Transformer](https://mlsanity.com/paper/2012.15460/) (2020)
- [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)
- [Attention on Attention for Image Captioning](https://mlsanity.com/paper/1908.06954/) (2019)
- [ATOM: Accurate Tracking by Overlap Maximization](https://mlsanity.com/paper/1811.07628/) (2018)
- [Probabilistic Regression for Visual Tracking](https://mlsanity.com/paper/2003.12565/) (2020)
- [Associating Objects with Transformers for Video Object Segmentation](https://mlsanity.com/paper/2106.02638/) (2021)
- [Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking](https://mlsanity.com/paper/2103.11681/) (2021)
- [Ocean: Object-aware Anchor-free Tracking](https://mlsanity.com/paper/2006.10721/) (2020)
- [Acquisition of Localization Confidence for Accurate Object Detection](https://mlsanity.com/paper/1807.11590/) (2018)
- [Neighbourhood Consensus Networks](https://mlsanity.com/paper/1810.10510/) (2018)
- [How Much Position Information Do Convolutional Neural Networks Encode?](https://mlsanity.com/paper/2001.08248/) (2020)

## Built on by (most cited first, 30 of 137)

- [Emergent Correspondence from Image Diffusion](https://mlsanity.com/paper/2306.03881/) (2023)
- [ODTrack: Online Dense Temporal Token Learning for Visual Tracking](https://mlsanity.com/paper/2401.01686/) (2024)
- [SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory](https://mlsanity.com/paper/2411.11922/) (2024)
- [Generalized Relation Modeling for Transformer Tracking](https://mlsanity.com/paper/2303.16580/) (2023)
- [Robust Object Modeling for Visual Tracking](https://mlsanity.com/paper/2308.05140/) (2023)
- [Autoregressive Queries for Adaptive Tracking with Spatio-TemporalTransformers](https://mlsanity.com/paper/2403.10574/) (2024)
- [Event Stream-based Visual Object Tracking: A High-Resolution Benchmark Dataset and A Novel Baseline](https://mlsanity.com/paper/2309.14611/) (2023)
- [HIPTrack: Visual Tracking with Historical Prompts](https://mlsanity.com/paper/2311.02072/) (2023)
- [Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance](https://mlsanity.com/paper/2403.05231/) (2024)
- [Single-Model and Any-Modality for Video Object Tracking](https://mlsanity.com/paper/2311.15851/) (2023)
- [OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuning](https://mlsanity.com/paper/2403.09634/) (2024)
- [Towards Unified Token Learning for Vision-Language Tracking](https://mlsanity.com/paper/2308.14103/) (2023)
- [State Space Model for New-Generation Network Alternative to Transformers: A Survey](https://mlsanity.com/paper/2404.09516/) (2024)
- [Exploring Lightweight Hierarchical Vision Transformers for Efficient Visual Tracking](https://mlsanity.com/paper/2308.06904/) (2023)
- [Revisiting Color-Event based Tracking: A Unified Network, Dataset, and Metric](https://mlsanity.com/paper/2211.11010/) (2022)
- [Explicit Visual Prompts for Visual Object Tracking](https://mlsanity.com/paper/2401.03142/) (2024)
- [SDSTrack: Self-Distillation Symmetric Adapter Learning for Multi-Modal Visual Object Tracking](https://mlsanity.com/paper/2403.16002/) (2024)
- [Frame-Event Alignment and Fusion Network for High Frame Rate Tracking](https://mlsanity.com/paper/2305.15688/) (2023)
- [Cross-modal Orthogonal High-rank Augmentation for RGB-Event Transformer-trackers](https://mlsanity.com/paper/2307.04129/) (2023)
- [Exploring Enhanced Contextual Information for Video-Level Object Tracking](https://mlsanity.com/paper/2412.11023/) (2024)
- [CiteTracker: Correlating Image and Text for Visual Tracking](https://mlsanity.com/paper/2308.11322/) (2023)
- [Towards Universal Modal Tracking with Online Dense Temporal Token Learning](https://mlsanity.com/paper/2507.20177/) (2025)
- [Towards Real-World Visual Tracking with Temporal Contexts](https://mlsanity.com/paper/2308.10330/) (2023)
- [Swift Parameter-free Attention Network for Efficient Super-Resolution](https://mlsanity.com/paper/2311.12770/) (2023)
- [SPMTrack: Spatio-Temporal Parameter-Efficient Fine-Tuning with Mixture of Experts for Scalable Visual Tracking](https://mlsanity.com/paper/2503.18338/) (2025)
- [Exploring Decoupled Spatio-Temporal Consistency Learning and Self-Prompting Evolution for Self-Supervised Tracking](https://mlsanity.com/paper/2507.21606/) (2025)
- [DropMAE: Learning Representations via Masked Autoencoders with Spatial-Attention Dropout for Temporal Matching Tasks](https://mlsanity.com/paper/2304.00571/) (2023)
- [OmniVid: A Generative Framework for Universal Video Understanding](https://mlsanity.com/paper/2403.17935/) (2024)
- [Mamba-FETrack: Frame-Event Tracking via State Space Model](https://mlsanity.com/paper/2404.18174/) (2024)
- [Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Tracking](https://mlsanity.com/paper/2304.14394/) (2023)

## Abstract (arXiv)

Transformer trackers have achieved impressive advancements recently, where the attention mechanism plays an important role. However, the independent correlation computation in the attention mechanism could result in noisy and ambiguous attention weights, which inhibits further performance improvement. To address this issue, we propose an attention in attention (AiA) module, which enhances appropriate correlations and suppresses erroneous ones by seeking consensus among all correlation vectors. Our AiA module can be readily applied to both self-attention blocks and cross-attention blocks to facilitate feature aggregation and information propagation for visual tracking. Moreover, we propose a streamlined Transformer tracking framework, dubbed AiATrack, by introducing efficient feature reuse and target-background embeddings to make full use of temporal references. Experiments show that our tracker achieves state-of-the-art performance on six tracking benchmarks while running at a real-time speed.