# Deformable Siamese Attention Networks for Visual Object Tracking

arXiv: https://arxiv.org/abs/2004.06711 · HTML: https://mlsanity.com/paper/2004.06711/

## Key facts

- Cited by 97 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Apr 2020.

## Built on by (most cited first, 30 of 97)

- [Transformer Tracking](https://mlsanity.com/paper/2103.15436/) (2021)
- [Learning Spatio-Temporal Transformer for Visual Tracking](https://mlsanity.com/paper/2103.17154/) (2021)
- [MixFormer: End-to-End Tracking with Iterative Mixed Attention](https://mlsanity.com/paper/2203.11082/) (2022)
- [Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking](https://mlsanity.com/paper/2103.11681/) (2021)
- [AiATrack: Attention in Attention for Transformer Visual Tracking](https://mlsanity.com/paper/2207.09603/) (2022)
- [Learning Target Candidate Association to Keep Track of What Not to Track](https://mlsanity.com/paper/2103.16556/) (2021)
- [SwinTrack: A Simple and Strong Baseline for Transformer Tracking](https://mlsanity.com/paper/2112.00995/) (2021)
- [Backbone is All Your Need: A Simplified Architecture for Visual Object Tracking](https://mlsanity.com/paper/2203.05328/) (2022)
- [Transforming Model Prediction for Tracking](https://mlsanity.com/paper/2203.11192/) (2022)
- [Generalized Relation Modeling for Transformer Tracking](https://mlsanity.com/paper/2303.16580/) (2023)
- [STMTrack: Template-free Visual Tracking with Space-time Memory Networks](https://mlsanity.com/paper/2104.00324/) (2021)
- [Robust Object Modeling for Visual Tracking](https://mlsanity.com/paper/2308.05140/) (2023)
- [Changer: Feature Interaction is What You Need for Change Detection](https://mlsanity.com/paper/2209.08290/) (2022)
- [Transformer Tracking with Cyclic Shifting Window Attention](https://mlsanity.com/paper/2205.03806/) (2022)
- [A Keypoint-based Global Association Network for Lane Detection](https://mlsanity.com/paper/2204.07335/) (2022)
- [Single-Model and Any-Modality for Video Object Tracking](https://mlsanity.com/paper/2311.15851/) (2023)
- [Correlation-Aware Deep Tracking](https://mlsanity.com/paper/2203.01666/) (2022)
- [3D Siamese Voxel-to-BEV Tracker for Sparse Point Clouds](https://mlsanity.com/paper/2111.04426/) (2021)
- [Compact Transformer Tracker with Correlative Masked Modeling](https://mlsanity.com/paper/2301.10938/) (2023)
- [Divert More Attention to Vision-Language Tracking](https://mlsanity.com/paper/2207.01076/) (2022)
- [Visual Object Tracking with Discriminative Filters and Siamese Networks: A Survey and Outlook](https://mlsanity.com/paper/2112.02838/) (2021)
- [SiamAPN++: Siamese Attentional Aggregation Network for Real-Time UAV Tracking](https://mlsanity.com/paper/2106.08816/) (2021)
- [Robust Visual Tracking by Segmentation](https://mlsanity.com/paper/2203.11191/) (2022)
- [Saliency-Associated Object Tracking](https://mlsanity.com/paper/2108.03637/) (2021)
- [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)
- [Learning Target-aware Representation for Visual Tracking via Informative Interactions](https://mlsanity.com/paper/2201.02526/) (2022)
- [Efficient Visual Tracking via Hierarchical Cross-Attention Transformer](https://mlsanity.com/paper/2203.13537/) (2022)
- [Where is my Wallet? Modeling Object Proposal Sets for Egocentric Visual Query Localization](https://mlsanity.com/paper/2211.10528/) (2022)
- [Diff-Tracker: Text-to-Image Diffusion Models are Unsupervised Trackers](https://mlsanity.com/paper/2407.08394/) (2024)

## Abstract (arXiv)

Siamese-based trackers have achieved excellent performance on visual object tracking. However, the target template is not updated online, and the features of the target template and search image are computed independently in a Siamese architecture. In this paper, we propose Deformable Siamese Attention Networks, referred to as SiamAttn, by introducing a new Siamese attention mechanism that computes deformable self-attention and cross-attention. The self attention learns strong context information via spatial attention, and selectively emphasizes interdependent channel-wise features with channel attention. The cross-attention is capable of aggregating rich contextual inter-dependencies between the target template and the search image, providing an implicit manner to adaptively update the target template. In addition, we design a region refinement module that computes depth-wise cross correlations between the attentional features for more accurate tracking. We conduct experiments on six benchmarks, where our method achieves new state of-the-art results, outperforming the strong baseline, SiamRPN++ [24], by 0.464->0.537 and 0.415->0.470 EAO on VOT 2016 and 2018. Our code is available at: https://github.com/msight-tech/research-siamattn.