Data-driven saliency has recently gained a lot of attention thanks to the use of convolutional neural networks for predicting gaze fixations. In this paper, we go beyond standard approaches to saliency prediction, in which gaze maps are computed with a feed-forward network, and present a novel model which can predict accurate saliency maps by incorporating neural attentive mechanisms. The core of our solution is a convolutional long short-term memory that focuses on the most salient regions of the input image to iteratively refine the predicted saliency map. In addition, to tackle the center bias typical of human eye fixations, our model can learn a set of prior maps generated with Gaussian functions. We show, through an extensive evaluation, that the proposed architecture outperforms the current state-of-the-art on public saliency prediction datasets. We further study the contribution of each key component to demonstrate their robustness on different scenarios.

Predicting human eye fixations via an LSTM-Based saliency attentive model

Serra G.;
2018-01-01

Abstract

Data-driven saliency has recently gained a lot of attention thanks to the use of convolutional neural networks for predicting gaze fixations. In this paper, we go beyond standard approaches to saliency prediction, in which gaze maps are computed with a feed-forward network, and present a novel model which can predict accurate saliency maps by incorporating neural attentive mechanisms. The core of our solution is a convolutional long short-term memory that focuses on the most salient regions of the input image to iteratively refine the predicted saliency map. In addition, to tackle the center bias typical of human eye fixations, our model can learn a set of prior maps generated with Gaussian functions. We show, through an extensive evaluation, that the proposed architecture outperforms the current state-of-the-art on public saliency prediction datasets. We further study the contribution of each key component to demonstrate their robustness on different scenarios.
File in questo prodotto:
File Dimensione Formato  
2018_TIP.pdf

non disponibili

Tipologia: Versione Editoriale (PDF)
Licenza: Non pubblico
Dimensione 4.76 MB
Formato Adobe PDF
4.76 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
2018_Journal_Saliency.pdf

Open Access dal 29/03/2021

Tipologia: Documento in Post-print
Licenza: Creative commons
Dimensione 6.28 MB
Formato Adobe PDF
6.28 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11390/1178506
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 311
  • ???jsp.display-item.citation.isi??? 256
social impact