Attention models are widely used in Vision-language (V-L) tasks to perform the visual-textual correlation. Humans such a correlation with strong linguistic understanding of visual world. However, even best performing attention model V-L lacks high-level understanding, thus creating semantic gap between modalities. In this paper, we propose an mechanism - Linguistically-aware (LAT) that leverage...

To compare the cortical dynamics of different oculomotor tasks, EEG and eye movements were recorded in 21 volunteers. Using a comprehensive approach, subjects were asked to perform saccadic tasks, which included a saccadic eye movement to a peripheral target (prosaccadic), a movement to the opposite side (antisaccadic), or maintain the gaze fixed (no-go). In mixed trials, prosaccadic, antisacca...