Evaluating Small Vision-Language Models on Distance-Dependent Traffic Perception

Vision-Language Models (VLMs) are becoming increasingly powerful, demonstrating strong performance on tasks that require both visual and textual understanding. Their strong generalisation abilities make them a promising component for automated driving systems, which must handle unexpected corner cas...

Полное описание

Библиографические подробности

Главные авторы:	Nikos Theodoridis, Tim Brophy, Reenu Mohandas, Ganesh Sistu, Fiachra Collins, Anthony Scanlan, Ciaran Eising
Формат:	Artigo
Язык:	Inglês
Опубликовано:	IEEE 2026-01-01
Серии:	IEEE Open Journal of Vehicular Technology
Предметы:	Automated driving perception Vision-Language Models VQA benchmark
Online-ссылка:	https://ieeexplore.ieee.org/document/11230063/
Метки:	Добавить метку Нет меток, Требуется 1-ая метка записи!