Publication

Modeling Object Dissimilarity for Deep Saliency Prediction

Publications associées (32)

Saliency prediction in 360° architectural scenes: Performance and impact of daylight variations

Marilyne Andersen, Sabine Süsstrunk, Caroline Karmann, Bahar Aydemir, Kynthia Chamilothori, Seungryong Kim

Saliency models are image-based prediction models that estimate human visual attention. Such models, when applied to architectural spaces, could pave the way for design decisions where visual attention is taken into account. In this study, we tested the pe ...
2023

Is there an association between cognitive and visual decline?

Michael Herzog, Simona Adele Garobbio

Cognitive and visual abilities decline with age. Recently, it has been suggested that the risk to suffer from dementia is associated with decreased visual acuity. Two theories, the sensory deprivation theory (stating that visual impairments cause cognitive ...
2022

Unraveling brain interactions in vision: the example of crowding

Michael Herzog, Bogdan Draganski, Vitaly Chicherov, Maya Anna Jastrzebowska

In visual crowding, the presence of neighboring elements impedes the perception of a target. Crowding is traditionally explained with feedforward, local models. However, increasing the number of neighboring elements can decrease crowding, i.e., lead to unc ...
2021

Towards Modelling of Visual Saliency in Point Clouds for Immersive Applications

Touradj Ebrahimi, Evangelos Alexiou, Peisen Xu

Modelling human visual attention is of great importance in the field of computer vision and has been widely explored for 3D imaging. Yet, in the absence of ground truth data, it is unclear whether such predictions are in alignment with the actual human vie ...
2019

(Un)crowding modulates recurrent connectivity in the visual cortex

Michael Herzog, Vitaly Chicherov, Maya Anna Jastrzebowska

Introduction: In crowding, neighboring elements impede the perception of a target. Surprisingly, increasing the number of neighboring elements can decrease crowding, i.e., lead to uncrowding (Manassi et al., 2015). Few neuroimaging studies have explored th ...
2019

Preservation of visual function in an animal model of retinal degeneration using CRISPR/Cas9 gene editing

Diego Ghezzi, Paola Vagni, Tommaso Marchetti

Aims: Inherited Retinal Disorders represent a difficult target for gene therapy. This study exploits the possibility of using CRISPR/Cas9-based gene editing in photoreceptor progenitors to prevent cell death. We performed all the experiments on Rd10 mice, ...
2018

Preventing visual function loss in the rd10 mouse model of retinitis pigmentosa using gene editing

Diego Ghezzi, Paola Vagni

Currently, there is no known cure for retinitis pigmentosa (RP). Even if some treatments can slow down the progression of the disease, none of them can effectively stop retinal degeneration. This study exploits the possibility of an early intervention in p ...
2017

Gene editing in photoreceptor progenitors prevents visual function loss in a mouse model of retinal degeneration

Diego Ghezzi, Paola Vagni

Purpose:Currently, there is no known cure for Retinitis pigmentosa (RP). Even if some treatments can slow down the progression of the disease, none of them can effectively stop retinal degeneration. We exploited the possibility of an early intervention in ...
2017

A simple method to obtain visual attention data in head mounted virtual reality

Touradj Ebrahimi, Evgeniy Upenik

Automatic prediction of salient regions in images is a well developed topic in the field of computer vision. Yet, virtual reality omnidirectional visual content brings new challenges to this topic, due to a different representation of visual information an ...
IEEE2017

Daylight Management in Mediterranean Cities: When Shortage Is Not the Issue

Gloria Serra Coch

Natural resources such as daylight and sunlight are highly appreciated in countries with prevailing overcast skies. Taking advantage of this scarce resource contributes to saving energy on artificial lighting. In contrast to northern, southern European cit ...
2016

Graph Chatbot

Chattez avec Graph Search

Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.

AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.