16 citations · 19 across the 2 of their papers we have counts for
1 paper · 2 filters
Ekta Sood, Fabian Kögel, Florian Strohm +2
We present VQA-MHUG - a novel 49-participant dataset of multimodal human gaze on both images and questions during visual question answering (VQA) collected using a high-speed eye t…