all AI news
Predicting Visual Attention and Distraction During Visual Search Using Convolutional Neural Networks. (arXiv:2210.15093v1 [cs.CV])
cs.LG updates on arXiv.org arxiv.org
Most studies in computational modeling of visual attention encompass
task-free observation of images. Free-viewing saliency considers limited
scenarios of daily life. Most visual activities are goal-oriented and demand a
great amount of top-down attention control. Visual search task demands more
top-down control of attention, compared to free-viewing. In this paper, we
present two approaches to model visual attention and distraction of observers
during visual search. Our first approach adapts a light-weight free-viewing
saliency model to predict eye fixation density maps …
arxiv attention convolutional neural networks networks neural networks search visual attention