After a decade of huge progress in computer vision using at processing schemes, new
architectures based on deep hierarchies [1] are currently gaining strength in the field. This …

Estimating the focus of attention of a person looking at an image or a video is a crucial step
which can enhance many vision-based inference mechanisms: image segmentation and …

Visual attention is the ability to select visual stimuli that are most behaviorally relevant
among the many others. It allows us to allocate our limited processing resources to the most …

In this paper it is studied how existing visual saliency models designed for 2D images can
be extended and applied to Omnidirectional images in the equirectangular format. Three …

Recent results suggest that state-of-the-art saliency models perform far from optimal in
predicting fixations. This lack in performance has been attributed to an inability to model the …

We present a set of metrics that utilize vision priors to effectively assess the performance of
saliency methods on image classification tasks. To understand behavior in deep learning …

In this Chapter, we describe how to model the top-down factors in human vision system.
Usually, such top-down factors should be learned from user data such as fixations or labeled …

State of the art approaches for saliency prediction are based on Fully Convolutional
Networks, in which saliency maps are built using the last layer. In contrast, we here present …

Many successful models for predicting attention in a scene involve three main steps:
convolution with a set of filters, a center-surround mechanism and spatial pooling to …

In this technical report, we present our publicly downloadable implementation of the
SALICON saliency model. At the time of this writing, SALICON is one of the top performing …