# VISTA-DZ: Visual Semantic Trajectory Adaptation for Personalized Dilemma Zone Prediction

arXiv: https://arxiv.org/abs/2606.29548 · HTML: https://mlsanity.com/paper/2606.29548/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 47 references that are in the map.
- First posted on arXiv 28 Jun 2026.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [GPT-Driver: Learning to Drive with GPT](https://mlsanity.com/paper/2310.01415/) (2023)
- [A Learned Representation For Artistic Style](https://mlsanity.com/paper/1610.07629/) (2016)
- [VLP: Vision Language Planning for Autonomous Driving](https://mlsanity.com/paper/2401.05577/) (2024)
- [Driving Policy Transfer via Modularity and Abstraction](https://mlsanity.com/paper/1804.09364/) (2018)
- [Personalized Autonomous Driving with Large Language Models: Field Experiments](https://mlsanity.com/paper/2312.09397/) (2023)
- [Learning to Drive from Simulation without Real World Labels](https://mlsanity.com/paper/1812.03823/) (2018)
- [SIND: A Drone Dataset at Signalized Intersection in China](https://mlsanity.com/paper/2209.02297/) (2022)
- [PDB: Not All Drivers Are the Same -- A Personalized Dataset for Understanding Driving Behavior](https://mlsanity.com/paper/2503.06477/) (2025)
- [Driver Identification Using Automobile Sensor Data from a Single Turn](https://mlsanity.com/paper/1708.04636/) (2017)
- [Driver2vec: Driver Identification from Automotive Data](https://mlsanity.com/paper/2102.05234/) (2021)
- [Investigating Personalized Driving Behaviors in Dilemma Zones: Analysis and Prediction of Stop-or-Go Decisions](https://mlsanity.com/paper/2405.03873/) (2024)

## Abstract (arXiv)

Driver decision making in the dilemma zone at signalized intersections is safety critical, as vehicles approaching a yellow signal must decide whether to stop or proceed within limited time and distance margins. Accurate prediction of both stop-go decisions and decision timing is important for adaptive signal control, advanced driver assistance systems, and human-centered intelligent transportation applications. However, dilemma zone behavior is strongly driver dependent. Similar approach trajectories may lead to different decisions across drivers because of differences in risk preference, braking habit, and decision threshold. Existing personalized models often rely on handcrafted scalar descriptors, which provide useful but limited summaries of individual behavior. This paper proposes VISTA-DZ, a semantic-profile-conditioned framework for personalized stop-go and decision-time prediction. Historical trajectories are converted into visual representations, interpreted by a vision-language model to generate behavioral profiles, and encoded as semantic embeddings to condition a dual-output prediction network. The final model combines a bidirectional GRU encoder, driver-conditioned multi-head cross-attention, and Feature-wise Linear Modulation for temporal evidence selection and feature adaptation. Experiments on the SDZ dataset and a newly collected FDZ dataset show that VISTA-DZ outperforms trajectory-only and handcrafted personalization baselines, achieving 93.26% in-domain simulation accuracy and 90.22% mean accuracy across 20 held-out simulation drivers. Cross-domain results further show feasible zero-shot simulation-to-real transfer and better real-world generalization when simulation data are combined with limited field data.