How do we find what we are looking for? Even when the desired target is in the current field
of view, we need to search because fundamental limits on visual processing make it …

Detecting and segmenting salient objects from natural scenes, often referred to as salient
object detection, has attracted great interest in computer vision. While many models have …

The many successes of deep neural networks (DNNs) over the past decade have largely
been driven by computational scale rather than insights from biological intelligence. Here …

Understanding how people explore immersive virtual environments is crucial for many
applications, such as designing virtual reality (VR) content, developing new compression …

This paper explores gaze prediction in dynamic $360^ circ $ immersive videos, emph {ie},
based on the history scan path and VR contents, we predict where a viewer will look at an …

Understanding where people look in images is an important problem in computer vision.
Despite significant research, it remains unclear to what extent human fixations can be …

We extensively compare, qualitatively and quantitatively, 41 state-of-the-art models (29
salient object detection, 10 fixation prediction, 1 objectness, and 1 baseline) over seven …

Visual saliency models have enjoyed a big leap in performance in recent years, thanks to
advances in deep learning and large scale annotated data. Despite enormous effort and …

Humans typically move their eyes in “scanpaths” of fixations linked by saccades. Here we
present DeepGaze III, a new model that predicts the spatial location of consecutive fixations …

Deep neural networks (DNNs) have become powerful and increasingly ubiquitous tools to
model human cognition, and often produce similar behaviors. For example, with their …