most citedOptimizing Visual Question Answering Models for Driving: Bridging the Gap Between Human and Machine Attention Patterns

3 citations · 4 across the 2 of their papers we have counts for

collaborators

2 papers

cs.CV2024★ 3 cited

Optimizing Visual Question Answering Models for Driving: Bridging the Gap Between Human and Machine Attention Patterns

Kaavya Rekanar, Martin Hayes, Ganesh Sistu +1

Visual Question Answering (VQA) models play a critical role in enhancing the perception capabilities of autonomous driving systems by allowing vehicles to analyze visual inputs alo…

cs.CV2023★ 1 cited

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

Kaavya Rekanar, Ciarán Eising, Ganesh Sistu +1

This short paper presents a preliminary analysis of three popular Visual Question Answering (VQA) models, namely ViLBERT, ViLT, and LXMERT, in the context of answering questions re…