# VIT-Ped: Visionary Intention Transformer for Pedestrian Behavior Analysis

arXiv: https://arxiv.org/abs/2601.01989 · HTML: https://mlsanity.com/paper/2601.01989/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 11 references that are in the map.
- First posted on arXiv 5 Jan 2026.

## 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)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://mlsanity.com/paper/1506.04214/) (2015)
- [Joint Attention in Autonomous Driving (JAAD)](https://mlsanity.com/paper/1609.04741/) (2016)
- [PedFormer: Pedestrian Behavior Prediction via Cross-Modal Attention Modulation and Gated Multitask Learning](https://mlsanity.com/paper/2210.07886/) (2022)
- [IntFormer: Predicting pedestrian intention with the aid of the Transformer architecture](https://mlsanity.com/paper/2105.08647/) (2021)
- [PIP-Net: Pedestrian Intention Prediction in the Wild](https://mlsanity.com/paper/2402.12810/) (2024)

## Built on by (most cited first, 2 of 2)

- [INTENT: An LSTM Framework for Vehicle Intention Prediction in Intersection Scenarios with Comprehensive Ablation Analysis](https://mlsanity.com/paper/2607.08316/) (2026)
- [Swapping Faces, Saving Features: A Dual-Purpose Pipeline for Pedestrian Privacy in ITS](https://mlsanity.com/paper/2607.08402/) (2026)

## Abstract (arXiv)

Pedestrian Intention prediction is one of the key technologies in the transition from level 3 to level 4 autonomous driving. To understand pedestrian crossing behaviour, several elements and features should be taken into consideration to make the roads of tomorrow safer for everybody. We introduce a transformer / video vision transformer based algorithm of different sizes which uses different data modalities .We evaluated our algorithms on popular pedestrian behaviour dataset, JAAD, and have reached SOTA performance and passed the SOTA in metrics like Accuracy, AUC and F1-score. The advantages brought by different model design choices are investigated via extensive ablation studies.