# Scenario Understanding of Traffic Scenes Through Large Visual Language Models

arXiv: https://arxiv.org/abs/2501.17131 · HTML: https://mlsanity.com/paper/2501.17131/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Driving VLMs and open-vocabulary detection, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 12 of its 22 references that are in the map.
- First posted on arXiv 28 Jan 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Driving VLMs and open-vocabulary detection](https://mlsanity.com/mllm/driving-vlms-and-open-vocabulary-detection/)

## Builds on (most cited first, 12 of 12)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities](https://mlsanity.com/paper/2308.02490/) (2023)
- [CogAgent: A Visual Language Model for GUI Agents](https://mlsanity.com/paper/2312.08914/) (2023)
- [InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition](https://mlsanity.com/paper/2309.15112/) (2023)
- [Multimodal 3D Object Detection on Unseen Domains](https://mlsanity.com/paper/2404.11764/) (2024)

## Built on by (most cited first, 8 of 8)

- [Foundation Models in Autonomous Driving: A Survey on Scenario Generation and Scenario Analysis](https://mlsanity.com/paper/2506.11526/) (2025)
- [Exploring the Roles of Large Language Models in Reshaping Transportation Systems: A Survey, Framework, and Roadmap](https://mlsanity.com/paper/2503.21411/) (2025)
- [Large Language Models and Their Applications in Roadway Safety and Mobility Enhancement: A Comprehensive Review](https://mlsanity.com/paper/2506.06301/) (2025)
- [Structured Labeling Enables Faster Vision-Language Models for End-to-End Autonomous Driving](https://mlsanity.com/paper/2506.05442/) (2025)
- [Semantic Edge-Cloud Communication for Real-Time Urban Traffic Surveillance with ViT and LLMs over Mobile Networks](https://mlsanity.com/paper/2509.21259/) (2025)
- [Structured Prompting and Multi-Agent Knowledge Distillation for Traffic Video Interpretation and Risk Inference](https://mlsanity.com/paper/2508.13439/) (2025)
- [SGTA: Scene-Graph Based Multi-Modal Traffic Agent for Video Understanding](https://mlsanity.com/paper/2604.03697/) (2026)
- [Behavior-Grounded Lane Representation Learning for Multi-Task Traffic Digital Twins](https://mlsanity.com/paper/2605.01901/) (2026)

## Abstract (arXiv)

Deep learning models for autonomous driving, encompassing perception, planning, and control, depend on vast datasets to achieve their high performance. However, their generalization often suffers due to domain-specific data distributions, making an effective scene-based categorization of samples necessary to improve their reliability across diverse domains. Manual captioning, though valuable, is both labor-intensive and time-consuming, creating a bottleneck in the data annotation process. Large Visual Language Models (LVLMs) present a compelling solution by automating image analysis and categorization through contextual queries, often without requiring retraining for new categories. In this study, we evaluate the capabilities of LVLMs, including GPT-4 and LLaVA, to understand and classify urban traffic scenes on both an in-house dataset and the BDD100K. We propose a scalable captioning pipeline that integrates state-of-the-art models, enabling a flexible deployment on new datasets. Our analysis, combining quantitative metrics with qualitative insights, demonstrates the effectiveness of LVLMs to understand urban traffic scenarios and highlights their potential as an efficient tool for data-driven advancements in autonomous driving.