# Can Vision-Language Models Understand and Interpret Dynamic Gestures from Pedestrians? Pilot Datasets and Exploration Towards Instructive Nonverbal Commands for Cooperative Autonomous Vehicles

arXiv: https://arxiv.org/abs/2504.10873 · HTML: https://mlsanity.com/paper/2504.10873/

## Key facts

- Cited by 9 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 24 of its 40 references that are in the map.
- First posted on arXiv 15 Apr 2025.

## Placed in

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

## Builds on (most cited first, 24 of 24)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs](https://mlsanity.com/paper/2406.07476/) (2024)
- [VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding](https://mlsanity.com/paper/2501.13106/) (2025)
- [End-to-end Autonomous Driving: Challenges and Frontiers](https://mlsanity.com/paper/2306.16927/) (2023)
- [DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Model](https://mlsanity.com/paper/2310.01412/) (2023)
- [Multi-Modal Fusion Transformer for End-to-End Autonomous Driving](https://mlsanity.com/paper/2104.09224/) (2021)
- [LMDrive: Closed-Loop End-to-End Driving with Large Language Models](https://mlsanity.com/paper/2312.07488/) (2023)
- [CoVLA: Comprehensive Vision-Language-Action Dataset for Autonomous Driving](https://mlsanity.com/paper/2408.10845/) (2024)
- [Autonomous Vehicles that Interact with Pedestrians: A Survey of Theory and Practice](https://mlsanity.com/paper/1805.11773/) (2018)
- [Foundation Models for Video Understanding: A Survey](https://mlsanity.com/paper/2405.03770/) (2024)
- [Trajectory Prediction in Autonomous Driving with a Lane Heading Auxiliary Loss](https://mlsanity.com/paper/2011.06679/) (2020)
- [Towards Explainable, Safe Autonomous Driving with Language Embeddings for Novelty Identification and Active Learning: Framework and Experimental Analysis with Real-World Data Sets](https://mlsanity.com/paper/2402.07320/) (2024)
- [Traffic Control Gesture Recognition for Autonomous Vehicles](https://mlsanity.com/paper/2007.16072/) (2020)
- [Language-Driven Active Learning for Diverse Open-Set 3D Object Detection](https://mlsanity.com/paper/2404.12856/) (2024)
- [doScenes: An Autonomous Driving Dataset with Natural Language Instruction for Human Interaction and Vision-Language Navigation](https://mlsanity.com/paper/2412.05893/) (2024)
- [Salient Sign Detection In Safe Autonomous Driving: AI Which Reasons Over Full Visual Context](https://mlsanity.com/paper/2301.05804/) (2023)
- [On Salience-Sensitive Sign Classification in Autonomous Vehicle Path Planning: Experimental Explorations with a Novel Dataset](https://mlsanity.com/paper/2112.00942/) (2021)
- [Robust Traffic Light Detection Using Salience-Sensitive Loss: Computational Framework and Evaluations](https://mlsanity.com/paper/2305.04516/) (2023)
- [COOOL: Challenge Of Out-Of-Label A Novel Benchmark for Autonomous Driving](https://mlsanity.com/paper/2412.05462/) (2024)
- [Ensemble Learning for Fusion of Multiview Vision with Occlusion and Missing Information: Framework and Evaluations with Real-World Data and Applications in Driver Hand Activity Recognition](https://mlsanity.com/paper/2301.12592/) (2023)
- [GestLLM: Advanced Hand Gesture Interpretation via Large Language Models for Human-Robot Interaction](https://mlsanity.com/paper/2501.07295/) (2025)

## Built on by (most cited first, 9 of 9)

- [Towards a Multi-Agent Vision-Language System for Zero-Shot Novel Hazardous Object Detection for Autonomous Driving Safety](https://mlsanity.com/paper/2504.13399/) (2025)
- [Jailbreaking Large Vision Language Models in Intelligent Transportation Systems](https://mlsanity.com/paper/2511.13892/) (2025)
- [GRASP: Learning to Ground Social Reasoning in Multi-Person Non-Verbal Interactions](https://mlsanity.com/paper/2605.15764/) (2026)
- [When Stopping Fails: Rethinking Minimal Risk Conditions through Human-Interactive Autonomous Driving for Safe Transportation Systems](https://mlsanity.com/paper/2606.29115/) (2026)
- [Beyond General Prompts: Automated Prompt Refinement using Contrastive Class Alignment Scores for Disambiguating Objects in Vision-Language Models](https://mlsanity.com/paper/2505.09139/) (2025)
- [Understanding Pedestrian Gesture Misrecognition: Insights from Vision-Language Model Reasoning](https://mlsanity.com/paper/2508.06801/) (2025)
- [Looking and Listening Inside and Outside: Multimodal Artificial Intelligence Systems for Driver Safety Assessment and Intelligent Vehicle Decision-Making](https://mlsanity.com/paper/2602.07668/) (2026)
- [SafeGesture: Evaluating Fine-Grained Hand Gesture Understanding in Vision-Language Models through Scenario-Conditioned Safety Interpretation](https://mlsanity.com/paper/2608.16081/) (2026)
- [doPlan: A Variable-Horizon Dataset for Multi-Stage Language-Conditioned Planning in Autonomous Driving](https://mlsanity.com/paper/2609.38028/) (2026)

## Abstract (arXiv)

In autonomous driving, it is crucial to correctly interpret traffic gestures (TGs), such as those of an authority figure providing orders or instructions, or a pedestrian signaling the driver, to ensure a safe and pleasant traffic environment for all road users. This study investigates the capabilities of state-of-the-art vision-language models (VLMs) in zero-shot interpretation, focusing on their ability to caption and classify human gestures in traffic contexts. We create and publicly share two custom datasets with varying formal and informal TGs, such as 'Stop', 'Reverse', 'Hail', etc. The datasets are "Acted TG (ATG)" and "Instructive TG In-The-Wild (ITGI)". They are annotated with natural language, describing the pedestrian's body position and gesture. We evaluate models using three methods utilizing expert-generated captions as baseline and control: (1) caption similarity, (2) gesture classification, and (3) pose sequence reconstruction similarity. Results show that current VLMs struggle with gesture understanding: sentence similarity averages below 0.59, and classification F1 scores reach only 0.14-0.39, well below the expert baseline of 0.70. While pose reconstruction shows potential, it requires more data and refined metrics to be reliable. Our findings reveal that although some SOTA VLMs can interpret zero-shot human traffic gestures, none are accurate and robust enough to be trustworthy, emphasizing the need for further research in this domain.