English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

This short paper presents a preliminary analysis of three popular VisualQuestion Answering (VQA) models, namely ViLBERT, ViLT, and LXMERT, in thecontext of answering questions relating to driving scenarios. The performanceof these models is evaluated by comparing the similarity of responses toreference answers provided by computer vision experts. Model selection ispredicated on the analysis of transformer utilization in multimodalarchitectures. The results indicate that models incorporating cross-modalattention and late fusion techniques exhibit promising potential for generatingimproved answers within a driving perspective. This initial analysis serves asa launchpad for a forthcoming comprehensive comparative study involving nineVQA models and sets the scene for further investigations into the effectivenessof VQA model queries in self-driving scenarios. Supplementary material isavailable athttps://github.com/KaavyaRekanar/Towards-a-performance-analysis-on-pre-trained-VQA-models-for-autonomous-driving.

Towards a performance analysis on pre-trained Visual Question Answering models for autonomous driving