Emotional expressions are inherently multimodal – integrating facial
beh...
Human-like attention as a supervisory signal to guide neural attention h...
We present VQA-MHUG - a novel 49-participant dataset of multimodal human...
We propose a novel method that leverages human fixations to visually dec...
A lack of corpora has so far limited advances in integrating human gaze ...
While neural networks with attention mechanisms have achieved superior
p...
We propose a machine reading comprehension model based on the
compare-ag...