How Well Do Vision-Language Models Understand Sequential Driving Scenes? A Sensitivity Study

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Brusnicki, Roberto, Piccinini, Mattia, Betz, Johannes
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914583018471424
author Brusnicki, Roberto
Piccinini, Mattia
Betz, Johannes
author_facet Brusnicki, Roberto
Piccinini, Mattia
Betz, Johannes
contents Vision-Language Models (VLMs) are increasingly proposed for autonomous driving tasks, yet their performance on sequential driving scenes remains poorly characterized, particularly regarding how input configurations affect their capabilities. We introduce VENUSS (VLM Evaluation oN Understanding Sequential Scenes), a framework for systematic sensitivity analysis of VLM performance on sequential driving scenes, establishing baselines for future research. Building upon existing datasets, VENUSS extracts temporal sequences from driving videos, and generates structured evaluations across custom categories. By comparing 25+ existing VLMs across 2,600+ scenarios, we reveal how even top models achieve only 57% accuracy, not matching human performance under similar constraints (65%) and exposing significant capability gaps. Our analysis shows that VLMs excel with static object detection but struggle with understanding vehicle dynamics and temporal relations. VENUSS offers the first systematic sensitivity analysis of VLMs focused on how input image configurations - resolution, frame count, temporal intervals, spatial layouts, and presentation modes - affect performance on sequential driving scenes. Supplementary material available at https://TUM-AVS.github.io/VENUSS/.
format Preprint
id arxiv_https___arxiv_org_abs_2604_06750
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle How Well Do Vision-Language Models Understand Sequential Driving Scenes? A Sensitivity Study
Brusnicki, Roberto
Piccinini, Mattia
Betz, Johannes
Computer Vision and Pattern Recognition
68T45, 68T07, 68T50
Vision-Language Models (VLMs) are increasingly proposed for autonomous driving tasks, yet their performance on sequential driving scenes remains poorly characterized, particularly regarding how input configurations affect their capabilities. We introduce VENUSS (VLM Evaluation oN Understanding Sequential Scenes), a framework for systematic sensitivity analysis of VLM performance on sequential driving scenes, establishing baselines for future research. Building upon existing datasets, VENUSS extracts temporal sequences from driving videos, and generates structured evaluations across custom categories. By comparing 25+ existing VLMs across 2,600+ scenarios, we reveal how even top models achieve only 57% accuracy, not matching human performance under similar constraints (65%) and exposing significant capability gaps. Our analysis shows that VLMs excel with static object detection but struggle with understanding vehicle dynamics and temporal relations. VENUSS offers the first systematic sensitivity analysis of VLMs focused on how input image configurations - resolution, frame count, temporal intervals, spatial layouts, and presentation modes - affect performance on sequential driving scenes. Supplementary material available at https://TUM-AVS.github.io/VENUSS/.
title How Well Do Vision-Language Models Understand Sequential Driving Scenes? A Sensitivity Study
topic Computer Vision and Pattern Recognition
68T45, 68T07, 68T50
url https://arxiv.org/abs/2604.06750