# Vision Transformer Based User Equipment Positioning

arXiv: https://arxiv.org/abs/2511.08549 · HTML: https://mlsanity.com/paper/2511.08549/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 24 references that are in the map.
- First posted on arXiv 11 Nov 2025.

## Builds on (most cited first, 8 of 8)

- [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)
- [DeepMIMO: A Generic Deep Learning Dataset for Millimeter Wave and Massive MIMO Applications](https://mlsanity.com/paper/1902.06435/) (2019)
- [ViWi: A Deep Learning Dataset Framework for Vision-Aided Wireless Communications](https://mlsanity.com/paper/1911.06257/) (2019)
- [Deep Convolutional Neural Networks for Massive MIMO Fingerprint-Based Positioning](https://mlsanity.com/paper/1708.06235/) (2017)
- [DyLoc: Dynamic Localization for Massive MIMO Using Predictive Recurrent Neural Networks](https://mlsanity.com/paper/2101.07848/) (2021)
- [MAP-CSI: Single-site Map-Assisted Localization Using Massive MIMO CSI](https://mlsanity.com/paper/2110.00654/) (2021)
- [Multi-Array 5G V2V Relative Positioning: Performance Bounds](https://mlsanity.com/paper/1808.07373/) (2018)

## Abstract (arXiv)

Recently, Deep Learning (DL) techniques have been used for User Equipment (UE) positioning. However, the key shortcomings of such models is that: i) they weigh the same attention to the entire input; ii) they are not well suited for the non-sequential data e.g., when only instantaneous Channel State Information (CSI) is available. In this context, we propose an attention-based Vision Transformer (ViT) architecture that focuses on the Angle Delay Profile (ADP) from CSI matrix. Our approach, validated on the `DeepMIMO' and `ViWi' ray-tracing datasets, achieves an Root Mean Squared Error (RMSE) of 0.55m indoors, 13.59m outdoors in DeepMIMO, and 3.45m in ViWi's outdoor blockage scenario. The proposed scheme outperforms state-of-the-art schemes by ~ 38%. It also performs substantially better than other approaches that we have considered in terms of the distribution of error distance.